WO2012090198A2 - An apparatus and method for automatic detection of pathogens - Google Patents

An apparatus and method for automatic detection of pathogens Download PDF

Info

Publication number
WO2012090198A2
WO2012090198A2 PCT/IL2011/000973 IL2011000973W WO2012090198A2 WO 2012090198 A2 WO2012090198 A2 WO 2012090198A2 IL 2011000973 W IL2011000973 W IL 2011000973W WO 2012090198 A2 WO2012090198 A2 WO 2012090198A2
Authority
WO
WIPO (PCT)
Prior art keywords
cartridge
sample
images
image
image processing
Prior art date
Application number
PCT/IL2011/000973
Other languages
French (fr)
Other versions
WO2012090198A3 (en
Inventor
Ido Bachelet
Joseph Joel POLLAK
Daniel Levner
Yonatan BILU
Noam YORAV-RAPHAEL
Original Assignee
Parasight Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Parasight Ltd filed Critical Parasight Ltd
Priority to IN5069DEN2012 priority Critical patent/IN2012DN05069A/en
Publication of WO2012090198A2 publication Critical patent/WO2012090198A2/en
Publication of WO2012090198A3 publication Critical patent/WO2012090198A3/en
Priority to CN201280070778.9A priority patent/CN104169719B/en
Priority to EP12861524.2A priority patent/EP2798350B1/en
Priority to BR112014016072-4A priority patent/BR112014016072B1/en
Priority to PCT/IL2012/050556 priority patent/WO2013098821A1/en
Priority to US14/369,251 priority patent/US10640807B2/en
Priority to CN201710065911.6A priority patent/CN106840812B/en
Priority to ZA2014/05506A priority patent/ZA201405506B/en
Priority to US16/705,941 priority patent/US11584950B2/en
Priority to US18/100,181 priority patent/US20230159982A1/en

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
    • B01L3/00—Containers or dishes for laboratory use, e.g. laboratory glassware; Droppers
    • B01L3/50—Containers for the purpose of retaining a material to be analysed, e.g. test tubes
    • B01L3/502—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures
    • B01L3/5027—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures by integrated microfluidic structures, i.e. dimensions of channels and chambers are such that surface tension forces are important, e.g. lab-on-a-chip
    • B01L3/502715—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures by integrated microfluidic structures, i.e. dimensions of channels and chambers are such that surface tension forces are important, e.g. lab-on-a-chip characterised by interfacing components, e.g. fluidic, electrical, optical or mechanical interfaces
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N15/14—Optical investigation techniques, e.g. flow cytometry
    • G01N15/1429—Signal processing
    • G01N15/1433—Signal processing using image recognition
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/21—Polarisation-affecting properties
    • G01N21/23—Bi-refringence
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/59—Transmissivity
    • G01N21/5907—Densitometers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N21/645—Specially adapted constructive features of fluorimeters
    • G01N21/6456—Spatial resolved fluorescence measurements; Imaging
    • G01N21/6458—Fluorescence microscopy
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
    • B01L2300/00—Additional constructional details
    • B01L2300/08—Geometry, shape and general structure
    • B01L2300/0809—Geometry, shape and general structure rectangular shaped
    • B01L2300/0816—Cards, e.g. flat sample carriers usually with flow in two horizontal directions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
    • B01L2300/00—Additional constructional details
    • B01L2300/08—Geometry, shape and general structure
    • B01L2300/0861—Configuration of multiple channels and/or chambers in a single devices
    • B01L2300/0864—Configuration of multiple channels and/or chambers in a single devices comprising only one inlet and multiple receiving wells, e.g. for separation, splitting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/01—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials specially adapted for biological cells, e.g. blood cells
    • G01N2015/016—White blood cells
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/10—Investigating individual particles
    • G01N2015/1006—Investigating individual particles for cytology
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/59—Transmissivity
    • G01N21/5907—Densitometers
    • G01N2021/5957—Densitometers using an image detector type detector, e.g. CCD
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N2021/6417—Spectrofluorimetric devices
    • G01N2021/6419—Excitation at two or more wavelengths
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N2021/6417—Spectrofluorimetric devices
    • G01N2021/6421—Measuring at two or more wavelengths
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/04—Recognition of patterns in DNA microarrays

Definitions

  • the present invention relates to the field of medical devices. More particularly, the invention relates to an apparatus and method for automatically detecting and identifying pathogens, and particularly parasites, in bodily fluid or tissue samples.
  • Parasites represent a group of extremely abundant human pathogens, which is estimated to infect around one third of the world population. These diseases are source of immense suffering and millions of deaths annually worldwide. In the US alone 11 million new cases of parasitic infections are diagnosed each year. The economic burden imposed by parasitic infections is immense and impossible to calculate.
  • the "gold standard" for diagnosis of most types of parasites is manual identification under a microscope of stained smears of biological fluids. Most frequently, peripheral blood, is used, or in other instances, lymphatic fluid and cerebrospinal fluid (CSF). This method is laborious and requires highly trained personnel, and as a result it is typically low-throughput and expensive.
  • the method of the invention can be utilized to detect the presence of parasites, or other microorganisms.
  • the method of the invention includes steps of automated microscopy and machine-vision algorithms.
  • the method of the invention can be utilized, for instance, to detect the presence of blood parasites, such as those associated with Malaria and Babesiosis.
  • the invention provides an apparatus for automatic detection of pathogens within a sample, comprising:
  • a cartridge support frame for receiving and supporting a cartridge having a sample within or thereupon;
  • an optical imaging system having an optical path and comprising: at least one light source, at least one lens, and at least one digital camera; wherein the cartridge support frame is located within or may be moved into the optical path, such that images of the sample may be captured by the at least one digital camera;
  • At least one processor interacting with and activating at least one of components a)-b); wherein the processor is adapted to perform image processing using classification algorithms on visual classification features to detect one or more suspected pathogens, when present, in the sample.
  • the apparatus wherein the cartridge support frame is coupled to a moveable stage, movable in at least one dimension.
  • optical imaging system further comprises a focus actuator for focusing upon an image.
  • optical imaging system further comprises a plurality of objective lenses of varied magnification.
  • optical imaging system further comprises: at least one optical filter or at least one dichroic beamsplitters/mirror, for exciting or detecting fluorescence.
  • optical imaging system further comprises an actuator to switch the optical filters or the dichroic beamsplitter/mirror in and out of the optical path.
  • the apparatus wherein the at least one processor performs at least one of the following:
  • the apparatus wherein at least one of the at least one processor outputs a result that includes at least one of the following: the presence or absence of a pathogen; the species of pathogen; the number or concentration of pathogens detected; the life stage of the pathogen; a finding of anemia; a finding of an unusual white blood cell count; and information on the quality of the sample.
  • the apparatus wherein the processor outputs one or more images of suspected pathogens.
  • pathogen is a parasite
  • the apparatus wherein the processor is present in an external computer wired to at least one of the following: to one or more internal processors, and to the digital camera.
  • the apparatus wherein the processor is connected via a data network to at least one of the following: to one or more internal processors, and to the digital camera..
  • the apparatus wherein one or more images captured by the apparatus are sent to a remote server for image processing at a remote location.
  • the invention provides a cartridge for supporting a sample, wherein the cartridge comprises at least one microfluidic channel upon the cartridge.
  • the cartridge wherein the cartridge has dimensions of 25mm x 75mm.
  • the cartridge having a plurality of microfluidic channels, and the channels are connected to one another to facilitate simultaneous filling.
  • the cartridge wherein the microfluidic channel has a channel height permitting only a single layer of cells to fill the channel height, thereby presenting a monolayer for imaging.
  • the cartridge wherein the channel is manufactured with a hydrophilic material or is treated to promote capillary filling.
  • a staining reagent present in a form selected from: a liquid, solid, a coating, and dried within the cartridge.
  • the cartridge wherein the cartridge comprises a secondary application orifice allowing addition of an additional reagent to the sample after sample application is completed.
  • the cartridge wherein the cartridge is sterile.
  • the invention also provides a method for automatic detection of pathogens within a sample, comprising: performing image processing of at least one digital image captured using classification algorithms, the image processing including extracting visual classification features from the image.
  • the method comprising the step of obtaining one or more digital images of a sample using an automated microscopy system comprising at least one light source, at least one lens, and at least one digital camera; the images are obtained prior to image processing.
  • the sample is a slide selected from one or more of the following: a blood smear (thin or thick), a fecal smear, a lympathic smear, a cerebrospinal fluid smear, and a tissue biopsy.
  • the method comprising the step of preparing a sample within a cartridge, performed prior to the imaging
  • the cartridge comprises microfluidic channels for creating a monolayer of cells in at least one area, in order to facilitate imaging.
  • the preparing the sample further comprises staining the sample with one or more stains.
  • the method, wherein the one or more stains are selected to affect a change in at least one of the following: optical absorption, opaqueness, scattering, and color of structures within a sample.
  • the one or more stains include acridine orange, and wherein a plurality of the one or more digital images are taken using configurations that allow discerning respective staining of DNA and RNA.
  • the method, wherein the one or more stains include Giemsa, Romanowsky or related stains.
  • the method wherein the sample is anticoagulated before or after application to the slide or cartridge.
  • the method wherein the sample is anticoagulated by preloading one or more corresponding reagents onto the cartridge.
  • the method, wherein the obtaining one or more digital images includes moving the slide or cartridge with respect to the automated microscopy system in order to image multiple locations within a sample.
  • the method, wherein the obtaining one or more digital images includes automatically focusing the sample for the digital images.
  • the focusing includes moving at least one of the following: the at least one lens, the slide or cartridge, and the at least one component of the at least one digital camera.
  • the method wherein the obtaining one or more digital images employs at least one of the following: brightfield, darkfield, phase-contrast, any interference-contrast, and fluorescence microscopy and any combination thereof.
  • the method wherein the obtaining one or more digital images employs a plurality of objective lenses of varied magnification.
  • the method wherein the obtaining one or more digital images employs one or more optical filters or one or more dichroic beamsplitters/mirrors for exciting or detecting fluorescence.
  • the method, wherein the obtaining one or more digital images includes obtaining a plurality of digital images for at least one sample location and employing a plurality of microscopy methods.
  • the method wherein the plurality of microscopy methods comprise different fluorescence excitations and/or emissions.
  • the method wherein the obtaining one or more digital images includes a processor that interacts with and activates mechanical and optical components by performing at least one of the following:
  • the image processing outputs a result that includes at least one of the following: the presence or absence of a pathogen; the species of pathogen; the number or concentration of pathogens detected; the life stage of the pathogen; a finding of anemia; a finding of an unusual white blood cell count; and information on the quality of the sample.
  • the method wherein at least one of the one or more digital images is captured at a first location and is processed using a processor located at a second location.
  • classification features include one or more of the following: motion, size, shape, coloring, contrast, location in respect to additional biological structures, presence of internal structures, presence of extracellular structures, the aspect ratio, the optical density, florescence at predetermined wavelengths, optical birefringence, clustering behavior, and pattern matching.
  • the image processing includes searching at least one of the one or more digital images for at least one patch which is likely to contain a target in the digital image and marking it as a candidate.
  • the image processing further includes at least one of the following:
  • the method wherein the searching for at least one patch which is likely to contain a target is performed using at least one of the following: pattern matching, model matching, motion detection, high florescence segmenting and clustering, and multi-frame tracking.
  • the method wherein the image processing is performed using at least one of the following modules: a single frame classification cascade module; a multi- frame candidate construction module; a multi-frame candidate tracking module; a multi-frame candidate classification module; a sample classification module; a motion field construction module; an image verification module; a camera control model; and a masking module.
  • the method wherein the image processing includes finding the motion vector of the background of the image of the sample, and where the motion vector is used to reconstruct the image in order to compensate for the background motion.
  • the method wherein the image processing identifies at least one region within at least one of the digital images as a region not likely to contain a target.
  • the invention provides computer readable storage medium that includes software capable of performing the image processing method of the invention
  • the invention also provides computer readable storage medium that includes software capable of activating the apparatus of the invention.
  • Fig. 1 is an external view of the apparatus of the invention.
  • Fig. 2 is an isometric diagram of the central internal components of the apparatus.
  • Fig. 3 illustrates a cartridge for analysis, resting within a cartridge support frame.
  • Fig. 4 is an isometric view is shown, in which upper components have been removed for optimal viewing of the internal elements of the device.
  • Fig. 5 is a side view of the right side of the apparatus, showing components such as the battery, base for mounting and adjusting angled mirror, support components and sliding connectors of moveable stage.
  • Fig. 6 is a rear view of the apparatus, showing communication ports and electrical power inlet.
  • Fig. 7 is an image captured showing Trypanosoma brucei parasites in a peripheral blood sample, for analysis using the invention.
  • Fig. 8 is a florescent image of Trypanosoma brucei parasites. Automatic detection of the parasites was successful using the apparatus of the invention.
  • Fig. 9 illustrates an enlarged view of a cartridge, according to one embodiment.
  • the present invention discloses an automated apparatus for detection of parasitic and other pathogenic infection in a bodily fluid, human tissue or human waste product.
  • images of known pathogens Prior to sample testing, images of known pathogens are saved in a database, and image processing software of the invention is activated on the images to extract visual characteristics which are typically associated with each known pathogen. Classification features are constructed manually, automatically extracted or refined from a database of known pathogens, or a combination thereof.
  • the apparatus captures one or more digital images from a sample undergoing analysis.
  • the apparatus then utilizes image analysis software to locate putative appearances of the pathogen in the image.
  • the apparatus compares the characteristics of a suspected pathogen present in the image, to a succinct set of characteristics extracted from images of known pathogens.
  • the characteristics termed "classification features" herein, may include, but are not limited to, typical motion of live parasites, their typical shape, size, their coloring, their contrast, and their location with respect to other elements of the biological sample (for example, if the pathogen is located within a mammalian cell). Additional classification features are enlarged upon hereinbelow.
  • the analysis is rapid, and in certain instances may be performed in less than 1 second per image or less than 2 minutes per sample.
  • Images taken may include still digital images, video images in digital format or simulated video images. One or more images may be utilized from each sample, as deemed necessary.
  • the sensitivity of the present invention relates, in part, to the number of images captured of various areas within the sample. By preselecting this parameter, the user can set the sensitivity as needed during a given analysis. By choosing a sufficiently large number of imaged locations, therefore, the test described herein can exceed the sensitivity of the current gold standard.
  • Another advantage of the invention over prior art techniques for detecting pathogens is the ability to identify the presence of several pathogens by performing a single run of the sample in the apparatus of the invention. Since the algorithm of the apparatus can contain classification features associated with several known pathogens, a single test of the sample can be sufficient to identify a wide range of pathogens.
  • the apparatus of the invention thus simplifies and expedites the diagnostic procedure, by using a single test in the apparatus to identify a plurality of pathogens.
  • the invention grants an advantage over prior art techniques for identification of parasites, as the invention is not dependent upon, for instance, an antibody binding to a specific epitope that may disappear from the surface of the parasite after mutation occurs.
  • the invention maintains its efficacy, since parasite visual form tends to stay conserved despite rapid antigen mutation. Even if parasite visual form changes, the classification features may be updated to suitably detect the new form, and these classification features may be disseminated to all users of the invention.
  • Sensitivities and specificities greater than 99% were achieved using the apparatus and software of the invention on several test cases, in which a known parasite sample was analyzed in order to test the accuracy of diagnosis. This accuracy is greater than the 97% specificity achieved using prior art ELISA methods to identify parasitic samples.
  • the term "cartridge” refers to a support upon which a sample of human bodily material may be placed, after which the cartridge may be inserted into the apparatus of the invention, for analysis.
  • the cartridge may resemble a traditional slide for a light-microscope in general appearance and size, typically 75X25mm, and is typically for a single use per sample.
  • the cartridge may be a specialized sample support element, and may have dimensions of l"x3", or may resemble a multi-well plate.
  • bodily material a material originating in the human or mammalian body, and from which a portion may be readily removed for analysis for the presence of pathogens or for visually apparent changes related to disease progression.
  • Non-limiting examples include: blood, feces, saliva, plasma, serum, sweat, urine, milk, tears, pus, lymphatic fluid, cerebrospinal fluid, and mammalian tissues.
  • pathogens refers to disease causing organisms, including parasites, bacteria, fungi and viruses.
  • the apparatus of the invention can identify visual changes in bodily tissues and in fluids, which may occur as various diseases progress.
  • classification features refers to visually apparent characteristics of a particular pathogen or of disease progression.
  • the classification features may be used to identify a particular pathogen. Non-limiting examples include: typical motion of a pathogen (i.e. direction and velocity), size, typical shape, coloring, contrast, autofluorescence with or without staining, derived fluorescence, the aspect ratio, internal or external structures (organelles), etc. Additional classification features are described hereinbelow.
  • field refers to a region of the sample supported by the cartridge that may be viewed by the microscope and camera.
  • clip refers to a series of images captured in rapid succession by the camera.
  • patch refers to a region within an image, e.g. a set of adjacent pixels, which is focused upon during processing.
  • target refers to a real appearance of a pathogen in the image
  • candidate refers to a patch which, during the algorithmic processing stages, is suspected to contain a pathogen
  • classification algorithm refers to an algorithm that is composed of two phases.
  • the first is the "pre-processing" training phase, during which numerous examples of the data of interest, containing both "positive” and “negative” examples are analyzed manually, automatically or in combination thereof, and a model for separating these examples is computed.
  • a positive example is a patch depicting a pathogen
  • a negative example is one that does not depict a pathogen.
  • the actual classification takes place in the second phase.
  • the algorithm Given a novel candidate, the algorithm uses the separation model computed in the previous phase and extracts classification features to determine whether the candidate is a target or not.
  • the first "pre-processing" step typically occurs while the apparatus is customized and configured for particular parasites, and the resulting separation model is not usually modified by the clinical user, with the exception of potential software updates.
  • Software updates can, for example, be used to improve classification results or to introduce new diagnostic capabilities.
  • Fig. 1 illustrates an external view of an apparatus for detecting pathogens, according to an embodiment of the invention.
  • the apparatus 100 is preferably covered by a rigid casing 400, e.g. plastic or metal, for protecting the inner components of the apparatus.
  • Apparatus 100 includes a hinged cover 300 which may be opened to reveal a cartridge support frame (best shown in Fig. 3) for receiving a cartridge upon which a sample has been applied.
  • the cartridge support frame for supporting a cartridge, is designed to protect the apparatus from direct contact with the tissue or sample undergoing analysis.
  • Cartridge support frame is located such that after insertion of a cartridge containing a sample, cartridge is present within optical viewing path of microscope elements of the invention (described hereinbelow).
  • Cartridge support frame rests on a moveable stage, and both of which can be automatically moved to capture images from different areas of the cartridge.
  • Display screen 200 may display the analysis results.
  • Display screen 200 may be a touch screen, which may be used to interact with the device.
  • LCD touch screen is the "Thunderpack TAO-3530W” manufactured by TechnexionTM of Taiwan, including its interface board.
  • touch screen may be replaced with a display screen and keys for interaction with device.
  • Fig. 2 is an isometric diagram of the central internal components of the apparatus, according to an embodiment of the invention.
  • Apparatus 100 includes touch screen 200, which is in wired communication with processor 210 and controller 220.
  • Controller 220 may be a printed circuit board, designed to time and control the various operations of various other components.
  • Light source 340 is part of an optical viewing path, which includes angled mirror 520, beam splitter 350 and digital camera 500. Additional components of the optical viewing path are described in relation to Fig. 3. Optical viewing path acts to reflect an image from a cartridge undergoing analysis, after cartridge has been placed in cartridge support frame. Image is reflected towards digital camera 500.
  • Processor 210 is configured to receive images from the digital camera 500. Processor 210 then utilizes software of the invention to perform image analysis and compares a sample image to images stored in electronic memory, within a database of known images pertaining to known pathogens or known tissue views.
  • processor and controller may be a single processing unit. Alternatively, any number of processors may be included in the invention, as deemed necessary.
  • activation of the apparatus may be controlled by an external computer, such that the processor is located in the external computer.
  • Lateral movement servo 330 and longitudinal movement servo are configured to move the cartridge support frame 310 including a cartridge, when present, in 4 horizontal directions, thus allowing scanning of the cartridge and capturing of several images from the entire area of a cartridge.
  • a cartridge 380 is depicted, resting within a cartridge support frame 310. Hinged cover 300 (not shown) has been removed for ideal viewing. In this position, cartridge 380 is located within optical viewing path, as mirror 392 and LED circuit board 394 rest above cartridge 380 and are born by hinged cover 300 (not shown). Lens 396 is located beneath cartridge 380, thus focusing and continuing the optical viewing path. Referring to Fig. 9, an enlarged view of the cartridge is seen.
  • Cartridge 380 receives and supports a sample for analysis, replacing a traditional slide. After placing a sample of human bodily material upon the cartridge, the cartridge may be inserted into the apparatus of the invention, for analysis.
  • the cartridge may resemble a traditional slide for a light-microscope in general appearance and size, typically 75X25mm, and is typically for a single use per sample.
  • branched tracks 360 extend from an arched application recess 370. Branched tracks 360 act as microfluidic channels, to ensure diffusion of the sample over the majority of the cartridge 380 area by capillary force and can create a single layer of cells that is highly suitable for microscopic imaging. This novel cartridge design obviates the need for trained personnel to prepare the sample. Microfluidic channels typically have a maximal depth of 1mm.
  • the cartridge is typically disposable, however in certain embodiments it may be washed and reused.
  • the cartridge may additionally be pre-coated with various coatings useful for sample-preparation, such as staining, coatings for maintaining sample freshness or viability, for processing or pre-processing of the sample, and for facilitating imaging.
  • the cartridge may be packaged to maintain the sterility and/or the quality of preloaded stains or reagents to prevent degradation during storage.
  • the cartridge may have a secondary orifice to allow addition of another reagent after sample application has been performed.
  • a bodily sample is applied to the arched application recess 370 of a cartridge 380.
  • the cartridge 380 is inserted into cartridge support frame 310, which is affixed to a moveable stage 320, and hinged cover 300 is closed.
  • the controller 220 will activate light source 340, to emit a light beam to illuminate the cartridge.
  • the light beam may be emitted from one light source or a number of different light sources each emitting light beams of different wave lengths, or a combination thereof.
  • Light source is located internal to light source heat sink 610.
  • a white light source 340 and a blue light source 620 are included in the apparatus, and are manufactured by Quadica Developments Inc. of Ontario, Canada:
  • White light for transillumination is provided by a Luxeon® LXML-PWNl- 0120 Rebel Neutral White high power LED, producing 120 lumens of light at 350mA, and 220 lumens at 700mA.
  • Blue light for detecting epifluorescence is provided by Luxeon® Blue Rebel LED, 23.5 Lumens at 350mA and 48 Lumens at 700mA pre-soldered to a MCPCB base.
  • the MCPCB base is a mounted heat sink. Additional components (not shown) may be included in the apparatus that allow florescence microscopy, such as an excitation filter, a dichroic mirror or beamsplitter, and an emission filter.
  • one or more of the following light sources may be used: a light emitting diode (LED), laser, halogen lamp, an arc lamp, white light, blue light, yellow light, green light, red light, ultraviolet light, and infrared light, to facilitate fluorescence and non-fluorescence imaging.
  • LED light emitting diode
  • laser halogen lamp
  • an arc lamp white light, blue light, yellow light, green light, red light, ultraviolet light, and infrared light
  • the controller 220 may select from among one or more emitting light sources, in order to change the wave length of the light beam according to the requirements and needs of a specific analysis.
  • the controller 220 selects the exposure time, namely how long the light source will be on, how long the shutter time of the digital camera will be, the specifics of moving the moving stage (timing and direction of movement), focus and zooming in of digital camera, adjustment of the angle of angled mirror (for adjusting angle of beam, thus obtaining a depth- perspective of the sample).
  • Controller 220 co-ordinates timing and directional movement of the cartridge support frame 310 and moveable stage 320 bearing the cartridge, with the timing of activation of light source and with image capture of the digital camera, to ensure proper sequence is maintained and to ensure images are initially captured from different areas of the cartridge. Subsequently, when images have been processed and certain areas of the sample have been tagged as requiring additional analysis, controller may move the cartridge support frame 310, may move the stage 320, or may instruct camera to zoom in on these areas, may replace or add optical filters, or may illuminate the area of interest with a different light source to gather additional information.
  • Digital camera may be any electronic camera.
  • digital camera was monochrome 5Mpixel 12bit, CMOS (complementary metal-oxide- silicon) camera. Model no. BTE-B050-U, manufactured by Mightex Systems of Toronto Canada and California USA.
  • Camera includes a CCTV lens 510, or may have other type of lens.
  • lens is a CCTV lens of 5 MP resolution, catalog number SV-5014H manufactured by NET of Finning, Germany.
  • the resolution obtained was approximately 0.5 micron per pixel with a lOx objective. This resolution is sufficient to detect parasites such as T. brucei, which are typically 20 microns in length. In other embodiments, the resolution obtained was approximately 0.15 micron per pixel with a 40x objective, which is sufficient to detect parasites such as Plasmodium falciparum.
  • objective lens 396 is located above angled mirror 520, and below cartridge 380. Angled mirror 520 reflects the illumination from the cartridge 380 in support frame 310 to the camera 500.
  • the viewing path may include any of the following (not shown): a field, aperture and/or condenser diaphragm, one or more shutters, a condenser lens, a plurality of objective lenses of different magnifications, and a plurality of fluorescence filters of different optical passbands.
  • the digital image is then transmitted to processor 210 which is designed to process and analyze the image.
  • processor 210 which is designed to process and analyze the image.
  • the image processing techniques used for analyzing the picture are described hereinbelow in the section titled "Image Processing Modules”.
  • lateral movement servo 330 and longitudinal movement servo 730 are depicted. Controller (not shown) can instruct lateral movement servo 330 to move the moveable stage 320, in order to scan and capture images from different areas of the cartridge (when present in the apparatus).
  • Controller (not shown) can instruct lateral movement servo 330 to move the moveable stage 320, in order to scan and capture images from different areas of the cartridge (when present in the apparatus).
  • servo is "Dynamixel AX-12A Robot Actuator” manufactured by Trossen Robotics LLC of Illinois, USA.
  • Servo includes a gear reducer, DC motor and servo regulating circuitry.
  • the depicted cartridge support frame 310 is born by two horizontal rods 640a, 640b fixed to the upper surface of the moveable stage 320.
  • Moveable stage 320 is also supported by two horizontal rods 690a, 690b which are perpendicular to the upper two rods, thus it is possible to shift the cartridge when present in its support frame 310, in all 4 cardinal directions, when lateral movement servo 330 and longitudinal movement servo 730 act to slide the movable stage 320 and/or cartridge support frame 310 on the rods.
  • moveable stage may be moved using any of the following components: stepper motor, servo motor, lead screw, belt drive and worm drive.
  • the controller 220 can instruct servos 330, 730, to move the cartridge in all the planar directions, either in a preset pattern or according to contemporary needs, whether for image capture of the whole cartridge or for picturing specific areas of interest on the cartridge.
  • the images may be analyzed one by one or may be aggregated to be analyzed together. Images may be captured from each area one or more times, and may be sequential or non- sequential.
  • an additional servo termed the "autofocus servo" 650 is a focus actuator that acts to focus objective lens.
  • lithium ion battery 660 is depicted, and acts to provide power to the apparatus when the apparatus is used in a remote location.
  • apparatus may be connected to the electricity power grid using power inlet 670 for electrical cord, best shown in Fig. 6.
  • Display screen 200 is shown in side view.
  • Strut 700 and stand 710 support horizontal rod 690b, which extends towards moveable stage 320.
  • Sliding connectors 720a, 720b surround horizontal rod 690b, and are fixed to moveable stage 320, allowing stage 320 to slide upon rod 690b when longitudinal servo 730 exerts directional force upon stage 320.
  • processor 210 stores the images obtained, in local memory, and image analysis is performed within the apparatus.
  • the apparatus may send the images or portions thereof to be stored in an outer repository and/or analyzed on a remote computer.
  • Ethernet port jack 740 is included at the rear of the apparatus, and provides the apparatus with the option to be wired into a local area network or any other communication network for sending images obtained to a remote computer, or for communicating any other information.
  • remote computer may send and update images of known parasites for storing within the memory of the apparatus.
  • USB port 750 additionally allows two way data transfer, such as of images captured.
  • Power inlet 670 is provided to connect the apparatus to the electrical grid, when desired.
  • Power switch 770 is used to switch the apparatus on/off.
  • Cooling fan 780 cools interior electrical components of the device.
  • the remote computer may be a central server which constantly receives images from apparatuses utilized at various locations, and server may be programmed to disseminate images of various new parasitical species to all users.
  • the images are uploaded to the remote server, where image processing and analysis is performed, and the final decision and pathogen identification is returned to the apparatus for display on the display screen.
  • the image processing and analysis software of the invention may be run using processing hardware that may be included in the device, or can be collocated on a standalone computer, or may be run on a remote computer in communication with the device, such as over the internet.
  • the computer software makes use of machine vision algorithms that detects the presence or suspected presence of parasites and optionally other information about the parasites. Some embodiments of this software are described herein below.
  • Image analysis can take place following, alongside and/or intermittently with image capture. AN ALTERNATIVE EMBODIMENT OF THE APPARATUS
  • the apparatus comprises the following central components:
  • Components manufactured by Olympus Corporation included: microscope BX43, manual florescence illuminator BX3-URA, Trinocular tube U-CTR30-2-2, Camera adapter with C-mount, 0.5x U-TV0.5xC-3-7, Quintuple revolving nosepiece U-5RE-2, Abbe condenser U-AC2, True color LED light source U- LHLEDC, Power Cord 1.8 M UYCP, FITC filter cube U- FBW, UPLFLN20X /0.5 Universal Plan Fluorite objective with 20x magnification, and UPLFLN40X/0.75 Universal Plan Fluorite objective with 40x magnification.
  • Optiscan XYZ stage (Cat. No. ES103PS) comprising: two 10-position filter wheels (for 25 mm diameter filters), probe encoder for Z, travel XY stage, focus drive with adapter, joystick, RS232 and USB cables.
  • Lumen 200 florescence illumination system (Cat. No. L200OL2)
  • classification features which are associated with specific pathogens, in order to reach an algorithmic decision whether a pathogen is identified in the sample or not.
  • Each pathogen is associated with specific visually identifiable classification features.
  • These classification features can be collected when known samples are imaged using brightfield, darkfield, phase-contrast, any interference-contrast, or fluorescence microscopy. Samples can be treated to induce fluorescence, and samples can be viewed either with or without suitable staining.
  • classification features include:
  • Presence of intracellular structures associated with the pathogen e.g. nucleus, kinetoplast, granularity.
  • Extraceullular structures associated with the known pathogen e.g. flagella, knobs.
  • ⁇ Aspect ratio the ratio between the length/width of suspected structures.
  • each pathogen is associated with specific florescence which can be viewed upon illumination and emission-filtering at predetermined wavelengths.
  • Optical birefringence illumination in a specific wavelength results in detection of internal structures in certain parasites.
  • the set of classification features is relatively small for each known pathogen, thereby their use for classification of a suspected pathogen is efficient and rapid.
  • the method and apparatus may be used on biological samples from various tissue sources or their combinations
  • sample materials can include but are not limited to blood (peripheral or otherwise), lymphatic fluid, cerebrospinal fluid (CSF), urine, fecal matter, saliva, and tissue biopsies (for example, muscle, liver, etc.)
  • the biological sample is prepared for imaging using methods known in the art, such as thick or thin peripheral blood smears, or using a cartridge as presented herein.
  • the sample may be stained with a sample-appropriate stain, before the sample is applied to the slide or cartridge, for example acridine orange may be added to peripheral blood samples.
  • the sample may be stained after application to the slide or cartridge, for example by dipping a thin or thick smear preparation into a stain.
  • a staining reagent may be present within the cartridge. Certain samples are best analyzed without undergoing staining.
  • Images are obtained using one or more imaging modalities to illuminate the sample, including for instance, brightfield, darkfield, phase-contrast, any interference-contrast and fluorescence microscopies.
  • One or more optical filter combinations may be included in the device, and used for example, in excitation and emission light paths.
  • One or more light sources may be used.
  • One or more magnification powers may be utilized, and images may be obtained at one or more locations within the sample. Images may be captured using one or more focus depths for each sample or for each imaging location.
  • Fluorescence microscopy offers unique advantages in the context of the invention. Most notably, by employing a suitably chosen fluorescent staining or by imaging suitable autofluorescence channels, the resultant images can emphasize pathogen markers. For example, when blood is stained with acridine orange, fluorescence images reveal only white blood cells and parasites, due to their nucleic-acid content; red blood cells remain invisible. Such emphasis can greatly ease the computation burden on machine-vision algorithms. Furthermore, fluorescence and autofluoresence permit the identification of defined sample or cell components (such as DNA, RNA, or cell membranes). This significance can be used to inform machine -vision algorithms, thereby yielding substantially improved results.
  • Microscopic imaging can take advantage of autofocus capabilities. These can be implemented, for example, by providing the objective (or potentially any other lens in the optical path) with an actuated stage, actuating the sample support stage in the optical direction or by providing focus control in the camera. Focus information for the control of such actuators can be computed based on captured image sharpness, which may optionally be automatically obtained for this purpose, or with a hardware-based autofocus system, such as one based on laser return (e.g. Prior Scientific LF210).
  • the invention can take advantage of objectives with high depth of fields or with one of a number of computational and hardware techniques to extend depth of field that are known in the art ("Extended depth of field" methods). Different embodiments may take advantage of one or several stains or staining methods.
  • Some stains include but are not limited to; acridine orange, Giemsa stain, Romanowsky stain, Leishman stain, H&E stain, Jenner stain, Wright stain, Field stain, silver stain, Papanicolaou stain, Sudan stain, Masson's trichrome, Gram stain, eosin, orange G, DAPI, Ethidium bromide, Hoechst, SYBR stains, and other nucleic acid stains.
  • the components, partial compositions or the combinations of these stains are possible.
  • Giemsa stain produces both a color that is visible in brightfield microscopy and a fluorescence signature that is visible in epifluorescence microscopy.
  • eosin is typically used for its chromogenic effect, it also carries a distinct fluorescent signature, which can be advantageous.
  • single or multiple stains can be imaged for fluorescence using one of more excitation wavelengths and imaged using multiple emission filters to yield multiparametric image data.
  • samples stained using acridine orange can be illuminated using blue fluorescent excitation (e.g. wavelengths 460nm to 495nm) and imaged, either sequentially or simultaneously, using an emission filter or filter combination for yellow-green light (e.g. bandpass filter for 515nm to 535nm) and an emission filter or filter combination for red light (e.g. longpass filter for 600nm and up).
  • an emission filter or filter combination for yellow-green light e.g. bandpass filter for 515nm to 535nm
  • red light e.g. longpass filter for 600nm and up
  • Such multiparameteric biologically- meaningful data can be used to identify various parasites, using the software algorithms of the invention.
  • multiple fluorescence images are obtained in part by mechanically switching optical filters and/or dichroic beamsplitters/mirrors in and out of the optical path.
  • the optical path is split at least once using dichroic or partial beamsplitters/mirrors and multiple fluorescence images (or fluorescence and non-fluorescence images) are obtained on multiple cameras.
  • the one or more cameras are high- sensitivity CMOS cameras, such as those based on the Aptina/Micron MT9P031 sensor family.
  • any of the cameras can be CCD, cooled CCD, intensified CCD, or electron-multiplied CCD.
  • a cartridge or a traditional slide is used to support the sample for analysis within the apparatus of the invention.
  • the cartridge is intended to simplify sample preparation, and is the presently preferred embodiment.
  • the cartridge may be designed to present a single layer of cells in order to ease microscopic imaging.
  • Use of a cartridge presents an improvement over prior art, since prior art sample preparation is known to require training, experience and time. For example, thick blood smears typically take over an hour to dry, whereas thin blood smear require significant operator skill in order to yield large useful area.
  • the cartridge may be disposable or reusable. In particular embodiments the cartridge has dimensions similar to a typical microscope slide, 1" x 3" or 25mm x 75mm.
  • the cartridge has one or more fluidic or microfluidic channels, which may optionally be connected to each other to facilitate simultaneous filling. These channels may be comprised of at least one section with a channel height that permits only a single layer of cells to fill it, hence presenting a monolayer for imaging. In the preferred embodiment, the channels may be designed for capillary filling, for example, by choice of materials, coatings or postprocessing, as is known in the art.
  • the cartridge may be prefilled or pretreated with a staining reagent or reagents, which may be stored as a liquid, solid, a coating or dried within the cartridge. In particular embodiments, the cartridge is preloaded or pretreated with one or more anticoagulation reagents.
  • stains and/or anticoagulation reagents are added to the sample before loading onto the cartridge.
  • the cartridge is sterile or sterilized.
  • the cartridge is packaged to maintain the sterility or the quality of preloaded stains or reagents to prevent degradation during storage.
  • the cartridge permits washing, staining or otherwise treating the sample using reagents that are provided externally or that are preloaded.
  • the sample may be prepared, loaded onto a cartridge or microscope slide, or stained using one or more automated instruments.
  • Each such instrument may either be separate from or may be included in the apparatus of the invention.
  • the apparatus may employ a Prior ScientificTM PL200 slide loader to automatically load microscope slides of cartridges with a microscope-slide form factor of l"x3".
  • the slide loader may be modified to additionally dip the slide into appropriate staining and washing solutions.
  • a sample of ⁇ is sufficient in volume for analysis.
  • a finger prick can be utilized to obtain this minute quantity, with blood being collected into a capillary, thus obviating the need for trained blood technicians for taking a sample from a patient.
  • the capillary can then be brought into contact with the cartridge to apply the blood sample to the cartridge.
  • Suitable processors for implementation of the invention include, by way of example, both general and special purpose microprocessors.
  • a processor will receive instructions and data from a read-only memory and/or a random access memory.
  • the apparatus may include one or more mass storage devices for storing data files (such as images obtained or images of known pathogens).
  • mass storage devices include magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and optical disks.
  • Storage devices suitable for tangibly embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM disks.
  • the cover 300 may be opened and the cartridge may be taken out and disposed of, after which, the apparatus 100 is ready for a new analysis.
  • Sample removal can be automated, for example, using a Prior Scientific PL200 slide loader.
  • a number of modules are described below for processing an image and finding pathogens.
  • the apparatus described above may utilize one or more of the following image processing modules.
  • the apparatus invokes the following modules in a preset sequence.
  • the following description is a presently preferred order of the processing steps, although alternative embodiments may use a different order:
  • Parasite Candidate Detection Module This module scans an entire image, which depicts a field within the sample, and searches for patches in the image within which it is likely that a pathogen of interest, referred to hereinafter as the "target", appears.
  • One or more of the following methods may be used to detect these candidate patches: Pattern matching - if the general form of the target is well defined, a pattern describing this form is constructed in a pre-processing stage: numerous examples of its form are manually collected, and the general pattern is extracted. When processing an image, this pattern is then matched at every location, and those locations which exhibit high similarity to the pattern are taken as candidates.
  • a human operator collects a number of images, containing a known target microorganism, and marks the target on these images. Then these marked images are fed to a processor adapted to extract the general pattern of the target, based on the numerous images of the target.
  • This pattern matching module which is invoked by the apparatus, can use the resultant pattern of the target for finding other similar patterns in the image.
  • the threshold of high similarity may be flexibly defined using trial and error, which may be steered by the application, or it may be defined rigidly as a pattern which has 90% similarity to the general pattern of the pathogen.
  • Various image-processing filters e.g.
  • wavelettes may be applied to enhance the features in the image which are relevant to the target's pattern and suppress those which are not.
  • an edge-avoiding wavelette may be used to smooth out noise, while keeping the sharp features of the pathogen's boundary.
  • Model matching if the general pattern of the target can be described by a simple model of a few image parameters (e.g. a blood cell can be described by a circle or an ellipse), patterns of this model are sought out in the image.
  • Hough transform may be used to transform the image into the parameter space, and parameter sets which gain support from numerous pixels are taken as candidates.
  • Motion detection - Using the Motion Field Detection Module (described below) the image can be segmented into pixels which are part of the ambient motion field, and pixels which move differently, i.e. move in other directions. The latter are clustered together spatially.
  • the clustering algorithm takes into account the form and movement of the desired target. Clusters which confer to the characteristics of the target, such as size, are taken as candidates.
  • High fluorescence The fluorescence image, which roughly overlays the intensity image, is segmented and clustered in a manner analogous to the motion detection above. Instead of looking for patches which move differently from the background, patches whose fluorescence is higher than the background, e.g. patches having high SNR, are sought.
  • High fluorescence can refer to high fluorescence intensity values, or high sum fluorescence, e.g. as integrated over an area.
  • Multi Frame - Using the Tracking Module (described below), multi- frame candidates (described below as well) are tracked to frames in which they are likely to appear. If the tracking is successful, the location to which the candidate was tracked is taken as a candidate in that frame.
  • multi-frame candidates are tracked to temporally- adjacent frames, leading to new candidates. This is done iteratively to enhance the construction of multi-frame candidates.
  • multi-frame candidates are found and processed as the images are being streamed into the processing device. They can be tracked only forward in time, and the process is performed only once.
  • the second step of the sequence may be:
  • Single Frame Classification Cascade Module may also be called “Multi Frame Classification Cascade Module”. This module receives candidates, from the first step, in a single frame, and computes the likelihood that they indeed contain an occurrence of the desired target.
  • Classifying algorithms are machine-learning algorithms which may operate according to the following techniques used in sequence:
  • classification features functions of the data to be classified - are determined. Therefore, these classification features must be relevant to the objects which are being classified. In our case these classification features may include the intensity and gradient of the candidate, the fluorescence of the candidate and/or motion of the candidate. Additional classification features are described hereinabove, in a separate section.
  • the images are then processed to create rotationally-invariant images, to make the classifying features independent of the viewing angle.
  • Magnification also affects the type of classification features used. In low magnification, the contour of the microorganism is an important hint, while in high magnification, finer details, such as pathogen-specific internal or external structures, are used.
  • the classifying algorithm is "trained" to differentiate between sets of classification features which describe the target and sets which do not. This is done in a so-called supervised manner, where clips in which all occurrences of the desired target are manually tagged.
  • the Parasite Candidate Detection Module is then used on these clips.
  • the candidates the module outputs, along with their manual tags, are used as input to train a maching-learning algorithm, such as a Support Vector Machine (SVM).
  • SVM Support Vector Machine
  • An SVM is a known classifier, which uses tagged inputs as above to construct a separator in the features space between true and spurious candidates. Other machine-learning algorithms are known in the art.
  • SVM Support Vector Machine
  • the Single Frame Classification Cascade Module may employ a cascade of classifying algorithms. Candidates which are found to be highly likely to contain a target are passed to the next classifying algorithm. This cascade allows using more powerful (and computationally intensive) classifying algorithms along the cascade— the fewer candidates remaining, the more powerful the classifying algorithm can be, while maintaining reasonable running times. Importantly, the pre-processing training of a classifying algorithm is done on the output of the previous classifying algorithm up the cascade.
  • the Single Frame Classification Cascade Module may also align them to canonical coordinates. This augments and complements the selection of rotationally-invariant features, allowing some flexibility in the latter. That is, classification features which are not invariant to rotation are still sometimes used, and the alignment phase rotates the patches to a canonical angle.
  • classification features and/or the separator may be determined or modified manually or with non-machine-learning analysis algorithms.
  • the human expert knowledge of a trained medical professional may be transcribed into classification features or separator algorithms that may be used independently or to supplement machine-learning based processing.
  • the third step of the sequence may be:
  • Multi-Frame Candidate Construction Module This module clusters together appearances of the same target in multiple frames.
  • Single-frame candidates may be matched to other such candidates based on their location in the image. If the target is relatively static, then candidates are matched if they are roughly in the same location in the image (or, more precisely, in the same relative location within the motion field). More generally, if the target is moving, it is tracked using the Tracking Module (described below), and is matched to candidates appearing in roughly the same location to where it is tracked.
  • the Tracking Module described below
  • the Multi-Frame Candidate Construction Module constructs a graph with the single-frame candidates as its vertices, and matches defining edges. Connected components within this graph are checked for coherency, i.e. that the target appears "the same" in all occurrences. In an iterative implementation, temporal gaps within these components may be filled by extrapolating the locations of missing occurrences, and processing them with the Single-Frame Classification Cascade Module. In this case, the entire set of single-frame classifying algorithms may be used, rather than conditioning on pervious results, since only a small number of candidates are processed this way.
  • the coherent, and possibly gap-filled, backbone of the connected components is the multi-frame candidate— a collection of all single-frame appearances of a specific target along with the results of its classification cascade.
  • Multi-Frame Candidate Tracking Module partially-constructed multi- frame candidates may be tracked to frames temporally-adjacent to the ones in which their single-frame constituents were identified in the previous step. This can be done by various computer-vision algorithms, such as mean-shift or differential methods.
  • this module facilitates initial candidate detection when other signals are weak. Candidates are created in location to which multi-frame candidates were tracked, as described in the Parasite Candidate Detection Module, above.
  • tracking defines the matching of single-frame candidates, on which the construction of multi-frame candidates is based.
  • the multi-frame construction can be seen as a form of agglomerated clustering: initially all single-frame candidates are distinct multi-frame candidates. They are then iteratively tracked, matched, and merged together into bigger clusters.
  • Multi-Frame Candidate Classification Module Once the entire set of target occurrences is determined, it may be classified as a whole. Technically, this is similar to the single frame classification, but here features from multiple images are used, as well as the relations between them (e.g. the trajectory of the target).
  • This module determines, for each multi-frame candidate, the likelihood that it's a true occurrence of the desired target.
  • Non-pathogen Sample Content Classification Module This module may be used to identify sample elements that are not the pathogens themselves but are useful in determining pathogen presence. For example, red blood cells may be identified in malaria diagnosis in order to determine whether a suspected target is located within a red blood cell. Similarly, white blood cells may be identified in order to rule out their nuclei as suspects. This module may itself take advantage of the same algorithms and modules that are described for the identification and analysis of pathogen suspects.
  • Sample Classification Module Based on the set of classifications of all multi-frame candidates, the sample is classified as either containing the defined microorganism or not containing it.
  • Motion Field Construction Module The purpose of this module is to construct the image of the blood ambient background at each image-capture time point. When the blood is not moving, several frames are taken around the time point, and for each pixel taking the median value at its location. More generally, dense optic flow may be used to determine the motion vector of the background from frame to frame, by taking the mean motion value. The background image is constructed by taking the median value of pixels in the same location relative to the background motion.
  • Image Verification Module The purpose of this module is to recognize and report poor samples, such as images taken from a blocked lens or damaged camera or images in which the sample does not appear at all.
  • Camera/Microscopy Control Module The purpose of this module is to control image capturing.
  • the location and magnification can be adjusted to clear ambiguities in the image.
  • the camera can be adjusted to zoom in on a candidate, to visualize it in finer detail.
  • the module may control exposure, illumination parameters and aperture parameters in order to obtain optimal images.
  • Masking Module The purpose of this module is to identify regions in the image in which targets are not likely to occur. Such regions are ignored by the Parasite Candidate Detection Module.
  • the invention is embodied in any suitable programming language or combination of programming languages, including Google Web Toolkit, JAVA, database managers and MySQL.
  • Each software component can be implemented in a high-level procedural or object-oriented programming language, or in assembly or machine language if desired.
  • the programming language may be a compiled or interpreted language.
  • Images are entered into and saved in a database which may be any suitable database for storing data objects and metadata relating thereto. Any suitable database program may be used.
  • the database is a relational database and a key/value database.
  • database is a modified relational database.
  • the search logic used for subsequent retrieval of experiments from the database is any suitable step, process, function or series of steps, processes and functions known in the art for searching a database.
  • the software of the invention may include a graphical user interface (GUI).
  • GUI graphical user interface
  • the contents of the screens, the functionality of the system and the work process may be adjustable to a user's needs.
  • the screen designs, terms and work process reflect the medical field and are user-friendly since they display and interact with the user in syntax familiar to medical technicians. Thus use of the system may appear intuitive.
  • the final analysis result, which is displayed onscreen may include the presence or suspected presence of parasites, as well as parameters regarding parasites detected, such as: their type or species, parasite load or number, life stage or maturity and any other medically relevant information.
  • the software may report medically pertinent information obtained from the biological sample yet unrelated to parasites, (such as detection of anemia, or detection of an unusual white blood-cell count). Information relevant to the quality of the test or sample may be displayed.
  • the separator or separator may be configured such that the provided images are only highly enriched for potential pathogens, enabling the user to make a determination based on a condensed subset of information. In these latter cases, the algorithm can be tuned to provide very high sensitivity at the cost of lower specificity.
  • Trypanosoma Cruzi is the parasite responsible for the potentially fatal Chaggas disease.
  • One of its life cycle stages (Trypomastigotes) occurs in the blood, where it has a worm-like shape - an elongated body and a flagellum— which constantly twirls and spins in the blood. This motion is the cue for the detection algorithm.
  • an image captured shows Trypanosoma brucei parasites (indicated by arrows), surrounded by red blood cells.
  • Extract classification features for each database entry For example, compute a Census Transform of the entry: divide the result into equal- sized rectangular regions (e.g. 9 non-overlapping squares) and compute a histogram of the census transform in each region.
  • the feature vector for the entry is a concatenation of these histograms.
  • Plasmodium are parasites responsible for Malaria disease; Babesia are parasites responsible for Babesiosis disease. Both types of parasites infect red blood cells (RBCs) and in the initial stages of the infection form ring-like structures. Importantly, normal RBCs expel their organelles, and in particular their nucleus, before entering the blood stream. Hence the goal is to detect RBCs which contain a significant amount of DNA, indicating parasitic infection of Plasmodium or Babesia.
  • RBCs red blood cells
  • Plasmodium and Babesia species of interest include P. Falciparum, P. Vivax, P. Ovale, P. Malariae, B. Microti and B. Divergens.
  • Detection Algorithm Initially, the blood is stained with fluorochromatic dyes such as Acridine Orange, Giemsa or Ethidium Bromide. Dyes which stain DNA and not RNA or which create a contrast between the two, are preferable.
  • a thin blood smear is prepared upon a cartridge, images are captured, and the images are divided into fields, as explained in the first example. Each field is analyzed independently by recording two images from that field - a "bright field” (BF) image (visible light) and "florescence image” (FL) radiated with a wave length appropriate to cause the dye to fluoresce.
  • BF dark field
  • FL fluescence image
  • BF-image For each BF-image, verify its validity using the Image Verification Module. If more than a specified number of images are poor (e.g. > 10%) report an error on this field.
  • a Hough Transform of its vicinity indicates that it's contained inside a circle in the image whose size is appropriate for a RBC. This is, effectively, the use of the Model Matching method of the Parasite Candidate Detection Module.
  • a contour detection algorithm of its vicinity indicates that it's within a convex shape in the image, whose size is appropriate for a RBC.
  • the Pattern Matching method of the Parasite Candidate Detection Module processing the patch's vicinity locates a strong RBC pattern overlapping the patch.
  • each candidate RBC is classified as to whether or not it's a RBC containing a parasite.
  • Extract classification features for each database entry For example, compute the Census Transform of the entry; divide the result into equal-sized rectangular regions (e.g. 9 non-overlapping squares) and compute a histogram of the census transform in each region.
  • the feature vector for the entry is a concatenation of these histograms.
  • the apparatus and method of the invention answer a long-felt need for automatic identification of pathogens, and especially of parasites within a mammalian sample.
  • the apparatus and method allow rapid identification of parasites that previously required use of expensive resources and trained personnel that are unavailable in many third world countries.
  • the invention now allows blood donations and blood tests to be screened for parasites, such that a single run through the apparatus will identify a great many parasites, representing maximal efficiency.
  • the apparatus and method overcome the difficulty of parasites constantly evolving, as an image of the new species may be easily uploaded into the database of known images and the characteristics of the new species may be analyzed to allow its identification in future.

Landscapes

  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biochemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Dispersion Chemistry (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Hematology (AREA)
  • Clinical Laboratory Science (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)

Abstract

The invention discloses an apparatus and method for automatic detection of pathogens within a sample. The apparatus and method are especially useful for high-throughput and/or low-cost detection of parasites with minimal need for trained personnel. The invention entails automated microscopic data acquisition, and performing image processing of images captured from a sample using classification algorithms. Visual classification features of structures are extracted from the image and compared to visual classification features associated with known pathogens. A determination is reached whether a pathogen is present in the sample; and if present, the pathogen may be identified to a pathogen species. Diagnosis is rapid and does not require medically trained personnel.

Description

AN APPARATUS AND METHOD FOR AUTOMATIC
DETECTION OF PATHOGENS
FIELD OF THE INVENTION
The present invention relates to the field of medical devices. More particularly, the invention relates to an apparatus and method for automatically detecting and identifying pathogens, and particularly parasites, in bodily fluid or tissue samples.
BACKGROUND OF THE INVENTION
To date, when a sample of bodily fluid is collected from an individual for testing of the presence of a parasitic infection, best results are obtained when the sample is smeared on a slide, stained and viewed under a microscope. Only trained medical personnel having sufficient experience are able to perceptively detect and correctly identify the presence of parasitic infection.
This process is labor intensive, as it is performed manually, and thus a low throughput is achieved. PCR or immunological testing may be performed as well. These processes are not suited for general health clinics which may be located in third-world countries, and thus may not have proper laboratory equipment for preparing a sample, viewing it, or testing it. The need exists for an apparatus which automates identification of parasitic or microbial infection, allowing rapid diagnosis. Such an apparatus is essential especially in locations which may not have trained medical personnel or a full-laboratory for processing of bodily fluids, or where high- throughput screening is desired. Additionally, blood banks worldwide do not have the capability to test blood donations for many parasitic infections. While typically, some bacterial and viral infections, such as hepatitis, HIV, and others, are tested for, there are currently no rapid tests in use for parasitic infection of blood donations, other than for detection of a single parasitic species, Trypanosoma cruzi, which causes Chaggas Disease.
To exemplify the need, there are no established rapid tests for Malaria, which throughout the tropics and sub-tropics worldwide. There are similarly no rapid tests for Babesiosis, an emerging disease caused by the pathogen Babesia duncani or B. microti. Babesiosis is endemic to the US, particularly New England. The transmitting vector is a tick (that also transmits Lyme disease). Though Babesiosis infection is mostly asymptomatic in healthy adults, if it is transmitted through transfusion of an infected blood unit, it may be fatal in immunocompromised, splenectomized or elderly recipients. There is no FDA-approved test to date for the disease. Numerous authors have underscored the need for screening blood donations for these parasites. The problem of transfusion-based parasite transmission is expected to gain dramatically increasing significance, owing to globalization and international travel.
Hence, there is a need for an automated apparatus capable of inspecting blood donations or blood samples for the presence of microbial or parasitic infection. Such an apparatus should be capable of rapidly testing samples in a short time-frame, with minimal human involvement.
Parasites represent a group of extremely abundant human pathogens, which is estimated to infect around one third of the world population. These diseases are source of immense suffering and millions of deaths annually worldwide. In the US alone 11 million new cases of parasitic infections are diagnosed each year. The economic burden imposed by parasitic infections is immense and impossible to calculate. The "gold standard" for diagnosis of most types of parasites is manual identification under a microscope of stained smears of biological fluids. Most frequently, peripheral blood, is used, or in other instances, lymphatic fluid and cerebrospinal fluid (CSF). This method is laborious and requires highly trained personnel, and as a result it is typically low-throughput and expensive. Despite that, microscopic analysis remains the most sensitive and specific method for the diagnosis of many parasitic diseases, including malaria and babesiosis. According to the World Health Organization, a patient is to be certified as free of malaria after a trained technician observes no parasites by examining 100 images of a "thick" peripheral blood smear at lOOx magnification.
Additional prior art methods for detecting parasites are based on immunological or PCR tests. All such methods that are in use today are either laborious and/or expensive, preventing their use in high-throughput screening applications. For example, many versions of malaria-testing "dip sticks" have recently been described. While these may be used for initial screening in remote locations, they are not usable, for example, in blood-bank screening, as their high false positive rates would result in too many parasite-free samples to be discarded. Even when immunological and PCR tests yield a positive result, the patient's blood is most often tested by the microscopic method for conformation.
The need exists for an automated apparatus capable of inspecting blood donations or blood samples for the presence of parasitic infection. Such an apparatus should be capable of rapidly testing samples in a short time-frame, with minimal human involvement.
It would therefore be desirable to provide an apparatus for rapid detection of pathogens, and especially parasites, in bodily samples, which may be used by minimally trained personnel and which provides a high throughput.
SUMMARY OF THE INVENTION
It is an object of the present invention to provide a method for automatically and rapidly detecting pathogens in human and animal bodily fluids, bodily tissues or bodily waste products. The method of the invention can be utilized to detect the presence of parasites, or other microorganisms. The method of the invention includes steps of automated microscopy and machine-vision algorithms. The method of the invention can be utilized, for instance, to detect the presence of blood parasites, such as those associated with Malaria and Babesiosis.
It is still another object of the present invention to provide an apparatus for identifying pathogens, where the apparatus includes components for automated microscopy, and machine-vision processing for performing automatic identification of pathogens.
Other objects and advantages of the invention will become apparent as the description proceeds.
The invention provides an apparatus for automatic detection of pathogens within a sample, comprising:
a) a cartridge support frame for receiving and supporting a cartridge having a sample within or thereupon; b) an optical imaging system having an optical path and comprising: at least one light source, at least one lens, and at least one digital camera; wherein the cartridge support frame is located within or may be moved into the optical path, such that images of the sample may be captured by the at least one digital camera;
at least one processor interacting with and activating at least one of components a)-b); wherein the processor is adapted to perform image processing using classification algorithms on visual classification features to detect one or more suspected pathogens, when present, in the sample. The apparatus wherein the cartridge support frame is coupled to a moveable stage, movable in at least one dimension.
The apparatus wherein the optical imaging system further comprises a focus actuator for focusing upon an image.
The apparatus, wherein the optical imaging system further comprises a plurality of objective lenses of varied magnification.
The apparatus wherein the optical imaging system further comprises: at least one optical filter or at least one dichroic beamsplitters/mirror, for exciting or detecting fluorescence.
The apparatus wherein the optical imaging system further comprises an actuator to switch the optical filters or the dichroic beamsplitter/mirror in and out of the optical path.
The apparatus wherein the at least one processor performs at least one of the following:
selecting at least one light source from among a plurality of light sources, and activating the light source;
selecting an exposure time of a light source;
selecting an exposure time for the digital camera.
The apparatus wherein at least one of the at least one processor outputs a result that includes at least one of the following: the presence or absence of a pathogen; the species of pathogen; the number or concentration of pathogens detected; the life stage of the pathogen; a finding of anemia; a finding of an unusual white blood cell count; and information on the quality of the sample. The apparatus wherein the processor outputs one or more images of suspected pathogens.
The apparatus wherein pathogen is a parasite.
The apparatus wherein the processor is present in an external computer wired to at least one of the following: to one or more internal processors, and to the digital camera.
The apparatus wherein the processor is connected via a data network to at least one of the following: to one or more internal processors, and to the digital camera..
The apparatus wherein one or more images captured by the apparatus are sent to a remote server for image processing at a remote location.
The apparatus wherein visual classification features or updated images of known pathogens or other software updates are uploadable to the apparatus.
The invention provides a cartridge for supporting a sample, wherein the cartridge comprises at least one microfluidic channel upon the cartridge.
The cartridge wherein the cartridge has dimensions of 25mm x 75mm.
The cartridge having a plurality of microfluidic channels, and the channels are connected to one another to facilitate simultaneous filling.
The cartridge wherein the microfluidic channel has a channel height permitting only a single layer of cells to fill the channel height, thereby presenting a monolayer for imaging.
The cartridge wherein the channel is manufactured with a hydrophilic material or is treated to promote capillary filling.
The cartridge wherein the cartridge further comprises a staining reagent, present in a form selected from: a liquid, solid, a coating, and dried within the cartridge. The cartridge wherein the cartridge further comprises with one or more anticoagulation reagents.
The cartridge wherein the cartridge comprises a secondary application orifice allowing addition of an additional reagent to the sample after sample application is completed.
The cartridge wherein the cartridge is sterile.
The invention also provides a method for automatic detection of pathogens within a sample, comprising: performing image processing of at least one digital image captured using classification algorithms, the image processing including extracting visual classification features from the image.
The method, comprising the step of obtaining one or more digital images of a sample using an automated microscopy system comprising at least one light source, at least one lens, and at least one digital camera; the images are obtained prior to image processing.
The method, wherein the sample is a slide selected from one or more of the following: a blood smear (thin or thick), a fecal smear, a lympathic smear, a cerebrospinal fluid smear, and a tissue biopsy.
The method, comprising the step of preparing a sample within a cartridge, performed prior to the imaging
The method, wherein the cartridge is disposed of after use.
The method, wherein the cartridge is reusable.
The method, wherein the cartridge comprises microfluidic channels for creating a monolayer of cells in at least one area, in order to facilitate imaging.
The method, wherein the cartridge is filled using capillary filling.
The method, wherein the capillary filling is done by touching the cartridge to a pin-pricked digit.
The method, wherein the preparing the sample further comprises staining the sample with one or more stains. The method, wherein the one or more stains are selected to affect a change in at least one of the following: optical absorption, opaqueness, scattering, and color of structures within a sample.
The method, wherein the one or more stains include acridine orange, and wherein a plurality of the one or more digital images are taken using configurations that allow discerning respective staining of DNA and RNA. The method, wherein the one or more stains include Giemsa, Romanowsky or related stains.
The method, wherein the sample is anticoagulated before or after application to the slide or cartridge.
The method, wherein the sample is anticoagulated by preloading one or more corresponding reagents onto the cartridge.
The method, wherein the cartridge is sterilized.
The method, wherein the obtaining one or more digital images includes moving the slide or cartridge with respect to the automated microscopy system in order to image multiple locations within a sample.
The method, wherein the obtaining one or more digital images includes automatically focusing the sample for the digital images.
The method , wherein the focusing includes moving at least one of the following: the at least one lens, the slide or cartridge, and the at least one component of the at least one digital camera.
The method, wherein the obtaining one or more digital images employs at least one of the following: brightfield, darkfield, phase-contrast, any interference-contrast, and fluorescence microscopy and any combination thereof.
The method, wherein the obtaining one or more digital images employs a plurality of objective lenses of varied magnification.
The method, wherein the obtaining one or more digital images employs one or more optical filters or one or more dichroic beamsplitters/mirrors for exciting or detecting fluorescence. The method, wherein the obtaining one or more digital images includes obtaining a plurality of digital images for at least one sample location and employing a plurality of microscopy methods.
The method, wherein the plurality of microscopy methods comprise different fluorescence excitations and/or emissions.
The method, wherein the obtaining one or more digital images includes a processor that interacts with and activates mechanical and optical components by performing at least one of the following:
selecting at least one light source from among a plurality of light sources, and activating the light source;
selecting an exposure time of a light source;
selecting an exposure time for the digital camera
The method, wherein the image processing outputs a result that includes at least one of the following: the presence or absence of a pathogen; the species of pathogen; the number or concentration of pathogens detected; the life stage of the pathogen; a finding of anemia; a finding of an unusual white blood cell count; and information on the quality of the sample.
The method wherein the image processing outputs one or more images of suspected pathogens.
The method, wherein the pathogen is a parasite.
The method,, wherein at least one of the one or more digital images is captured at a first location and is processed using a processor located at a second location.
The method, wherein at least one of the one or more digital images is sent to a remote server.
The method, wherein the image processing or other software is updated remotely.
The method, wherein the classification features include one or more of the following: motion, size, shape, coloring, contrast, location in respect to additional biological structures, presence of internal structures, presence of extracellular structures, the aspect ratio, the optical density, florescence at predetermined wavelengths, optical birefringence, clustering behavior, and pattern matching.
The method, wherein the image processing includes searching at least one of the one or more digital images for at least one patch which is likely to contain a target in the digital image and marking it as a candidate.
The method, wherein the image processing further includes at least one of the following:
calculating the likelihood that the at least one candidate contains a target;
processing the candidates for finding if more than one candidate belongs to the same target, and where found, candidates of the same target are clustered together;
tracking at least one candidate, in relation to the at least one cluster, that may belong to the cluster, and where the tracked candidate belongs, adding the tracked candidate to the cluster;
determining and classifying the likelihood that the at least one cluster contains a target; and
determining if the image contains a target, based on the classification, and thus determining if the sample contains a pathogen.
The method, wherein the searching for at least one patch which is likely to contain a target is performed using at least one of the following: pattern matching, model matching, motion detection, high florescence segmenting and clustering, and multi-frame tracking.
The method, wherein the image processing is performed using at least one of the following modules: a single frame classification cascade module; a multi- frame candidate construction module; a multi-frame candidate tracking module; a multi-frame candidate classification module; a sample classification module; a motion field construction module; an image verification module; a camera control model; and a masking module. The method wherein the image processing is performed in an aggregated processing manner.
The method, wherein the image processing is performed on-the-fly.
The method wherein the image processing includes finding the motion vector of the background of the image of the sample, and where the motion vector is used to reconstruct the image in order to compensate for the background motion.
The method wherein the image processing identifies and discards one or more poor images.
The method wherein the location and magnification of at least one digital images are adjusted to clear ambiguities in the image.
The method wherein the image processing identifies at least one region within at least one of the digital images as a region not likely to contain a target.
The invention provides computer readable storage medium that includes software capable of performing the image processing method of the invention The invention also provides computer readable storage medium that includes software capable of activating the apparatus of the invention.
Brief Description of the Drawings
Some embodiments of the invention are herein described, by way of example only, with reference to the accompanying drawings. With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of embodiments of the invention. In this regard, the description and the drawings make apparent to those skilled in the art how embodiments of the invention may be practiced.
In the drawings:
Fig. 1 is an external view of the apparatus of the invention.
Fig. 2 is an isometric diagram of the central internal components of the apparatus.
Fig. 3 illustrates a cartridge for analysis, resting within a cartridge support frame.
Fig. 4 is an isometric view is shown, in which upper components have been removed for optimal viewing of the internal elements of the device.
Fig. 5 is a side view of the right side of the apparatus, showing components such as the battery, base for mounting and adjusting angled mirror, support components and sliding connectors of moveable stage.
Fig. 6 is a rear view of the apparatus, showing communication ports and electrical power inlet.
Fig. 7 is an image captured showing Trypanosoma brucei parasites in a peripheral blood sample, for analysis using the invention.
Fig. 8 is a florescent image of Trypanosoma brucei parasites. Automatic detection of the parasites was successful using the apparatus of the invention.
Fig. 9 illustrates an enlarged view of a cartridge, according to one embodiment.
DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
In general, the present invention discloses an automated apparatus for detection of parasitic and other pathogenic infection in a bodily fluid, human tissue or human waste product.
Prior to sample testing, images of known pathogens are saved in a database, and image processing software of the invention is activated on the images to extract visual characteristics which are typically associated with each known pathogen. Classification features are constructed manually, automatically extracted or refined from a database of known pathogens, or a combination thereof.
To automatically identify pathogens within a sample, the apparatus captures one or more digital images from a sample undergoing analysis. The apparatus then utilizes image analysis software to locate putative appearances of the pathogen in the image. The apparatus compares the characteristics of a suspected pathogen present in the image, to a succinct set of characteristics extracted from images of known pathogens. The characteristics, termed "classification features" herein, may include, but are not limited to, typical motion of live parasites, their typical shape, size, their coloring, their contrast, and their location with respect to other elements of the biological sample (for example, if the pathogen is located within a mammalian cell). Additional classification features are enlarged upon hereinbelow.
The analysis is rapid, and in certain instances may be performed in less than 1 second per image or less than 2 minutes per sample.
Images taken may include still digital images, video images in digital format or simulated video images. One or more images may be utilized from each sample, as deemed necessary.
Amongst the advantages of the invention over prior art techniques are that it effectively reduces the expense, time duration, and required training for microscopic parasite detection while maintaining or exceeding the sensitivity offered by prior art gold standard methods. The sensitivity of the present invention relates, in part, to the number of images captured of various areas within the sample. By preselecting this parameter, the user can set the sensitivity as needed during a given analysis. By choosing a sufficiently large number of imaged locations, therefore, the test described herein can exceed the sensitivity of the current gold standard.
Another advantage of the invention over prior art techniques for detecting pathogens is the ability to identify the presence of several pathogens by performing a single run of the sample in the apparatus of the invention. Since the algorithm of the apparatus can contain classification features associated with several known pathogens, a single test of the sample can be sufficient to identify a wide range of pathogens.
In contrast, in prior art techniques, in order to identify, for instance, the presence of Plasmodium, the infectious organism for malaria, or the presence of Trypanosoma cruzi, the infectious organism for Chagas disease, it would be necessary to perform, for instance, one test using an antibody which identifies Plasmodium, and a second test using an antibody which identifies Trypanosoma cruzi. When a multitude of patients is considered, and several pathogens are considered for each patient, the expense of multiple tests and the time consumed for diagnosis are therefore considerable.
The apparatus of the invention thus simplifies and expedites the diagnostic procedure, by using a single test in the apparatus to identify a plurality of pathogens.
As parasites, most notable Trypanosoma brucei, are known to rapidly mutate and become immunologically distinct from their previously known form, the invention grants an advantage over prior art techniques for identification of parasites, as the invention is not dependent upon, for instance, an antibody binding to a specific epitope that may disappear from the surface of the parasite after mutation occurs. In contrast, the invention maintains its efficacy, since parasite visual form tends to stay conserved despite rapid antigen mutation. Even if parasite visual form changes, the classification features may be updated to suitably detect the new form, and these classification features may be disseminated to all users of the invention.
Sensitivities and specificities greater than 99% were achieved using the apparatus and software of the invention on several test cases, in which a known parasite sample was analyzed in order to test the accuracy of diagnosis. This accuracy is greater than the 97% specificity achieved using prior art ELISA methods to identify parasitic samples.
For the sake of clarity the following terms are defined explicitly: The term "cartridge" refers to a support upon which a sample of human bodily material may be placed, after which the cartridge may be inserted into the apparatus of the invention, for analysis. The cartridge may resemble a traditional slide for a light-microscope in general appearance and size, typically 75X25mm, and is typically for a single use per sample. Alternatively, the cartridge may be a specialized sample support element, and may have dimensions of l"x3", or may resemble a multi-well plate.
The terms "bodily material", "bodily fluid", "bodily waste product", "tissue" and "sample" are used interchangeably to refer to a material originating in the human or mammalian body, and from which a portion may be readily removed for analysis for the presence of pathogens or for visually apparent changes related to disease progression. Non-limiting examples include: blood, feces, saliva, plasma, serum, sweat, urine, milk, tears, pus, lymphatic fluid, cerebrospinal fluid, and mammalian tissues. The term "pathogens" refers to disease causing organisms, including parasites, bacteria, fungi and viruses. In addition to detection of the pathogen itself, the apparatus of the invention can identify visual changes in bodily tissues and in fluids, which may occur as various diseases progress.
The term "classification features" refers to visually apparent characteristics of a particular pathogen or of disease progression. The classification features may be used to identify a particular pathogen. Non-limiting examples include: typical motion of a pathogen (i.e. direction and velocity), size, typical shape, coloring, contrast, autofluorescence with or without staining, derived fluorescence, the aspect ratio, internal or external structures (organelles), etc. Additional classification features are described hereinbelow.
The term "field" refers to a region of the sample supported by the cartridge that may be viewed by the microscope and camera.
The term "clip" refers to a series of images captured in rapid succession by the camera. The term "patch" refers to a region within an image, e.g. a set of adjacent pixels, which is focused upon during processing.
When processing an image for pathogens, the term "target" refers to a real appearance of a pathogen in the image; the term "candidate" refers to a patch which, during the algorithmic processing stages, is suspected to contain a pathogen.
The term "classification algorithm" is known in the art, and refers to an algorithm that is composed of two phases. The first is the "pre-processing" training phase, during which numerous examples of the data of interest, containing both "positive" and "negative" examples are analyzed manually, automatically or in combination thereof, and a model for separating these examples is computed. In this context, a positive example is a patch depicting a pathogen, and a negative example is one that does not depict a pathogen. The actual classification takes place in the second phase. Given a novel candidate, the algorithm uses the separation model computed in the previous phase and extracts classification features to determine whether the candidate is a target or not. The first "pre-processing" step typically occurs while the apparatus is customized and configured for particular parasites, and the resulting separation model is not usually modified by the clinical user, with the exception of potential software updates. Software updates can, for example, be used to improve classification results or to introduce new diagnostic capabilities. CENTRAL COMPONENTS OF THE APPARATUS
Fig. 1 illustrates an external view of an apparatus for detecting pathogens, according to an embodiment of the invention. The apparatus 100 is preferably covered by a rigid casing 400, e.g. plastic or metal, for protecting the inner components of the apparatus. Apparatus 100 includes a hinged cover 300 which may be opened to reveal a cartridge support frame (best shown in Fig. 3) for receiving a cartridge upon which a sample has been applied. The cartridge support frame, for supporting a cartridge, is designed to protect the apparatus from direct contact with the tissue or sample undergoing analysis. Cartridge support frame is located such that after insertion of a cartridge containing a sample, cartridge is present within optical viewing path of microscope elements of the invention (described hereinbelow). Cartridge support frame rests on a moveable stage, and both of which can be automatically moved to capture images from different areas of the cartridge.
Display screen 200 may display the analysis results. Display screen 200 may be a touch screen, which may be used to interact with the device. In one embodiment, LCD touch screen is the "Thunderpack TAO-3530W" manufactured by Technexion™ of Taiwan, including its interface board. Alternatively, touch screen may be replaced with a display screen and keys for interaction with device.
Fig. 2 is an isometric diagram of the central internal components of the apparatus, according to an embodiment of the invention. Apparatus 100 includes touch screen 200, which is in wired communication with processor 210 and controller 220. Controller 220 may be a printed circuit board, designed to time and control the various operations of various other components.
Light source 340 is part of an optical viewing path, which includes angled mirror 520, beam splitter 350 and digital camera 500. Additional components of the optical viewing path are described in relation to Fig. 3. Optical viewing path acts to reflect an image from a cartridge undergoing analysis, after cartridge has been placed in cartridge support frame. Image is reflected towards digital camera 500.
Processor 210 is configured to receive images from the digital camera 500. Processor 210 then utilizes software of the invention to perform image analysis and compares a sample image to images stored in electronic memory, within a database of known images pertaining to known pathogens or known tissue views. In certain embodiments of the invention, processor and controller may be a single processing unit. Alternatively, any number of processors may be included in the invention, as deemed necessary. In certain embodiments, activation of the apparatus may be controlled by an external computer, such that the processor is located in the external computer.
Lateral movement servo 330 and longitudinal movement servo (shown in Fig. 4) are configured to move the cartridge support frame 310 including a cartridge, when present, in 4 horizontal directions, thus allowing scanning of the cartridge and capturing of several images from the entire area of a cartridge.
Referring to Fig. 3, a cartridge 380 is depicted, resting within a cartridge support frame 310. Hinged cover 300 (not shown) has been removed for ideal viewing. In this position, cartridge 380 is located within optical viewing path, as mirror 392 and LED circuit board 394 rest above cartridge 380 and are born by hinged cover 300 (not shown). Lens 396 is located beneath cartridge 380, thus focusing and continuing the optical viewing path. Referring to Fig. 9, an enlarged view of the cartridge is seen. Cartridge 380 receives and supports a sample for analysis, replacing a traditional slide. After placing a sample of human bodily material upon the cartridge, the cartridge may be inserted into the apparatus of the invention, for analysis. The cartridge may resemble a traditional slide for a light-microscope in general appearance and size, typically 75X25mm, and is typically for a single use per sample.
In the embodiment illustrated in Fig. 9, branched tracks 360 extend from an arched application recess 370. Branched tracks 360 act as microfluidic channels, to ensure diffusion of the sample over the majority of the cartridge 380 area by capillary force and can create a single layer of cells that is highly suitable for microscopic imaging. This novel cartridge design obviates the need for trained personnel to prepare the sample. Microfluidic channels typically have a maximal depth of 1mm.
The cartridge is typically disposable, however in certain embodiments it may be washed and reused.
The cartridge may additionally be pre-coated with various coatings useful for sample-preparation, such as staining, coatings for maintaining sample freshness or viability, for processing or pre-processing of the sample, and for facilitating imaging. The cartridge may be packaged to maintain the sterility and/or the quality of preloaded stains or reagents to prevent degradation during storage. The cartridge may have a secondary orifice to allow addition of another reagent after sample application has been performed.
USE OF THE INVENTION
According to a presently preferred embodiment, in use of the invention, a bodily sample is applied to the arched application recess 370 of a cartridge 380. The cartridge 380 is inserted into cartridge support frame 310, which is affixed to a moveable stage 320, and hinged cover 300 is closed. Referring back to Fig. 2, the controller 220 will activate light source 340, to emit a light beam to illuminate the cartridge. The light beam may be emitted from one light source or a number of different light sources each emitting light beams of different wave lengths, or a combination thereof. Light source is located internal to light source heat sink 610.
Referring now to Fig. 4, an isometric view is shown, in which certain upper or outer components have been removed, or made transparent for optimal viewing of the internal elements of the device. In one embodiment shown in Fig. 4, a white light source 340 and a blue light source 620 are included in the apparatus, and are manufactured by Quadica Developments Inc. of Ontario, Canada:
White light for transillumination is provided by a Luxeon® LXML-PWNl- 0120 Rebel Neutral White high power LED, producing 120 lumens of light at 350mA, and 220 lumens at 700mA.
Blue light for detecting epifluorescence is provided by Luxeon® Blue Rebel LED, 23.5 Lumens at 350mA and 48 Lumens at 700mA pre-soldered to a MCPCB base. The MCPCB base is a mounted heat sink. Additional components (not shown) may be included in the apparatus that allow florescence microscopy, such as an excitation filter, a dichroic mirror or beamsplitter, and an emission filter.
In certain embodiments, one or more of the following light sources may be used: a light emitting diode (LED), laser, halogen lamp, an arc lamp, white light, blue light, yellow light, green light, red light, ultraviolet light, and infrared light, to facilitate fluorescence and non-fluorescence imaging.
The controller 220 (shown in Fig 2) may select from among one or more emitting light sources, in order to change the wave length of the light beam according to the requirements and needs of a specific analysis.
Similarly, the controller 220 selects the exposure time, namely how long the light source will be on, how long the shutter time of the digital camera will be, the specifics of moving the moving stage (timing and direction of movement), focus and zooming in of digital camera, adjustment of the angle of angled mirror (for adjusting angle of beam, thus obtaining a depth- perspective of the sample).
Typically, several images representing a broad area of the cartridge are then captured by digital camera 500. Controller 220 co-ordinates timing and directional movement of the cartridge support frame 310 and moveable stage 320 bearing the cartridge, with the timing of activation of light source and with image capture of the digital camera, to ensure proper sequence is maintained and to ensure images are initially captured from different areas of the cartridge. Subsequently, when images have been processed and certain areas of the sample have been tagged as requiring additional analysis, controller may move the cartridge support frame 310, may move the stage 320, or may instruct camera to zoom in on these areas, may replace or add optical filters, or may illuminate the area of interest with a different light source to gather additional information.
Digital camera may be any electronic camera. In one embodiment, digital camera was monochrome 5Mpixel 12bit, CMOS (complementary metal-oxide- silicon) camera. Model no. BTE-B050-U, manufactured by Mightex Systems of Toronto Canada and California USA.
Camera includes a CCTV lens 510, or may have other type of lens. In a presently preferred embodiment, lens is a CCTV lens of 5 MP resolution, catalog number SV-5014H manufactured by NET of Finning, Germany.
In one embodiment, the resolution obtained was approximately 0.5 micron per pixel with a lOx objective. This resolution is sufficient to detect parasites such as T. brucei, which are typically 20 microns in length. In other embodiments, the resolution obtained was approximately 0.15 micron per pixel with a 40x objective, which is sufficient to detect parasites such as Plasmodium falciparum. Referring still to Fig. 4, objective lens 396 is located above angled mirror 520, and below cartridge 380. Angled mirror 520 reflects the illumination from the cartridge 380 in support frame 310 to the camera 500.
Optionally, the viewing path may include any of the following (not shown): a field, aperture and/or condenser diaphragm, one or more shutters, a condenser lens, a plurality of objective lenses of different magnifications, and a plurality of fluorescence filters of different optical passbands.
The digital image is then transmitted to processor 210 which is designed to process and analyze the image. The image processing techniques used for analyzing the picture are described hereinbelow in the section titled "Image Processing Modules".
Referring still to Fig. 4, lateral movement servo 330 and longitudinal movement servo 730 are depicted. Controller (not shown) can instruct lateral movement servo 330 to move the moveable stage 320, in order to scan and capture images from different areas of the cartridge (when present in the apparatus). In one embodiment, shown in the figure, servo is "Dynamixel AX-12A Robot Actuator" manufactured by Trossen Robotics LLC of Illinois, USA. Servo includes a gear reducer, DC motor and servo regulating circuitry.
The depicted cartridge support frame 310 is born by two horizontal rods 640a, 640b fixed to the upper surface of the moveable stage 320. Moveable stage 320 is also supported by two horizontal rods 690a, 690b which are perpendicular to the upper two rods, thus it is possible to shift the cartridge when present in its support frame 310, in all 4 cardinal directions, when lateral movement servo 330 and longitudinal movement servo 730 act to slide the movable stage 320 and/or cartridge support frame 310 on the rods. In certain embodiments, moveable stage may be moved using any of the following components: stepper motor, servo motor, lead screw, belt drive and worm drive. The controller 220 can instruct servos 330, 730, to move the cartridge in all the planar directions, either in a preset pattern or according to contemporary needs, whether for image capture of the whole cartridge or for picturing specific areas of interest on the cartridge. The images may be analyzed one by one or may be aggregated to be analyzed together. Images may be captured from each area one or more times, and may be sequential or non- sequential.
Referring to Fig. 5, an additional servo termed the "autofocus servo" 650, is a focus actuator that acts to focus objective lens.
Referring still to Fig. 5, lithium ion battery 660 is depicted, and acts to provide power to the apparatus when the apparatus is used in a remote location. Alternatively, apparatus may be connected to the electricity power grid using power inlet 670 for electrical cord, best shown in Fig. 6. Display screen 200 is shown in side view.
Strut 700 and stand 710 support horizontal rod 690b, which extends towards moveable stage 320. Sliding connectors 720a, 720b surround horizontal rod 690b, and are fixed to moveable stage 320, allowing stage 320 to slide upon rod 690b when longitudinal servo 730 exerts directional force upon stage 320.
In a presently preferred embodiment, processor 210 stores the images obtained, in local memory, and image analysis is performed within the apparatus. In addition the apparatus may send the images or portions thereof to be stored in an outer repository and/or analyzed on a remote computer.
Referring now to Fig. 6, for this purpose, Ethernet port jack 740 is included at the rear of the apparatus, and provides the apparatus with the option to be wired into a local area network or any other communication network for sending images obtained to a remote computer, or for communicating any other information. Optionally, remote computer may send and update images of known parasites for storing within the memory of the apparatus. USB port 750 additionally allows two way data transfer, such as of images captured.
Power inlet 670 is provided to connect the apparatus to the electrical grid, when desired. Power switch 770 is used to switch the apparatus on/off. Cooling fan 780 cools interior electrical components of the device.
The remote computer may be a central server which constantly receives images from apparatuses utilized at various locations, and server may be programmed to disseminate images of various new parasitical species to all users.
In an alternative embodiment, the images are uploaded to the remote server, where image processing and analysis is performed, and the final decision and pathogen identification is returned to the apparatus for display on the display screen. The image processing and analysis software of the invention may be run using processing hardware that may be included in the device, or can be collocated on a standalone computer, or may be run on a remote computer in communication with the device, such as over the internet. The computer software, in turn, makes use of machine vision algorithms that detects the presence or suspected presence of parasites and optionally other information about the parasites. Some embodiments of this software are described herein below. Image analysis can take place following, alongside and/or intermittently with image capture. AN ALTERNATIVE EMBODIMENT OF THE APPARATUS
In an alternative embodiment, the apparatus comprises the following central components:
Components manufactured by Olympus Corporation (Tokyo, JP) included: microscope BX43, manual florescence illuminator BX3-URA, Trinocular tube U-CTR30-2-2, Camera adapter with C-mount, 0.5x U-TV0.5xC-3-7, Quintuple revolving nosepiece U-5RE-2, Abbe condenser U-AC2, True color LED light source U- LHLEDC, Power Cord 1.8 M UYCP, FITC filter cube U- FBW, UPLFLN20X /0.5 Universal Plan Fluorite objective with 20x magnification, and UPLFLN40X/0.75 Universal Plan Fluorite objective with 40x magnification.
Components manufactured by Prior Scientific of Rockland, MA. USA, include: Optiscan XYZ stage (Cat. No. ES103PS) comprising: two 10-position filter wheels (for 25 mm diameter filters), probe encoder for Z, travel XY stage, focus drive with adapter, joystick, RS232 and USB cables.
Stage insert (Cat. No. H224LP) for l"x3"slide
Shutter 35 mm diameter, high temp (Cat. No.HF204HT)
Excitation adapter for BX/IX (Cat. No. HF235)
Emission Adapter for BX (Cat. No. HF239)
Transmitted Light adapter for BX3 (Cat. No. HF257)
Lumen 200 florescence illumination system (Cat. No. L200OL2)
Universal Stage insert for upright microscopes (Cat. No. H473UP). CLASSIFICATION FEATURES FOR PATHOGEN IDENTIFICATION
Central to the invention is the use of classification features which are associated with specific pathogens, in order to reach an algorithmic decision whether a pathogen is identified in the sample or not. Each pathogen is associated with specific visually identifiable classification features. These classification features can be collected when known samples are imaged using brightfield, darkfield, phase-contrast, any interference-contrast, or fluorescence microscopy. Samples can be treated to induce fluorescence, and samples can be viewed either with or without suitable staining. Non-limiting examples of classification features include:
• Typical motion: certain parasites are known to move in a specific directional course, and at a typical speed.
• Size.
• Presence of intracellular structures associated with the pathogen (e.g. nucleus, kinetoplast, granularity).
• Extraceullular structures associated with the known pathogen (e.g. flagella, knobs).
• Location with respect to other sample elements (e.g. whether suspected parasite is within a red blood cell).
· Aspect ratio: the ratio between the length/width of suspected structures.
• Optical density (intensity shade).
• Florescence in various channels: each pathogen is associated with specific florescence which can be viewed upon illumination and emission-filtering at predetermined wavelengths.
• Optical birefringence: illumination in a specific wavelength results in detection of internal structures in certain parasites.
• Clustering behavior: parasites maintain typical distances between one another within the human body. • Distance from human cells to suspected pathogen: Typically, pathogens maintain a predetermined distance between themselves and human cells.
• Pattern matching: general appearance of pathogen.
In a presently preferred embodiment, the set of classification features is relatively small for each known pathogen, thereby their use for classification of a suspected pathogen is efficient and rapid.
SAMPLE PREPARATION AND IMAGE CAPTURE
The method and apparatus may be used on biological samples from various tissue sources or their combinations These sample materials can include but are not limited to blood (peripheral or otherwise), lymphatic fluid, cerebrospinal fluid (CSF), urine, fecal matter, saliva, and tissue biopsies (for example, muscle, liver, etc.)
The biological sample is prepared for imaging using methods known in the art, such as thick or thin peripheral blood smears, or using a cartridge as presented herein. The sample may be stained with a sample-appropriate stain, before the sample is applied to the slide or cartridge, for example acridine orange may be added to peripheral blood samples. Alternatively, the sample may be stained after application to the slide or cartridge, for example by dipping a thin or thick smear preparation into a stain. Optionally, a staining reagent may be present within the cartridge. Certain samples are best analyzed without undergoing staining.
Images are obtained using one or more imaging modalities to illuminate the sample, including for instance, brightfield, darkfield, phase-contrast, any interference-contrast and fluorescence microscopies. One or more optical filter combinations may be included in the device, and used for example, in excitation and emission light paths. One or more light sources may be used. One or more magnification powers may be utilized, and images may be obtained at one or more locations within the sample. Images may be captured using one or more focus depths for each sample or for each imaging location.
Fluorescence microscopy offers unique advantages in the context of the invention. Most notably, by employing a suitably chosen fluorescent staining or by imaging suitable autofluorescence channels, the resultant images can emphasize pathogen markers. For example, when blood is stained with acridine orange, fluorescence images reveal only white blood cells and parasites, due to their nucleic-acid content; red blood cells remain invisible. Such emphasis can greatly ease the computation burden on machine-vision algorithms. Furthermore, fluorescence and autofluoresence permit the identification of defined sample or cell components (such as DNA, RNA, or cell membranes). This significance can be used to inform machine -vision algorithms, thereby yielding substantially improved results.
Microscopic imaging can take advantage of autofocus capabilities. These can be implemented, for example, by providing the objective (or potentially any other lens in the optical path) with an actuated stage, actuating the sample support stage in the optical direction or by providing focus control in the camera. Focus information for the control of such actuators can be computed based on captured image sharpness, which may optionally be automatically obtained for this purpose, or with a hardware-based autofocus system, such as one based on laser return (e.g. Prior Scientific LF210). In other embodiments, the invention can take advantage of objectives with high depth of fields or with one of a number of computational and hardware techniques to extend depth of field that are known in the art ("Extended depth of field" methods). Different embodiments may take advantage of one or several stains or staining methods. These methods may result in a change in optical absorption, opaqueness or scattering, and may influence the color or fluorescence observed in the sample. Some stains include but are not limited to; acridine orange, Giemsa stain, Romanowsky stain, Leishman stain, H&E stain, Jenner stain, Wright stain, Field stain, silver stain, Papanicolaou stain, Sudan stain, Masson's trichrome, Gram stain, eosin, orange G, DAPI, Ethidium bromide, Hoechst, SYBR stains, and other nucleic acid stains. In addition, the components, partial compositions or the combinations of these stains are possible. Some stains and combinations may produce effects in multiple imagining modalities: for example, Giemsa stain produces both a color that is visible in brightfield microscopy and a fluorescence signature that is visible in epifluorescence microscopy. In another example, while eosin is typically used for its chromogenic effect, it also carries a distinct fluorescent signature, which can be advantageous.
In particular embodiments, single or multiple stains can be imaged for fluorescence using one of more excitation wavelengths and imaged using multiple emission filters to yield multiparametric image data. For example, samples stained using acridine orange can be illuminated using blue fluorescent excitation (e.g. wavelengths 460nm to 495nm) and imaged, either sequentially or simultaneously, using an emission filter or filter combination for yellow-green light (e.g. bandpass filter for 515nm to 535nm) and an emission filter or filter combination for red light (e.g. longpass filter for 600nm and up). In this case, the yellow-green filtered image corresponds roughly to sample DNA content, whereas the red filtered image corresponds roughly to sample RNA content. Such multiparameteric biologically- meaningful data can be used to identify various parasites, using the software algorithms of the invention. In the preferred embodiment, multiple fluorescence images are obtained in part by mechanically switching optical filters and/or dichroic beamsplitters/mirrors in and out of the optical path. In other embodiments, the optical path is split at least once using dichroic or partial beamsplitters/mirrors and multiple fluorescence images (or fluorescence and non-fluorescence images) are obtained on multiple cameras. In the preferred embodiment, the one or more cameras are high- sensitivity CMOS cameras, such as those based on the Aptina/Micron MT9P031 sensor family. In alternative embodiments, any of the cameras can be CCD, cooled CCD, intensified CCD, or electron-multiplied CCD.
A cartridge or a traditional slide is used to support the sample for analysis within the apparatus of the invention. The cartridge is intended to simplify sample preparation, and is the presently preferred embodiment. Correspondingly, in particular embodiments, the cartridge may be designed to present a single layer of cells in order to ease microscopic imaging. Use of a cartridge presents an improvement over prior art, since prior art sample preparation is known to require training, experience and time. For example, thick blood smears typically take over an hour to dry, whereas thin blood smear require significant operator skill in order to yield large useful area. The cartridge may be disposable or reusable. In particular embodiments the cartridge has dimensions similar to a typical microscope slide, 1" x 3" or 25mm x 75mm. In a preferred embodiment, the cartridge has one or more fluidic or microfluidic channels, which may optionally be connected to each other to facilitate simultaneous filling. These channels may be comprised of at least one section with a channel height that permits only a single layer of cells to fill it, hence presenting a monolayer for imaging. In the preferred embodiment, the channels may be designed for capillary filling, for example, by choice of materials, coatings or postprocessing, as is known in the art. In certain embodiments the cartridge may be prefilled or pretreated with a staining reagent or reagents, which may be stored as a liquid, solid, a coating or dried within the cartridge. In particular embodiments, the cartridge is preloaded or pretreated with one or more anticoagulation reagents. In some embodiments, stains and/or anticoagulation reagents are added to the sample before loading onto the cartridge. In some embodiments the cartridge is sterile or sterilized. In particular embodiments, the cartridge is packaged to maintain the sterility or the quality of preloaded stains or reagents to prevent degradation during storage. In some embodiments, the cartridge permits washing, staining or otherwise treating the sample using reagents that are provided externally or that are preloaded.
In some embodiments, the sample may be prepared, loaded onto a cartridge or microscope slide, or stained using one or more automated instruments. Each such instrument may either be separate from or may be included in the apparatus of the invention. For example, the apparatus may employ a Prior Scientific™ PL200 slide loader to automatically load microscope slides of cartridges with a microscope-slide form factor of l"x3". Alternatively, the slide loader may be modified to additionally dip the slide into appropriate staining and washing solutions.
In one embodiment, a sample of ΙΟμΙ is sufficient in volume for analysis. In case of a blood sample, a finger prick can be utilized to obtain this minute quantity, with blood being collected into a capillary, thus obviating the need for trained blood technicians for taking a sample from a patient. The capillary can then be brought into contact with the cartridge to apply the blood sample to the cartridge.
Suitable processors for implementation of the invention include, by way of example, both general and special purpose microprocessors. Generally, a processor will receive instructions and data from a read-only memory and/or a random access memory.
The apparatus may include one or more mass storage devices for storing data files (such as images obtained or images of known pathogens). Such mass storage devices include magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and optical disks. Storage devices suitable for tangibly embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM disks.
After the analysis is completed, the cover 300 may be opened and the cartridge may be taken out and disposed of, after which, the apparatus 100 is ready for a new analysis. Sample removal can be automated, for example, using a Prior Scientific PL200 slide loader.
IMAGE PROCESSING MODULES
A number of modules are described below for processing an image and finding pathogens. The apparatus described above may utilize one or more of the following image processing modules. In one embodiment the apparatus invokes the following modules in a preset sequence. The following description is a presently preferred order of the processing steps, although alternative embodiments may use a different order:
1. Parasite Candidate Detection Module: This module scans an entire image, which depicts a field within the sample, and searches for patches in the image within which it is likely that a pathogen of interest, referred to hereinafter as the "target", appears. One or more of the following methods may be used to detect these candidate patches: Pattern matching - if the general form of the target is well defined, a pattern describing this form is constructed in a pre-processing stage: numerous examples of its form are manually collected, and the general pattern is extracted. When processing an image, this pattern is then matched at every location, and those locations which exhibit high similarity to the pattern are taken as candidates. In an example of preprocessing, a human operator collects a number of images, containing a known target microorganism, and marks the target on these images. Then these marked images are fed to a processor adapted to extract the general pattern of the target, based on the numerous images of the target. This pattern matching module, which is invoked by the apparatus, can use the resultant pattern of the target for finding other similar patterns in the image. The threshold of high similarity may be flexibly defined using trial and error, which may be steered by the application, or it may be defined rigidly as a pattern which has 90% similarity to the general pattern of the pathogen. Various image-processing filters (e.g. wavelettes) may be applied to enhance the features in the image which are relevant to the target's pattern and suppress those which are not. For example, when seeking pathogens which are well defined by their boundary, an edge-avoiding wavelette may be used to smooth out noise, while keeping the sharp features of the pathogen's boundary.
Model matching - if the general pattern of the target can be described by a simple model of a few image parameters (e.g. a blood cell can be described by a circle or an ellipse), patterns of this model are sought out in the image. In one embodiment, Hough transform may be used to transform the image into the parameter space, and parameter sets which gain support from numerous pixels are taken as candidates. Motion detection - Using the Motion Field Detection Module (described below) the image can be segmented into pixels which are part of the ambient motion field, and pixels which move differently, i.e. move in other directions. The latter are clustered together spatially. The clustering algorithm takes into account the form and movement of the desired target. Clusters which confer to the characteristics of the target, such as size, are taken as candidates.
d. High fluorescence— The fluorescence image, which roughly overlays the intensity image, is segmented and clustered in a manner analogous to the motion detection above. Instead of looking for patches which move differently from the background, patches whose fluorescence is higher than the background, e.g. patches having high SNR, are sought. High fluorescence can refer to high fluorescence intensity values, or high sum fluorescence, e.g. as integrated over an area.
e. Multi Frame - Using the Tracking Module (described below), multi- frame candidates (described below as well) are tracked to frames in which they are likely to appear. If the tracking is successful, the location to which the candidate was tracked is taken as a candidate in that frame.
Note that this can be done in batch or on-the-fly. In a batch implementation, multi-frame candidates are tracked to temporally- adjacent frames, leading to new candidates. This is done iteratively to enhance the construction of multi-frame candidates.
In an on-the-fly implementation multi-frame candidates are found and processed as the images are being streamed into the processing device. They can be tracked only forward in time, and the process is performed only once.
The second step of the sequence may be:
2. Single Frame Classification Cascade Module: may also be called "Multi Frame Classification Cascade Module". This module receives candidates, from the first step, in a single frame, and computes the likelihood that they indeed contain an occurrence of the desired target.
The main tool used in this module is a Classifying algorithm. Classifying algorithms are machine-learning algorithms which may operate according to the following techniques used in sequence:
a. A set of "classification features"— functions of the data to be classified - are determined. Therefore, these classification features must be relevant to the objects which are being classified. In our case these classification features may include the intensity and gradient of the candidate, the fluorescence of the candidate and/or motion of the candidate. Additional classification features are described hereinabove, in a separate section. The images are then processed to create rotationally-invariant images, to make the classifying features independent of the viewing angle.
Magnification also affects the type of classification features used. In low magnification, the contour of the microorganism is an important hint, while in high magnification, finer details, such as pathogen- specific internal or external structures, are used.
b. In a pre-processing stage, the classifying algorithm is "trained" to differentiate between sets of classification features which describe the target and sets which do not. This is done in a so-called supervised manner, where clips in which all occurrences of the desired target are manually tagged. The Parasite Candidate Detection Module is then used on these clips. The candidates the module outputs, along with their manual tags, are used as input to train a maching-learning algorithm, such as a Support Vector Machine (SVM). An SVM is a known classifier, which uses tagged inputs as above to construct a separator in the features space between true and spurious candidates. Other machine-learning algorithms are known in the art. c. When processing new data, the same set of classification features is extracted. The machine-learning algorithm, such as SVM, determines the likelihood of this set representing a true occurrence of the target using the separator constructed in the pre-processing stage.
The Single Frame Classification Cascade Module may employ a cascade of classifying algorithms. Candidates which are found to be highly likely to contain a target are passed to the next classifying algorithm. This cascade allows using more powerful (and computationally intensive) classifying algorithms along the cascade— the fewer candidates remaining, the more powerful the classifying algorithm can be, while maintaining reasonable running times. Importantly, the pre-processing training of a classifying algorithm is done on the output of the previous classifying algorithm up the cascade.
In addition to classifying candidates, the Single Frame Classification Cascade Module may also align them to canonical coordinates. This augments and complements the selection of rotationally-invariant features, allowing some flexibility in the latter. That is, classification features which are not invariant to rotation are still sometimes used, and the alignment phase rotates the patches to a canonical angle.
For example, when seeking the appearance of the ring-form of the malaria pathogen P. falciparum, it may be important that the ring form appears roughly in the same relative position within the patch. Candidates which pass the entire cascade are called "single-frame candidates".
In an alternative embodiment, classification features and/or the separator may be determined or modified manually or with non-machine-learning analysis algorithms. For example, the human expert knowledge of a trained medical professional may be transcribed into classification features or separator algorithms that may be used independently or to supplement machine-learning based processing. In some embodiments, such as when parasite motion is of diagnostic value, the third step of the sequence may be:
3. Multi-Frame Candidate Construction Module: This module clusters together appearances of the same target in multiple frames.
Single-frame candidates may be matched to other such candidates based on their location in the image. If the target is relatively static, then candidates are matched if they are roughly in the same location in the image (or, more precisely, in the same relative location within the motion field). More generally, if the target is moving, it is tracked using the Tracking Module (described below), and is matched to candidates appearing in roughly the same location to where it is tracked.
In effect, the Multi-Frame Candidate Construction Module constructs a graph with the single-frame candidates as its vertices, and matches defining edges. Connected components within this graph are checked for coherency, i.e. that the target appears "the same" in all occurrences. In an iterative implementation, temporal gaps within these components may be filled by extrapolating the locations of missing occurrences, and processing them with the Single-Frame Classification Cascade Module. In this case, the entire set of single-frame classifying algorithms may be used, rather than conditioning on pervious results, since only a small number of candidates are processed this way.
The coherent, and possibly gap-filled, backbone of the connected components is the multi-frame candidate— a collection of all single-frame appearances of a specific target along with the results of its classification cascade.
The other steps of the sequence may be:
4. Multi-Frame Candidate Tracking Module: partially-constructed multi- frame candidates may be tracked to frames temporally-adjacent to the ones in which their single-frame constituents were identified in the previous step. This can be done by various computer-vision algorithms, such as mean-shift or differential methods.
The purpose of this module is twofold. First, it facilitates initial candidate detection when other signals are weak. Candidates are created in location to which multi-frame candidates were tracked, as described in the Parasite Candidate Detection Module, above.
Second, tracking defines the matching of single-frame candidates, on which the construction of multi-frame candidates is based. Thus, the multi-frame construction can be seen as a form of agglomerated clustering: initially all single-frame candidates are distinct multi-frame candidates. They are then iteratively tracked, matched, and merged together into bigger clusters.
Note that in a sequential implementation tracking is done from one frame to the next, and thus multi-frame candidates are also constructed sequentially.
5. Multi-Frame Candidate Classification Module: Once the entire set of target occurrences is determined, it may be classified as a whole. Technically, this is similar to the single frame classification, but here features from multiple images are used, as well as the relations between them (e.g. the trajectory of the target).
This module determines, for each multi-frame candidate, the likelihood that it's a true occurrence of the desired target.
6. Non-pathogen Sample Content Classification Module: This module may be used to identify sample elements that are not the pathogens themselves but are useful in determining pathogen presence. For example, red blood cells may be identified in malaria diagnosis in order to determine whether a suspected target is located within a red blood cell. Similarly, white blood cells may be identified in order to rule out their nuclei as suspects. This module may itself take advantage of the same algorithms and modules that are described for the identification and analysis of pathogen suspects.
7. Sample Classification Module: Based on the set of classifications of all multi-frame candidates, the sample is classified as either containing the defined microorganism or not containing it.
The following steps are auxiliary steps of the sequence:
8. Motion Field Construction Module: The purpose of this module is to construct the image of the blood ambient background at each image-capture time point. When the blood is not moving, several frames are taken around the time point, and for each pixel taking the median value at its location. More generally, dense optic flow may be used to determine the motion vector of the background from frame to frame, by taking the mean motion value. The background image is constructed by taking the median value of pixels in the same location relative to the background motion.
9. Image Verification Module: The purpose of this module is to recognize and report poor samples, such as images taken from a blocked lens or damaged camera or images in which the sample does not appear at all.
This is done by verifying the values of simple image statistics (e.g. intensity, gradients), and the identification of known objects (e.g. blood cells).
10. Camera/Microscopy Control Module: The purpose of this module is to control image capturing.
In a sequential implementation, the location and magnification can be adjusted to clear ambiguities in the image. For example, the camera can be adjusted to zoom in on a candidate, to visualize it in finer detail. Additionally, the module may control exposure, illumination parameters and aperture parameters in order to obtain optimal images. 11. Masking Module: The purpose of this module is to identify regions in the image in which targets are not likely to occur. Such regions are ignored by the Parasite Candidate Detection Module.
Masking out image regions allows for quicker processing rate, and robustness against artifacts.
The invention is embodied in any suitable programming language or combination of programming languages, including Google Web Toolkit, JAVA, database managers and MySQL.
Each software component can be implemented in a high-level procedural or object-oriented programming language, or in assembly or machine language if desired. The programming language may be a compiled or interpreted language.
Images are entered into and saved in a database which may be any suitable database for storing data objects and metadata relating thereto. Any suitable database program may be used. In one embodiment, the database is a relational database and a key/value database. In one embodiment, database is a modified relational database. The search logic used for subsequent retrieval of experiments from the database, is any suitable step, process, function or series of steps, processes and functions known in the art for searching a database.
The software of the invention may include a graphical user interface (GUI). The contents of the screens, the functionality of the system and the work process may be adjustable to a user's needs. The screen designs, terms and work process reflect the medical field and are user-friendly since they display and interact with the user in syntax familiar to medical technicians. Thus use of the system may appear intuitive. The final analysis result, which is displayed onscreen, may include the presence or suspected presence of parasites, as well as parameters regarding parasites detected, such as: their type or species, parasite load or number, life stage or maturity and any other medically relevant information. In addition, the software may report medically pertinent information obtained from the biological sample yet unrelated to parasites, (such as detection of anemia, or detection of an unusual white blood-cell count). Information relevant to the quality of the test or sample may be displayed.
In alternative embodiment, it may be desirable to have a user verify the analysis result or authorize the last step of the analysis. In such cases, this can correspond to providing images corresponding to detection of suspected pathogens, in the final result. In other cases, the separator or separator may be configured such that the provided images are only highly enriched for potential pathogens, enabling the user to make a determination based on a condensed subset of information. In these latter cases, the algorithm can be tuned to provide very high sensitivity at the cost of lower specificity. EXAMPLES
EXAMPLE 1; Detection of Trypanosoma Cruzi or Trypanosoma brucei
Trypanosoma Cruzi is the parasite responsible for the potentially fatal Chaggas disease. One of its life cycle stages (Trypomastigotes) occurs in the blood, where it has a worm-like shape - an elongated body and a flagellum— which constantly twirls and spins in the blood. This motion is the cue for the detection algorithm.
Human African trypanosomiasis, also termed "African Sleeping Sickness", is caused by trypanosome parasites Trypanosoma brucei. There is NO immunological or genetic laboratory test for identification of the parasites to date. The software of the invention successfully identified the trypanosome parasites by tracking motion of pixels within successively captured images, in a peripheral blood sample, thus identifying typical motion associated with trypanosome parasites.
Referring to Fig. 7, an image captured shows Trypanosoma brucei parasites (indicated by arrows), surrounded by red blood cells.
Referring to Fig. 8, after the sample was dyed fluorescently the algorithm successfully tracked motion of florescent particles (indicated by arrows), and correctly identified this motion as typical in speed and direction to trypanosome parasites. An identification of trypanosome parasites was displayed onscreen.
Using the Detection Algorithm:
1. Prepare thin blood smears upon a cartridge, and capture images.
Divide the images into fields of images. Analyze each field independently by recording a series of images from that field, effectively creating a clip of images.
2. For each frame, verify its validity using the Image Verification Module.
If more than a specified number of consecutive images are poor (e.g. 4 images), report an error on this field.
3. Normalize the image to compensate for lighting variance, since typically the image is more strongly illuminated at its center.
4. For each frame in the clip, construct the background image using the Motion Field Construction Module. In thin blood samples it is possible to wait for the red blood cells to dry in order to use the simpler version of the algorithm. 5. Create initial single-frame candidates using the Motion Detection method of the Parasite Candidate detection Module.
6. Proceed to the next frame:
1. Use the Multi-Frame Candidate Tracking Module to track the single-frame candidates to the next frame,
2. Repeat steps 2-4 above for the next frame.
7. Use the Multi-frame Candidate Construction Module to match candidates from one frame to the next one.
8. Classify candidates which were matched for at least a specified fraction of consecutive frames (e.g. 3 of 4 frames) using the Multi- frame Candidate Classification Module.
9. Record the number of candidates classified as "true" targets (an appearance of T. Brucei), over all fields.
10. Determine if the blood sample is contaminated using the Blood Sample Classification Module.
Using the Training Algorithm - Single Multi-frame Candidate Classification Module:
1. Run the detection algorithm up to step 6
2. Tag the candidates as "true" and "false" occurrences of T. Brucei.
3. Create a database of false and true occurrences. In the database each occurrence appears multiple times, e.g. 12, by uniformly rotating it.
4. Extract classification features for each database entry. For example, compute a Census Transform of the entry: divide the result into equal- sized rectangular regions (e.g. 9 non-overlapping squares) and compute a histogram of the census transform in each region. The feature vector for the entry is a concatenation of these histograms.
5. Train an SVM classifier with a polynomial kernel (e.g. a 2nd degree polynomial) on this database.
Using the Training Algorithm - Blood Sample Classification Module:
1. Run the detection algorithm up to step 9.
2. Tag each sample as "clean" or "contaminated".
3. Create histograms of the number of "true" candidates over the "clean" samples and over the "contaminated" samples.
4. Determine the optimal value that differentiates between these two histograms (in the sense of maximum likelihood). This value determines how a blood sample is classified in the detection algorithm.
EXAMPLE 2: Detection of Plasmodium and Babesia species
Plasmodium are parasites responsible for Malaria disease; Babesia are parasites responsible for Babesiosis disease. Both types of parasites infect red blood cells (RBCs) and in the initial stages of the infection form ring-like structures. Importantly, normal RBCs expel their organelles, and in particular their nucleus, before entering the blood stream. Hence the goal is to detect RBCs which contain a significant amount of DNA, indicating parasitic infection of Plasmodium or Babesia.
Plasmodium and Babesia species of interest include P. Falciparum, P. Vivax, P. Ovale, P. Malariae, B. Microti and B. Divergens.
Detection Algorithm: Initially, the blood is stained with fluorochromatic dyes such as Acridine Orange, Giemsa or Ethidium Bromide. Dyes which stain DNA and not RNA or which create a contrast between the two, are preferable.
A thin blood smear is prepared upon a cartridge, images are captured, and the images are divided into fields, as explained in the first example. Each field is analyzed independently by recording two images from that field - a "bright field" (BF) image (visible light) and "florescence image" (FL) radiated with a wave length appropriate to cause the dye to fluoresce.
For each BF-image, verify its validity using the Image Verification Module. If more than a specified number of images are poor (e.g. > 10%) report an error on this field.
Normalize the image to compensate for lighting variance, since typically the image is more strongly illuminated at its center.
For each FL-image, locate high-intensity patches, indicative of DNA using the High Fluorescence method of the Parasite Candidate Detection Module.
For each such patch, tag it as inside a RBC, and identify a candidate RBC, if one the following holds:
a) A Hough Transform of its vicinity indicates that it's contained inside a circle in the image whose size is appropriate for a RBC. This is, effectively, the use of the Model Matching method of the Parasite Candidate Detection Module.
b) A contour detection algorithm of its vicinity indicates that it's within a convex shape in the image, whose size is appropriate for a RBC. c) The Pattern Matching method of the Parasite Candidate Detection Module processing the patch's vicinity locates a strong RBC pattern overlapping the patch.
7. Using the Single-frame Classification Cascade Module, each candidate RBC is classified as to whether or not it's a RBC containing a parasite.
8. Record the number of candidates classified as "true" (an appearance of an infected RBC), over all fields.
9. Determine if the blood sample is contaminated using the Blood Sample Classification Module.
Training Algorithm - Single-frame Candidate Classification Cascade Module:
In this embodiment, there is no true cascade, just a single classification algorithm.
1. Run the detection algorithm up to step 6
2. Tag the candidates as "true" or "false" occurrences of infected RBCs.
3. Create a database of false and true occurrences. In the database each occurrence appears multiple times, e.g. 12, by uniformly rotating it.
4. Extract classification features for each database entry. For example, compute the Census Transform of the entry; divide the result into equal-sized rectangular regions (e.g. 9 non-overlapping squares) and compute a histogram of the census transform in each region. The feature vector for the entry is a concatenation of these histograms.
5. Train an SVM classifier with a polynomial kernel, e.g. a 2nd degree polynomial, on this database.
Training Algorithm - Blood Sample Classification Module: 1. Run the detection algorithm up to step 8.
2. Tag each sample as "clean" or "contaminated".
3. Create histograms of the number of "true" candidates over the "clean" samples and over the "contaminated" samples.
4. Determine the optimal value that differentiates between these two histograms (in the sense of maximum likelihood). This value determines how a blood sample is classified in the detection algorithm.
In summary, the apparatus and method of the invention answer a long-felt need for automatic identification of pathogens, and especially of parasites within a mammalian sample. The apparatus and method allow rapid identification of parasites that previously required use of expensive resources and trained personnel that are unavailable in many third world countries. The invention now allows blood donations and blood tests to be screened for parasites, such that a single run through the apparatus will identify a great many parasites, representing maximal efficiency. The apparatus and method overcome the difficulty of parasites constantly evolving, as an image of the new species may be easily uploaded into the database of known images and the characteristics of the new species may be analyzed to allow its identification in future.
While some embodiments of the invention have been described by way of illustration, it will be apparent that the invention can be carried into practice with many modifications, variations and adaptations, and with the use of numerous equivalents or alternative solutions that are within the scope of persons skilled in the art, without departing from the invention or exceeding the scope of the appended claims.

Claims

1 . An apparatus for automatic detection of pathogens within a sample, comprising:
a) a cartridge support frame for receiving and supporting a cartridge having a sample within or thereupon;
b) an optical imaging system having an optical path and comprising: at least one light source, at least one lens, and at least one digital camera; wherein said cartridge support frame is located within or may be moved into said optical path, such that images of said sample may be captured by said at least one digital camera;
c) at least one processor interacting with and activating at least one of components a)-b); wherein said processor is adapted to perform image processing using classification algorithms on visual classification features to detect one or more suspected pathogens, when present, in said sample.
2. The apparatus of claim 1, wherein said cartridge support frame is coupled to a moveable stage, movable in at least one dimension.
3. The apparatus of claim 1, wherein the optical imaging system further comprises a focus actuator for focusing upon an image.
4. The apparatus of claim 1, wherein said optical imaging system further comprises a plurality of objective lenses of varied magnification.
5. The apparatus of claim 1, wherein said optical imaging system further comprises: at least one optical filter or at least one dichroic beamsplitters/mirror, for exciting or detecting fluorescence.
6. The apparatus of claim 5, wherein said optical imaging system further comprises an actuator to switch said optical filters or said dichroic beamsplitter/mirror in and out of said optical path.
7. The apparatus of claim 1, wherein said at least one processor performs at least one of the following: • selecting at least one light source from among a plurality of light sources, and activating said light source;
• selecting an exposure time of a light source;
• selecting an exposure time for said digital camera.
8. The apparatus of claim 1, wherein at least one of said at least one processor outputs a result that includes at least one of the following: the presence or absence of a pathogen; the species of pathogen; the number or concentration of pathogens detected; the life stage of said pathogen; a finding of anemia; a finding of an unusual white blood cell count; and information on the quality of the sample.
9. The apparatus of claim 1, wherein said processor outputs one or more images of suspected pathogens.
10. The apparatus of claim 1, wherein pathogen is a parasite.
11. The apparatus of claim 1, wherein said processor is present in an external computer wired to at least one of the following: to one or more internal processors, and to said digital camera.
12. The apparatus of claim 1, wherein said processor is connected via a data network to at least one of the following: to one or more internal processors, and to said digital camera..
13. The apparatus of claim 1, wherein one or more images captured by said apparatus are sent to a remote server for image processing at a remote location.
14. The apparatus of claim 1, wherein visual classification features or updated images of known pathogens or other software updates are uploadable to said apparatus.
15. A cartridge for supporting a sample, wherein said cartridge comprises at least one microfluidic channel upon said cartridge.
16. The cartridge of claim 15, wherein said cartridge has dimensions of 25mm x 75mm.
17. The cartridge of claim 15, having a plurality of microfluidic channels, and said channels are connected to one another to facilitate simultaneous filling.
18. The cartridge of claim 15, wherein said microfluidic channel has a channel height permitting only a single layer of cells to fill said channel height, thereby presenting a monolayer for imaging.
19. The cartridge of claim 15, wherein said channel is manufactured with a hydrophilic material or is treated to promote capillary filling.
20. The cartridge of claim 15, wherein said cartridge further comprises a staining reagent, present in a form selected from: a liquid, solid, a coating, and dried within said cartridge.
21. The cartridge of claim 15, wherein said cartridge further comprises with one or more anticoagulation reagents.
22. The cartridge of claim 15, wherein said cartridge comprises a secondary application orifice allowing addition of an additional reagent to said sample after sample application is completed.
23. The cartridge of claim 15, wherein said cartridge is sterile.
4 . A method for automatic detection of pathogens within a sample, comprising: performing image processing of at least one digital image captured using classification algorithms, said image processing including extracting visual classification features from said image.
25. The method of claim 24, comprising the step of obtaining one or more digital images of a sample using an automated microscopy system comprising at least one light source, at least one lens, and at least one digital camera; said images are obtained prior to image processing.
26. The method of claim 24, wherein said sample is a slide selected from one or more of the following: a blood smear (thin or thick), a fecal smear, a lympathic smear, a cerebrospinal fluid smear, and a tissue biopsy.
27. The method of claim 24, comprising the step of preparing a sample within a cartridge, performed prior to said imaging
28. The method of claim 27, wherein said cartridge is disposed of after use.
29. The method of claim 27, wherein said cartridge is reusable.
30. The method of claim 27, wherein said cartridge comprises microfluidic channels for creating a monolayer of cells in at least one area, in order to facilitate imaging.
31. The method of claim 27, wherein said cartridge is filled using capillary filling.
32. The method of claim 31, wherein said capillary filling is done by touching said cartridge to a pin-pricked digit.
33. The method of claim 27, wherein said preparing the sample further comprises staining the sample with one or more stains.
34. The method of claim 33, wherein said one or more stains are selected to affect a change in at least one of the following: optical absorption, opaqueness, scattering, and color of structures within a sample.
35. The method of claim 33, wherein said one or more stains include acridine orange, and wherein a plurality of said one or more digital images are taken using configurations that allow discerning respective staining of DNA and RNA.
36. The method of claim 33, wherein said one or more stains include Giemsa, Romanowsky or related stains.
37. The method of claim 27, wherein said sample is anticoagulated before or after application to said slide or cartridge.
38. The method of claim 37, wherein said sample is anticoagulated by preloading one or more corresponding reagents onto the cartridge.
39. The method of claim 27, wherein said cartridge is sterilized.
40. The method of claim 25, wherein said obtaining one or more digital images includes moving the slide or cartridge with respect to the automated microscopy system in order to image multiple locations within a sample.
41. The method of claim 25, wherein said obtaining one or more digital images includes automatically focusing the sample for the said digital images.
42. The method of claim 41, wherein said focusing includes moving at least one of the following: said at least one lens, said slide or cartridge, and said at least one component of the at least one digital camera.
43. The method of claim 25, wherein said obtaining one or more digital images employs at least one of the following: brightfield, darkfield, phase-contrast, any interference-contrast, and fluorescence microscopy and any combination thereof.
44. The method of claim 25, wherein said obtaining one or more digital images employs a plurality of objective lenses of varied magnification.
45. The method of claim 25, wherein said obtaining one or more digital images employs one or more optical filters or one or more dichroic beamsplitters/mirrors for exciting or detecting fluorescence.
46. The method of claim 25, wherein said obtaining one or more digital images includes obtaining a plurality of digital images for at least one sample location and employing a plurality of microscopy methods.
47. The method of claim 46, wherein said plurality of microscopy methods comprise different fluorescence excitations and/or emissions.
48. The method of claim 25, wherein said obtaining one or more digital images utilizes a processor that interacts with and activates mechanical and optical components by performing at least one of the following:
• selecting at least one light source from among a plurality of light sources, and activating said light source;
• selecting an exposure time of a light source;
• selecting an exposure time for said digital camera
49. The method of claim 24, wherein said image processing outputs a result that includes at least one of the following: the presence or absence of a pathogen; the species of pathogen; the number or concentration of pathogens detected; the life stage of said pathogen; a finding of anemia; a finding of an unusual white blood cell count; and information on the quality of the sample.
50. The method of claim 24, wherein said image processing outputs one or more images of suspected pathogens.
51. The method of claim 24, wherein said pathogen is a parasite.
52. The method of claim 24, wherein at least one of said one or more digital images is captured at a first location and is processed using a processor located at a second location.
53. The method of claim 24, wherein at least one of said one or more digital images is sent to a remote server.
54. The method of claim 24, wherein said image processing or other software is updated remotely.
55. The method of claim 24, wherein said classification features include one or more of the following: motion, size, shape, coloring, contrast, location in respect to additional biological structures, presence of internal structures, presence of extracellular structures, the aspect ratio, the optical density, florescence at predetermined wavelengths, optical birefringence, clustering behavior, and pattern matching.
56. The method of claim 24, wherein said image processing includes searching at least one of said one or more digital images for at least one patch which is likely to contain a target in said digital image and marking it as a candidate.
57. The method of claim 56, wherein said image processing further includes at least one of the following:
■ calculating the likelihood that said at least one candidate contains a target; ■ processing said candidates for finding if more than one candidate belongs to the same target, and where found, candidates of the same target are clustered together;
■ tracking at least one candidate, in relation to said at least one cluster, that may belong to said cluster, and where said tracked candidate belongs, adding said tracked candidate to said cluster;
■ determining and classifying the likelihood that said at least one cluster contains a target; and
■ determining if said image contains a target, based on said classification, and thus determining if said sample contains a pathogen.
58. The method of claim 56, wherein said searching for at least one patch which is likely to contain a target is performed using at least one of the following: pattern matching, model matching, motion detection, high florescence segmenting and clustering, and multi-frame tracking.
59. The method of claim 24, wherein said image processing is performed using at least one of the following modules: a single frame classification cascade module; a multi-frame candidate construction module; a multi-frame candidate tracking module; a multi-frame candidate classification module; a sample classification module; a motion field construction module; an image verification module; a camera control model; and a masking module.
60. The method of claim 24, wherein said image processing is performed in an aggregated processing manner.
61. The method of claim 24, wherein said image processing is performed on-the-fly.
62. The method of claim 24, wherein said image processing includes finding the motion vector of the background of the image of the sample, and where said motion vector is used to reconstruct said image in order to compensate for the background motion.
63. The method of claim 24, wherein said image processing identifies and discards one or more poor images.
64. The method of claim 24, wherein the location and magnification of at least one of the said digital images are adjusted to clear ambiguities in the image.
65. The method of claim 24, wherein said image processing identifies at least one region within at least one of said digital images as a region not likely to contain a target.
66. Computer readable storage medium that includes software capable of performing said image processing method of claim 24.
67. Computer readable storage medium that includes software capable of activating said apparatus of claim 1.
PCT/IL2011/000973 2010-12-29 2011-12-29 An apparatus and method for automatic detection of pathogens WO2012090198A2 (en)

Priority Applications (10)

Application Number Priority Date Filing Date Title
IN5069DEN2012 IN2012DN05069A (en) 2010-12-29 2011-12-29
CN201710065911.6A CN106840812B (en) 2011-12-29 2012-12-27 Methods and systems for detecting pathogens in biological samples
US14/369,251 US10640807B2 (en) 2011-12-29 2012-12-27 Methods and systems for detecting a pathogen in a biological sample
BR112014016072-4A BR112014016072B1 (en) 2011-12-29 2012-12-27 method and system for detecting a plasmodium infection in a blood sample
EP12861524.2A EP2798350B1 (en) 2011-12-29 2012-12-27 Methods and systems for detecting a pathogen in a biological sample
CN201280070778.9A CN104169719B (en) 2011-12-29 2012-12-27 For detecting the method and system of pathogen in biological sample
PCT/IL2012/050556 WO2013098821A1 (en) 2011-12-29 2012-12-27 Methods and systems for detecting a pathogen in a biological sample
ZA2014/05506A ZA201405506B (en) 2011-12-29 2014-07-25 Methods and systems for detecting a pathogen in a biological sample
US16/705,941 US11584950B2 (en) 2011-12-29 2019-12-06 Methods and systems for detecting entities in a biological sample
US18/100,181 US20230159982A1 (en) 2011-12-29 2023-01-23 Methods and systems for detecting entities in a biological sample

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201061427809P 2010-12-29 2010-12-29
US61/427,809 2010-12-29

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14/369,251 Continuation US10640807B2 (en) 2011-12-29 2012-12-27 Methods and systems for detecting a pathogen in a biological sample

Publications (2)

Publication Number Publication Date
WO2012090198A2 true WO2012090198A2 (en) 2012-07-05
WO2012090198A3 WO2012090198A3 (en) 2012-11-15

Family

ID=46380428

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IL2011/000973 WO2012090198A2 (en) 2010-12-29 2011-12-29 An apparatus and method for automatic detection of pathogens

Country Status (3)

Country Link
US (4) US9522396B2 (en)
IN (1) IN2012DN05069A (en)
WO (1) WO2012090198A2 (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9329129B2 (en) 2013-07-01 2016-05-03 S.D. Sight Diagnostics Ltd. Method, kit and system for imaging a blood sample
WO2017046799A1 (en) 2015-09-17 2017-03-23 S.D. Sight Diagnostics Ltd Methods and apparatus for detecting an entity in a bodily sample
CN107077732A (en) * 2014-08-27 2017-08-18 思迪赛特诊断有限公司 System and method for calculating digital microscope focus variations
WO2017168411A1 (en) 2016-03-30 2017-10-05 S.D. Sight Diagnostics Ltd Image processing device for identifying blood parasites
US10176565B2 (en) 2013-05-23 2019-01-08 S.D. Sight Diagnostics Ltd. Method and system for imaging a cell sample
US10640807B2 (en) 2011-12-29 2020-05-05 S.D. Sight Diagnostics Ltd Methods and systems for detecting a pathogen in a biological sample
US10831013B2 (en) 2013-08-26 2020-11-10 S.D. Sight Diagnostics Ltd. Digital microscopy systems, methods and computer program products
US10843190B2 (en) 2010-12-29 2020-11-24 S.D. Sight Diagnostics Ltd. Apparatus and method for analyzing a bodily sample
US11099175B2 (en) 2016-05-11 2021-08-24 S.D. Sight Diagnostics Ltd. Performing optical measurements on a sample
US11307196B2 (en) 2016-05-11 2022-04-19 S.D. Sight Diagnostics Ltd. Sample carrier for optical measurements
WO2022096648A1 (en) * 2020-11-05 2022-05-12 Oxford NanoImaging Limited Fluorescence assay for identifying pathogens in a sample, and computer-implemented systems for carrying out such assays
US11609413B2 (en) 2017-11-14 2023-03-21 S.D. Sight Diagnostics Ltd. Sample carrier for microscopy and optical density measurements

Families Citing this family (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120077206A1 (en) 2003-07-12 2012-03-29 Accelr8 Technology Corporation Rapid Microbial Detection and Antimicrobial Susceptibility Testing
CA2532414C (en) 2003-07-12 2017-03-14 Accelr8 Technology Corporation Sensitive and rapid biodetection
US10254204B2 (en) 2011-03-07 2019-04-09 Accelerate Diagnostics, Inc. Membrane-assisted purification
EP2683831B1 (en) 2011-03-07 2015-09-23 Accelerate Diagnostics, Inc. Rapid cell purification systems
US9677109B2 (en) 2013-03-15 2017-06-13 Accelerate Diagnostics, Inc. Rapid determination of microbial growth and antimicrobial susceptibility
US9536304B2 (en) * 2013-08-30 2017-01-03 Dairy Quality Inc. Determining pathogens based on an image of somatic cells in a fluid sample
ES2552405B1 (en) * 2014-05-27 2016-09-14 Tecnología Marina Ximo, S.L. System and method of detection of Anisakis parasites in fish fillets
EP3176563B1 (en) * 2014-07-29 2021-06-30 National University Corporation Hamamatsu University School of Medicine Identification device and identification method
WO2016061754A1 (en) * 2014-10-22 2016-04-28 中国科学院自动化研究所 Handheld molecular imaging navigation system
US11478789B2 (en) * 2014-11-26 2022-10-25 Medica Corporation Automated microscopic cell analysis
US12005441B1 (en) 2014-11-26 2024-06-11 Medica Corporation Automated microscopic cell analysis
US10625259B1 (en) 2014-11-26 2020-04-21 Medica Corporation Automated microscopic cell analysis
US20170328924A1 (en) 2014-11-26 2017-11-16 Ronald Jones Automated microscopic cell analysis
US10253355B2 (en) 2015-03-30 2019-04-09 Accelerate Diagnostics, Inc. Instrument and system for rapid microorganism identification and antimicrobial agent susceptibility testing
EP3278115A2 (en) 2015-03-30 2018-02-07 Accelerate Diagnostics, Inc. Instrument and system for rapid microorganism identification and antimicrobial agent susceptibility testing
USD786707S1 (en) * 2016-01-19 2017-05-16 Stem Arts Projects, Llc Wavelength scanning apparatus
US11650197B2 (en) 2016-01-28 2023-05-16 Siemens Healthcare Diagnostics Inc. Methods and apparatus adapted to quantify a specimen from multiple lateral views
JP6888770B2 (en) * 2016-01-28 2021-06-16 シーメンス・ヘルスケア・ダイアグノスティックス・インコーポレーテッドＳｉｅｍｅｎｓ Ｈｅａｌｔｈｃａｒｅ Ｄｉａｇｎｏｓｔｉｃｓ Ｉｎｃ． Methods and equipment for classifying artifacts in a sample
US10816538B2 (en) * 2016-01-28 2020-10-27 Siemens Healthcare Diagnostics Inc. Methods and apparatus for detecting an interferent in a specimen
US20200018749A1 (en) * 2016-12-20 2020-01-16 Indevr, Inc. Plug-in expertise for pathogen identification using modular neural networks
CN110234749B (en) 2017-02-02 2023-06-30 PhAST公司 Analysis and use of motional kinematics of microorganisms
KR101791029B1 (en) * 2017-05-31 2017-10-27 주식회사 뷰노 Method for diagnosis of protozoal disease and apparatus using the same
CN110892247B (en) 2017-08-17 2023-08-25 雅培医护站股份有限公司 Apparatus, systems, and methods for performing optical and electrochemical assays
US11047845B1 (en) 2017-11-15 2021-06-29 Medica Corporation Control material and methods for cell analyzers
WO2020009908A1 (en) * 2018-07-02 2020-01-09 Ortho-Clinical Diagnostics, Inc. Method and apparatus for selecting slide media image read location
CN110569856B (en) * 2018-08-24 2020-07-21 阿里巴巴集团控股有限公司 Sample labeling method and device, and damage category identification method and device
WO2020212628A1 (en) * 2019-04-18 2020-10-22 Fundació Institut De Ciències Fotòniques Fluidic apparatus for optical interrogation of individual microorganisms
US11402331B2 (en) * 2019-05-08 2022-08-02 City University Of Hong Kong Imaging and manipulation of biological sample
WO2020242978A1 (en) * 2019-05-24 2020-12-03 The Board Of Trustees Of The Leland Stanford Junior University A spectral imaging platform for infectious disease diagnosis
US20220218242A1 (en) * 2019-05-29 2022-07-14 Ohio State Innovation Foundation Methods and apparatus for making a determination about a presence or an absence of a parasite in a blood sample
MX2022004703A (en) 2019-10-22 2022-05-11 S D Sight Diagnostics Ltd Accounting for errors in optical measurements.
BR112022011255A2 (en) 2019-12-12 2022-09-06 S D Sight Diagnostics Ltd MICROSCOPIC IMAGES WITHOUT FOCUS OF A SAMPLE
WO2021116960A1 (en) 2019-12-12 2021-06-17 S.D. Sight Diagnostics Ltd Classification models for analyzing a sample
CN114787625A (en) 2019-12-12 2022-07-22 思迪赛特诊断有限公司 Detecting platelets in a blood sample
CA3160695A1 (en) 2019-12-12 2021-06-17 S.D. Sight Diagnostics Ltd Analyzing an analyte disposed within a medium
AU2020400353A1 (en) 2019-12-12 2022-06-02 S.D. Sight Diagnostics Ltd Artificial generation of color blood smear image
WO2022009104A2 (en) 2020-07-07 2022-01-13 S.D. Sight Diagnostics Ltd Focusing a microscope using fluorescent images
US11914131B1 (en) * 2020-08-16 2024-02-27 Gregory Dimitrenko Optical testing system for detecting infectious disease, testing device, specimen collector and related methods
CN113537306A (en) * 2021-06-29 2021-10-22 复旦大学 Image classification method based on progressive growth element learning
US20230129946A1 (en) * 2021-10-25 2023-04-27 Principia Life, LLC Smart material sample analysis
WO2023144713A1 (en) 2022-01-25 2023-08-03 S.D. Sight Diagnostics Ltd Sample carrier for use with a bodily sample
GB202218615D0 (en) 2022-12-12 2023-01-25 S D Sight Diagnostics Ltd System and method for analyzing bodily samples

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020028471A1 (en) * 1998-02-20 2002-03-07 Oberhardt Bruce J. Cell analysis methods and apparatus
US20030231791A1 (en) * 2002-06-12 2003-12-18 Torre-Bueno Jose De La Automated system for combining bright field and fluorescent microscopy
US20040241677A1 (en) * 2003-05-29 2004-12-02 Lin Jeffrey S Techniques for automated diagnosis of cell-borne anomalies with digital optical microscope
US20060063185A1 (en) * 2004-09-09 2006-03-23 Edouard Vannier Methods for detection of pathogens in red blood cells
US20080059135A1 (en) * 2006-07-24 2008-03-06 Sangeeta Murugkar Pathogen Detection Using Coherent Anti-Stokes Raman Scattering Microscopy
US20080118399A1 (en) * 2004-12-13 2008-05-22 Roger Fleming Self-Contained Test Sensor
US20090128618A1 (en) * 2007-11-16 2009-05-21 Samsung Electronics Co., Ltd. System and method for object selection in a handheld image capture device
US20100068747A1 (en) * 2005-12-01 2010-03-18 Evotec Technologies Gmbh Generic Assay for Monitoring Endocytosis
US20100136570A1 (en) * 2003-07-12 2010-06-03 Goldberg David A Sensitive and rapid determination of antimicrobial susceptibility
US20100295998A1 (en) * 2009-05-21 2010-11-25 Canon Kabushiki Kaisha Image processing apparatus and method of controlling the apparatus and program thereof
US20100300563A1 (en) * 2009-05-27 2010-12-02 John Ramunas Modular device and method for moving fluids to and from a sample delivery element

Family Cites Families (334)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3603156A (en) 1970-02-04 1971-09-07 Gradko Glass Lab Inc Disposable dilution system
US3676076A (en) 1970-09-24 1972-07-11 Gradko Glass Lab Inc Disposable container
GB1324323A (en) 1971-02-05 1973-07-25 Image Analysing Computers Ltd Automatic focusing of an optical image
US3967056A (en) 1973-02-26 1976-06-29 Minolta Camera Kabushiki Kaisha Automatic focusing apparatus
US3916205A (en) 1973-05-31 1975-10-28 Block Engineering Differential counting of leukocytes and other cells
US4076419A (en) 1976-07-12 1978-02-28 Kleker Richard G Method and apparatus for hematology
US4209548A (en) 1976-11-01 1980-06-24 Rush-Presbyterian-St. Luke's Medical Center Method for the preparation of blood samples for automated analysis
DE2910875C2 (en) 1979-03-20 1985-11-14 Kernforschungszentrum Karlsruhe Gmbh, 7500 Karlsruhe Auto-focus procedure
ES8307122A1 (en) 1981-08-27 1983-06-16 Becton Dickinson Co Sample collection container.
US4454235A (en) 1982-06-01 1984-06-12 Miles Laboratories, Inc. Capillary tube holder for liquid transfer in immunoassay
US4494479A (en) 1982-10-14 1985-01-22 Coulter Electronics, Inc. Slide preparation apparatus
DE3486467T3 (en) 1983-01-10 2004-10-14 Gen-Probe Inc., San Diego Methods for the detection, identification and quantification of organisms and viruses
US4580895A (en) 1983-10-28 1986-04-08 Dynatech Laboratories, Incorporated Sample-scanning photometer
WO1985005446A1 (en) 1984-05-15 1985-12-05 Merck Patent Gmbh Single dye replacement for romanowsky plural dye variable compositions in human biopsy specimen constituent identifications
US4700298A (en) 1984-09-14 1987-10-13 Branko Palcic Dynamic microscope image processing scanner
JPS61198204A (en) 1985-02-28 1986-09-02 Disco Abrasive Sys Ltd Automatic focusing method for microscope
US5164598A (en) 1985-08-05 1992-11-17 Biotrack Capillary flow device
US4761381A (en) 1985-09-18 1988-08-02 Miles Inc. Volume metering capillary gap device for applying a liquid sample onto a reactive surface
DE3707487A1 (en) 1986-05-16 1987-11-26 Reichert Optische Werke Ag METHOD FOR AUTOFOCUSING MICROSCOPES AND MICROSCOPE WITH AN AUTOFOCUSING
JPH0774856B2 (en) 1986-10-16 1995-08-09 オリンパス光学工業株式会社 Automatic focus adjustment method
US4774192A (en) 1987-01-28 1988-09-27 Technimed Corporation A dry reagent delivery system with membrane having porosity gradient
US4849340A (en) 1987-04-03 1989-07-18 Cardiovascular Diagnostics, Inc. Reaction system element and method for performing prothrombin time assay
US6262798B1 (en) 1992-09-29 2001-07-17 Board Of Regents, The University Of Texas System Method and apparatus for direct spectrophotometric measurements in unaltered whole blood
US5001067A (en) 1989-09-18 1991-03-19 Nova Biomedical Corporation Determining the concentration of water soluble species in biological fluid
US5064282A (en) 1989-09-26 1991-11-12 Artel, Inc. Photometric apparatus and method for measuring hemoglobin
US5229265A (en) 1990-03-13 1993-07-20 Litron Laboratories Process for analyzing clastogenic agents
US5427959A (en) 1990-10-01 1995-06-27 Canon Kabushiki Kaisha Apparatus and method for measuring specimen
US5331958A (en) 1992-03-31 1994-07-26 University Of Manitoba Spectrophotometric blood analysis
US5430542A (en) 1992-04-10 1995-07-04 Avox Systems, Inc. Disposable optical cuvette
US5342790A (en) 1992-10-30 1994-08-30 Becton Dickinson And Company Apparatus for indirect fluorescent assay of blood samples
EP0613003B1 (en) 1993-02-22 2000-04-26 Sysmex Corporation A reagent for detecting malaria infected cells and a detecting method for malaria infected cells using the same
US5483055A (en) 1994-01-18 1996-01-09 Thompson; Timothy V. Method and apparatus for performing an automatic focus operation for a microscope
US6074789A (en) 1994-03-08 2000-06-13 Philips Electronics N.A. Corp. Method for producing phosphor screens, and color cathode ray tubes incorporating same
US5590660A (en) 1994-03-28 1997-01-07 Xillix Technologies Corp. Apparatus and method for imaging diseased tissue using integrated autofluorescence
US5782770A (en) 1994-05-12 1998-07-21 Science Applications International Corporation Hyperspectral imaging methods and apparatus for non-invasive diagnosis of tissue for cancer
JPH07325247A (en) 1994-05-31 1995-12-12 Nikon Corp Automatic focusing device
JPH10502466A (en) 1994-07-01 1998-03-03 ジェフレイ エイチ． プライス， Autofocus system for scanning microscopy
US5932872A (en) 1994-07-01 1999-08-03 Jeffrey H. Price Autofocus system for scanning microscopy having a volume image formation
WO1996012981A1 (en) 1994-10-21 1996-05-02 Kla Instruments Corporation Autofocusing apparatus and method for high resolution microscope system
WO1996013615A1 (en) 1994-10-27 1996-05-09 Entremed, Inc. Identification of infection with flow cytometry
DE69417900T2 (en) 1994-11-17 1999-11-11 Chemunex, Maisons-Alfort Device and method for fast and highly sensitive detection and counting of microorganisms using fluorescence
SE504193C2 (en) 1995-04-21 1996-12-02 Hemocue Ab Capillary microcuvette
US5985595A (en) 1995-06-07 1999-11-16 The University Of Connecticut Early detection of Borrelia infection
US6005964A (en) * 1996-01-24 1999-12-21 The Board Of Trustees Of The University Of Illinois Automatic machine vision microscope slide inspection system and method
KR0165522B1 (en) 1996-05-23 1999-03-20 김광호 Optimal point detector for non-invasive diagnosis of blood constituents and non-invasive diagnostic device using the same
JP2001526780A (en) 1997-05-05 2001-12-18 シェモメテック・アクティーゼルスカブ Method and system for measurement of particles in a liquid sample
US6074879A (en) 1997-06-23 2000-06-13 Bayer Corporation Synthetic polymer particles for use as standards and calibrators in flow cytometry
JPH1173903A (en) 1997-08-28 1999-03-16 Jeol Ltd Autofocusing method for scanning electron microscope
GB2329014A (en) 1997-09-05 1999-03-10 Colin Campbell Automated identification of tubercle bacilli
US6064474A (en) 1998-02-06 2000-05-16 Optical Sensors, Inc. Optical measurement of blood hematocrit incorporating a self-calibration algorithm
US6929953B1 (en) 1998-03-07 2005-08-16 Robert A. Levine Apparatus for analyzing biologic fluids
US5948686A (en) 1998-03-07 1999-09-07 Robert A. Leuine Method for performing blood cell counts
US6723290B1 (en) 1998-03-07 2004-04-20 Levine Robert A Container for holding biologic fluid for analysis
US6350613B1 (en) 1998-03-07 2002-02-26 Belton Dickinson & Co. Determination of white blood cell differential and reticulocyte counts
US6027695A (en) 1998-04-01 2000-02-22 Dupont Pharmaceuticals Company Apparatus for holding small volumes of liquids
KR20010083041A (en) 1998-06-02 2001-08-31 추후 Methods and apparatus for confocal interference microscopy using wavenumber domain reflectometry and background amplitude reduction and compensation
US6101104A (en) 1998-06-04 2000-08-08 Hughes Electronics Corporation Predictive threshold synchronous rectifier control
IT1304854B1 (en) 1998-07-29 2001-04-05 Paolo Fazii METHOD OF CHROMATIC DIFFERENTIATION OF FLUORESCENCE MICROORGANISMS
US6132685A (en) 1998-08-10 2000-10-17 Caliper Technologies Corporation High throughput microfluidic systems and methods
US6320979B1 (en) 1998-10-06 2001-11-20 Canon Kabushiki Kaisha Depth of field enhancement
US6340613B1 (en) 1998-11-12 2002-01-22 Micron Technology, Inc. Structural integrity enhancement of dielectric films
US6496260B1 (en) 1998-12-23 2002-12-17 Molecular Devices Corp. Vertical-beam photometer for determination of light absorption pathlength
JP2000199845A (en) 1999-01-05 2000-07-18 Ricoh Co Ltd Device and method for automatic focusing
US6344340B1 (en) 1999-03-01 2002-02-05 Novus International, Inc. Viability assay for sporocyst-forming protozoa
US6582964B1 (en) 1999-05-12 2003-06-24 Cme Telemetrix Inc. Method and apparatus for rapid measurement of HbA1c
JP3901427B2 (en) 1999-05-27 2007-04-04 松下電器産業株式会社 Electronic device, manufacturing method thereof, and manufacturing device thereof
WO2002019285A2 (en) 2000-05-23 2002-03-07 Munroe Chirnomas Method and apparatus for including article identification in an article handling device
US7034883B1 (en) 1999-08-10 2006-04-25 Cellavision Ab Automatic focusing
US6949384B2 (en) 2001-12-21 2005-09-27 Spectromedical Inc. Method for monitoring degradation of Hb-based blood substitutes
US6611777B2 (en) 1999-11-23 2003-08-26 James Samsoondar Method for calibrating spectrophotometric apparatus
US6711516B2 (en) 1999-11-23 2004-03-23 Spectromedical Inc. Method for calibrating spectrophotometric apparatus
ATE386815T1 (en) 2000-01-06 2008-03-15 Caliper Life Sciences Inc METHODS AND SYSTEMS FOR MONITORING INTRACELLULAR BINDING REACTIONS
JP2001199845A (en) 2000-01-24 2001-07-24 Kao Corp Hair cosmetic
US6836559B2 (en) 2000-03-09 2004-12-28 The Regents Of The University Of California Automated video-microscopic imaging and data acquisition system for colloid deposition measurements
WO2001078005A2 (en) 2000-04-11 2001-10-18 Cornell Research Foundation, Inc. System and method for three-dimensional image rendering and analysis
US7668362B2 (en) 2000-05-03 2010-02-23 Aperio Technologies, Inc. System and method for assessing virtual slide image quality
US6711283B1 (en) 2000-05-03 2004-03-23 Aperio Technologies, Inc. Fully automatic rapid microscope slide scanner
US6799119B1 (en) 2000-05-15 2004-09-28 Colorado School Of Mines Method for detection of biological related materials using biomarkers
EP1290428A1 (en) 2000-06-02 2003-03-12 Medicometrics APS Method and system for classifying a biological sample
US7630063B2 (en) 2000-08-02 2009-12-08 Honeywell International Inc. Miniaturized cytometer for detecting multiple species in a sample
US6554788B1 (en) 2000-06-02 2003-04-29 Cobe Cardiovascular, Inc. Hematocrit sampling system
US6632681B1 (en) 2000-07-24 2003-10-14 Ey Laboratories Reagent delivery device and method of use
US6819408B1 (en) * 2000-09-27 2004-11-16 Becton, Dickinson And Company Method for obtaining a monolayer of desired particles in a liquid sample
US6448024B1 (en) 2000-10-03 2002-09-10 Roche Diagnostics Corporation Method, reagent, cartridge, and device for determining fibrinogen
US20100261159A1 (en) 2000-10-10 2010-10-14 Robert Hess Apparatus for assay, synthesis and storage, and methods of manufacture, use, and manipulation thereof
DE10051806A1 (en) 2000-10-18 2002-04-25 Bayer Ag Characterization of microbial mixtures, useful e.g. for quality control, comprises comparing spectra and chromatograms with reference data
US7027628B1 (en) 2000-11-14 2006-04-11 The United States Of America As Represented By The Department Of Health And Human Services Automated microscopic image acquisition, compositing, and display
US7155049B2 (en) 2001-01-11 2006-12-26 Trestle Acquisition Corp. System for creating microscopic digital montage images
EP1349493A2 (en) 2001-01-12 2003-10-08 The General Hospital Corporation System and method for enabling simultaneous calibration and imaging of a medium
JP4937457B2 (en) 2001-03-01 2012-05-23 オリンパス株式会社 Microscope control apparatus, microscope control system, microscope control method, program, and recording medium
US6898451B2 (en) 2001-03-21 2005-05-24 Minformed, L.L.C. Non-invasive blood analyte measuring system and method utilizing optical absorption
US6519355B2 (en) 2001-03-28 2003-02-11 Alan C. Nelson Optical projection imaging system and method for automatically detecting cells having nuclear and cytoplasmic densitometric features associated with disease
WO2002082805A1 (en) 2001-03-30 2002-10-17 National Institute Of Advanced Industrial Science And Technology Real-time omnifocus microscope camera
US6884983B2 (en) 2002-06-10 2005-04-26 Palantyr Research, Llc Imaging system for examining biological material
US7385168B2 (en) 2001-07-06 2008-06-10 Palantyr Research, Llc Imaging system, methodology, and applications employing reciprocal space optical design
US7863552B2 (en) 2001-07-06 2011-01-04 Palantyr Research Llc Digital images and related methodologies
US7338168B2 (en) 2001-07-06 2008-03-04 Palantyr Research, Llc Particle analyzing system and methodology
US6872930B2 (en) 2003-03-31 2005-03-29 Palantyr Research, Llc Imaging system and methodology employing reciprocal space optical design
US7248716B2 (en) 2001-07-06 2007-07-24 Palantyr Research, Llc Imaging system, methodology, and applications employing reciprocal space optical design
US7151246B2 (en) 2001-07-06 2006-12-19 Palantyr Research, Llc Imaging system and methodology
US7105795B2 (en) 2001-07-06 2006-09-12 Palantyr Research, Llc Imaging system, methodology, and applications employing reciprocal space optical design
US7288751B2 (en) 2001-07-06 2007-10-30 Palantyr Research, Llc Imaging system, methodology, and applications employing reciprocal space optical design
US7439478B2 (en) 2001-07-06 2008-10-21 Palantyr Research, Llc Imaging system, methodology, and applications employing reciprocal space optical design having at least one pixel being scaled to about a size of a diffraction-limited spot defined by a microscopic optical system
US6664528B1 (en) 2001-07-06 2003-12-16 Palantyr Research, Llc Imaging system and methodology employing reciprocal space optical design
US7132636B1 (en) 2001-07-06 2006-11-07 Palantyr Research, Llc Imaging system and methodology employing reciprocal space optical design
JP4751535B2 (en) 2001-07-26 2011-08-17 シスメックス株式会社 Fractionation method and blood analyzer using the same
EP1428018B1 (en) 2001-09-06 2010-06-09 Straus Holdings Inc. Rapid and sensitive detection of molecules
US6989891B2 (en) 2001-11-08 2006-01-24 Optiscan Biomedical Corporation Device and method for in vitro determination of analyte concentrations within body fluids
SE0104443D0 (en) 2001-12-28 2001-12-28 Hemocue Ab Analysis method and cuvette for that
US7713474B2 (en) 2002-01-15 2010-05-11 Siemens Healthcare Diagnostics Inc. Liquid permeable composition in dry reagent devices
US7133547B2 (en) 2002-01-24 2006-11-07 Tripath Imaging, Inc. Method for quantitative video-microscopy and associated system and computer software program product
US7764821B2 (en) 2002-02-14 2010-07-27 Veridex, Llc Methods and algorithms for cell enumeration in a low-cost cytometer
EP1428169B1 (en) 2002-02-22 2017-01-18 Olympus America Inc. Focusable virtual microscopy apparatus and method
US20030161514A1 (en) 2002-02-28 2003-08-28 Curry Bo U. Bi-directional scanner control system
DE10246777A1 (en) 2002-03-21 2003-10-02 Endress & Hauser Wetzer Gmbh Device for identifying sample container and/or for preparing information connected with sample container comprises electronic label assigned to container
DE10217404A1 (en) 2002-04-18 2003-11-06 Leica Microsystems Autofocus method for a microscope and system for adjusting the focus for a microscope
US6658143B2 (en) 2002-04-29 2003-12-02 Amersham Biosciences Corp. Ray-based image analysis for biological specimens
AU2003221584A1 (en) * 2002-05-01 2003-11-17 Chromos Molecular Systems, Inc. Methods for delivering nucleic acid molecules into cells and assessment thereof
JP2004061942A (en) 2002-07-30 2004-02-26 Nikon Corp Microscope system
US7177767B2 (en) 2002-10-18 2007-02-13 Abaxis, Inc. Systems and methods for the detection of short and long samples
JP3904505B2 (en) 2002-10-22 2007-04-11 独立行政法人科学技術振興機構 Malaria infection diagnostic agent and Plasmodium dye
DE10254685A1 (en) 2002-11-22 2004-06-03 Roche Diagnostics Gmbh Measuring device for the optical examination of a test element
US7490085B2 (en) 2002-12-18 2009-02-10 Ge Medical Systems Global Technology Company, Llc Computer-assisted data processing system and method incorporating automated learning
US20040128077A1 (en) * 2002-12-27 2004-07-01 Automated Cell, Inc. Method and apparatus for following cells
US20040132171A1 (en) 2003-01-06 2004-07-08 Peter Rule Wearable device for measuring analyte concentration
US20040253742A1 (en) 2003-01-31 2004-12-16 Affleck Rhett L. Automated imaging system and method
JP3869810B2 (en) 2003-02-24 2007-01-17 株式会社堀場製作所 Micro blood cell counter
US6955872B2 (en) 2003-03-20 2005-10-18 Coulter International Corp. Dye compositions which provide enhanced differential fluorescence and light scatter characteristics
CN1795272B (en) * 2003-03-27 2013-04-24 巴特朗医疗成像有限责任公司 System and method for rapidly identifying pathogens, bacteria and abnormal cells
EP1616286A1 (en) 2003-04-02 2006-01-18 Amersham Biosciences UK Limited Method of, and computer software for, classification of cells into subpopulations
US7329537B2 (en) 2003-04-17 2008-02-12 Nexcelom Bioscience, Llc Micro-pattern embedded plastic optical film device for cell-based assays
US7706862B2 (en) 2003-04-17 2010-04-27 Research Foundation Of The City University Of New York Detecting human cancer through spectral optical imaging using key water absorption wavelengths
US7324694B2 (en) 2003-05-23 2008-01-29 International Remote Imaging Systems, Inc. Fluid sample analysis using class weights
ES2920892T3 (en) 2003-06-12 2022-08-11 Accupath Diagnostic Laboratories Inc Method for forming cell arrays
WO2005017184A2 (en) 2003-06-26 2005-02-24 Litron Laboratories, Ltd. Method for the enumeration of micronucleated erythrocyte populations while distinguishing platelets and/or platelet-associated aggregates
KR100573621B1 (en) 2003-07-18 2006-04-25 주식회사 디지탈바이오테크놀러지 Device for counting cells and method for manufacturing the same
EP1651947B1 (en) 2003-07-19 2015-11-04 NanoEnTek, Inc. Device for counting micro particles
SE0302114D0 (en) 2003-07-21 2003-07-21 Cellavision Ab Ways to distinguish an object outline
US20050089208A1 (en) 2003-07-22 2005-04-28 Rui-Tao Dong System and method for generating digital images of a microscope slide
WO2005017025A2 (en) 2003-08-15 2005-02-24 The President And Fellows Of Harvard College Study of polymer molecules and conformations with a nanopore
US7998435B2 (en) 2003-09-19 2011-08-16 Life Technologies Corporation High density plate filler
US20060233671A1 (en) 2003-09-19 2006-10-19 Beard Nigel P High density plate filler
JP4521490B2 (en) 2003-11-21 2010-08-11 国立大学法人高知大学 Similar pattern search device, similar pattern search method, similar pattern search program, and fraction separation device
US7030351B2 (en) 2003-11-24 2006-04-18 Mitutoyo Corporation Systems and methods for rapidly automatically focusing a machine vision inspection system
EP1718973B1 (en) 2004-02-09 2009-09-09 Rapid Pathogen Screening Inc. Method for the rapid diagnosis of targets in human body fluids
US9176121B2 (en) 2004-02-13 2015-11-03 Roche Diagnostics Hematology, Inc. Identification of blood elements using inverted microscopy
JP4417143B2 (en) 2004-03-11 2010-02-17 シスメックス株式会社 SAMPLE ANALYZER, PROGRAM, AND RECORDING MEDIUM CONTAINING THE PROGRAM
JP2007529015A (en) 2004-03-12 2007-10-18 バイオトローブ， インコーポレイテッド Nanoliter array loading
US7925070B2 (en) 2004-03-30 2011-04-12 Sysmex Corporation Method for displaying virtual slide and terminal device for displaying virtual slide
ES2643836T3 (en) 2004-04-07 2017-11-24 Abbott Laboratories Disposable chamber to analyze biological fluids
WO2005121863A1 (en) 2004-06-11 2005-12-22 Nicholas Etienne Ross Automated diagnosis of malaria and other infections
DE602005023305D1 (en) 2004-06-17 2010-10-14 Koninkl Philips Electronics Nv AUTOFOCUS MECHANISM FOR A SPECTROSCOPIC SYSTEM
GB0414201D0 (en) 2004-06-24 2004-07-28 Fujifilm Electronic Imaging Method and apparatus for forming a multiple focus stack image
US8582924B2 (en) 2004-06-30 2013-11-12 Carl Zeiss Microimaging Gmbh Data structure of an image storage and retrieval system
US7456377B2 (en) 2004-08-31 2008-11-25 Carl Zeiss Microimaging Ais, Inc. System and method for creating magnified images of a microscope slide
US20060095241A1 (en) 2004-10-29 2006-05-04 Microsoft Corporation Systems and methods that utilize machine learning algorithms to facilitate assembly of aids vaccine cocktails
WO2006040387A1 (en) 2004-10-11 2006-04-20 Thermo Fisher Scientific Oy Method for automatically detecting factors that disturb analysis by a photometer
US8045782B2 (en) 2004-12-07 2011-10-25 Ge Healthcare Niagara, Inc. Method of, and apparatus and computer software for, implementing image analysis protocols
WO2006065898A1 (en) 2004-12-13 2006-06-22 Bayer Healthcare Llc Transmission spectroscopy system for use in the determination of analytes in body fluid
JP2008523407A (en) 2004-12-14 2008-07-03 ユニバーシティ・オブ・ジ・ウィトウォーターズランド・ヨハネスブルク Methods for diagnosing and monitoring disease cell reservoirs
US20070103678A1 (en) 2005-02-14 2007-05-10 Sterling Bernhard B Analyte detection system with interferent identification and correction
US20060223052A1 (en) 2005-03-30 2006-10-05 Kimberly-Clark Worldwide, Inc. Technique for detecting microorganisms
PL3026874T3 (en) 2005-04-01 2020-05-18 Polymer Technology Systems, Inc. Body fluid testing component for analyte detection
US7580120B2 (en) 2005-04-07 2009-08-25 Sysmex Corporation Blood analyzer, sample analyzer, and flow cytometer
JP4667944B2 (en) 2005-04-20 2011-04-13 シスメックス株式会社 Image creation device
JP2006301270A (en) 2005-04-20 2006-11-02 Hitachi Kokusai Electric Inc Device and method for automatic focusing
FR2884920B1 (en) 2005-04-21 2007-08-10 Horiba Abx Sa Sa DEVICE AND METHOD FOR MULTIPARAMETRIC ANALYSIS OF MICROSCOPIC ELEMENTS
EP1888778B1 (en) 2005-05-06 2012-11-14 Samsung Electronics Co., Ltd. Digital bio disc(dbd), dbd driver apparatus, and assay method using the same
AT501944B1 (en) 2005-06-15 2007-06-15 Tissuegnostics Gmbh PROCESS FOR SEGMENTING LEUKOCYTES
US7417213B2 (en) 2005-06-22 2008-08-26 Tripath Imaging, Inc. Apparatus and method for rapid microscopic image focusing having a movable objective
US7518710B2 (en) 2005-07-14 2009-04-14 Battelle Memorial Institute Optical devices for biological and chemical detection
US20070031056A1 (en) 2005-08-02 2007-02-08 Perz Cynthia B System for and method of focusing in automated microscope systems
JP2007040814A (en) 2005-08-03 2007-02-15 Matsushita Electric Ind Co Ltd Absorbance measuring sensor and method
US7776553B2 (en) 2005-09-16 2010-08-17 Presidents And Fellows Of Harvard College Screening assays and methods
US7609369B2 (en) 2005-09-24 2009-10-27 Beckman Coulter, Inc. Methods of detection of iron deficiency and hemochromatosis
US7796797B2 (en) 2005-09-28 2010-09-14 Sysmex Corporation Apparatus for obtaining an image of a blood cell and method for obtaining an image of a blood cell
US7599893B2 (en) 2005-10-13 2009-10-06 Aureon Laboratories, Inc. Methods and systems for feature selection in machine learning based on feature contribution and model fitness
GB2431537B (en) 2005-10-20 2011-05-04 Amersham Biosciences Uk Ltd Method of processing an image
US7344890B2 (en) 2005-11-09 2008-03-18 Beckman Coulter, Inc. Method for discriminating platelets from red blood cells
US7933435B2 (en) 2005-11-21 2011-04-26 Vala Sciences, Inc. System, method, and kit for processing a magnified image of biological material to identify components of a biological object
SE529536C2 (en) 2006-01-25 2007-09-04 Hemocue Ab Method for ensuring the quality of a sample container
GB2435925A (en) * 2006-03-09 2007-09-12 Cytokinetics Inc Cellular predictive models for toxicities
SE530244C2 (en) 2006-05-05 2008-04-08 Hemocue Ab Method and system for quantitative hemoglobin determination
JP5040191B2 (en) 2006-06-29 2012-10-03 富士通株式会社 Microinjection apparatus and automatic focus adjustment method
AT503862B1 (en) 2006-07-05 2010-11-15 Arc Austrian Res Centers Gmbh PATHOGENIC IDENTIFICATION DUE TO A 16S OR 18S RRNA MICROARRAY
DE102006031177A1 (en) 2006-07-06 2008-01-10 Carl Zeiss Microimaging Gmbh Method and device for producing an image of a thin layer of an object
SE530750C2 (en) 2006-07-19 2008-09-02 Hemocue Ab A measuring device, a method and a computer program
US8067245B2 (en) 2006-07-24 2011-11-29 Medica Corporation Automated microscope for blood cell analysis
US8428331B2 (en) 2006-08-07 2013-04-23 Northeastern University Phase subtraction cell counting method
WO2008063135A1 (en) 2006-11-24 2008-05-29 Agency For Science, Technology And Research Apparatus for processing a sample in a liquid droplet and method of using the same
KR100844350B1 (en) 2007-01-09 2008-07-07 주식회사 디지탈바이오테크놀러지 A chip having microchannel for counting specific micro particles among floating micro particle mixture by optical means and a method for counting micro particles using the same
WO2008085048A1 (en) 2007-01-11 2008-07-17 Intellectual Property Mvm B.V. The measurement of functional microcirculatory geometry and velocity distributions using automated image analysis
US7738094B2 (en) 2007-01-26 2010-06-15 Becton, Dickinson And Company Method, system, and compositions for cell counting and analysis
US8877458B2 (en) 2007-02-02 2014-11-04 Canadian Blood Services Method of detecting bacterial contamination using dynamic light scattering
US8131035B2 (en) 2007-02-05 2012-03-06 Siemens Healthcare Diagnostics Inc. Cell analysis using isoperimetric graph partitioning
JP5105945B2 (en) * 2007-04-19 2012-12-26 キヤノン株式会社 Pan head device and control method thereof
DE102007021387A1 (en) 2007-05-04 2008-11-06 Eads Deutschland Gmbh Detection device for the detection of biological microparticles such as bacteria, viruses, spores, pollen or biological toxins, and detection methods
US20080305514A1 (en) 2007-06-06 2008-12-11 Alcon Research, Ltd. Method for detecting microbes
KR100900511B1 (en) 2007-07-23 2009-06-03 주식회사 디지탈바이오테크놀러지 Chip for analyzing fluids
EP2171420A1 (en) 2007-07-31 2010-04-07 Micronics, Inc. Sanitary swab collection system, microfluidic assay device, and methods for diagnostic assays
US7936913B2 (en) 2007-08-07 2011-05-03 Nextslide Imaging Llc Network image review in clinical hematology
US7884254B2 (en) 2007-08-08 2011-02-08 Honeywell International Inc. Dehydrochlorination of hydrochlorofluorocarbons using pre-treated activated carbon catalysts
US8878923B2 (en) 2007-08-23 2014-11-04 General Electric Company System and method for enhanced predictive autofocusing
CN101387599B (en) 2007-09-13 2011-01-26 深圳迈瑞生物医疗电子股份有限公司 Method for distinguishing particle community and particle analyzer
US20100256323A1 (en) 2007-09-21 2010-10-07 Dow Global Technologies Inc. Prepolymers and polymers for elastomers
WO2009041918A1 (en) 2007-09-26 2009-04-02 Agency For Science, Technology And Research A method and system for generating an entirely well-focused image of a large three-dimensional scene
JP2009109198A (en) 2007-10-26 2009-05-21 Arkray Inc Analyzer
KR101009447B1 (en) 2007-11-12 2011-01-19 바디텍메드 주식회사 Device for sampling and preprocessing biological fluids and method thereof
CN101952762B (en) * 2008-01-02 2012-11-28 加利福尼亚大学董事会 High numerical aperture telemicroscopy apparatus
US20090185734A1 (en) 2008-01-18 2009-07-23 Hemocue Ab Apparatus and method for analysis of particles in a liquid sample
JP4558047B2 (en) 2008-01-23 2010-10-06 オリンパス株式会社 Microscope system, image generation method, and program
CN101971208A (en) * 2008-03-12 2011-02-09 皇家飞利浦电子股份有限公司 Correction of spot area in measuring brightness of sample in biosensing device
WO2009117682A1 (en) 2008-03-21 2009-09-24 Abbott Point Of Care, Inc. Method and apparatus for detecting and counting platelets individually and in aggregate clumps
JP2011516833A (en) 2008-03-21 2011-05-26 アボット・ポイント・オブ・ケア Method and apparatus for analyzing individual cells or particulate matter using fluorescence quenching and / or fluorescence fading
WO2009117652A1 (en) 2008-03-21 2009-09-24 Abbott Point Of Care, Inc. Method and apparatus for determining the hematocrit of a blood sample utilizing the intrinsic pigmentation of hemoglobin contained within the red blood cells
ES2398488T3 (en) 2008-03-21 2013-03-19 Abbott Point Of Care, Inc. Method and apparatus for determining red blood cell indices in a blood sample using intrinsic pigmentation of hemoglobin contained in red blood cells
CN102016595B (en) 2008-03-27 2014-08-06 哈佛学院院长等 Three-dimensional microfluidic devices
US8883491B2 (en) 2008-04-09 2014-11-11 Nexcelom Bioscience Llc Systems and methods for counting cells and biomolecules
US9017610B2 (en) 2008-04-25 2015-04-28 Roche Diagnostics Hematology, Inc. Method of determining a complete blood count and a white blood cell differential count
US8379944B2 (en) 2008-04-29 2013-02-19 Siemens Healthcare Diagnostics Inc. Identification, classification and counting of targets of interest in multispectral image data
WO2009157385A1 (en) 2008-06-27 2009-12-30 古河電気工業株式会社 Method for distinguishing and sorting cells and device therefor
DE102008030874A1 (en) 2008-06-30 2010-01-07 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Method and device for determining a contour and a center point of an object
EP2145684A3 (en) 2008-07-14 2013-06-26 Samsung Electronics Co., Ltd. Microfluidic device, sample analyzing method using the same, and dilution ration measuring method
US8385971B2 (en) 2008-08-19 2013-02-26 Digimarc Corporation Methods and systems for content processing
WO2010025302A2 (en) 2008-08-27 2010-03-04 Life Technologies Corporation Apparatus for and method of processing biological samples
US9240043B2 (en) * 2008-09-16 2016-01-19 Novartis Ag Reproducible quantification of biomarker expression
US8280134B2 (en) 2008-09-22 2012-10-02 Cambridge Research & Instrumentation, Inc. Multi-spectral imaging including at least one common stain
JP5380973B2 (en) 2008-09-25 2014-01-08 株式会社ニコン Image processing apparatus and image processing program
WO2010044870A1 (en) 2008-10-14 2010-04-22 The Burnham Institute For Medical Research Automated scanning cytometry using chromatic aberration for multiplanar image acquisition
US8842900B2 (en) 2008-10-28 2014-09-23 Sysmex Corporation Specimen processing system and blood cell image classifying apparatus
EP2356465B1 (en) 2008-11-13 2014-10-01 Beckman Coulter, Inc. Method of correction of particle interference to hemoglobin measurement
CN101403650B (en) 2008-11-21 2010-06-23 北京理工大学 Differential confocal combination ultra-long focal length measuring method and apparatus
CN102227747B (en) 2008-11-27 2014-06-04 皇家飞利浦电子股份有限公司 Generation of multicolour image of unstained biological specimen
US20100157086A1 (en) 2008-12-15 2010-06-24 Illumina, Inc Dynamic autofocus method and system for assay imager
GB0900526D0 (en) 2009-01-14 2009-02-11 Perkinelmer Ltd Fluorescence microscopy methods and apparatus
JP5426181B2 (en) 2009-01-21 2014-02-26 シスメックス株式会社 Specimen processing system, cell image classification apparatus, and specimen processing method
EP2216095A1 (en) 2009-01-27 2010-08-11 Koninklijke Philips Electronics N.V. Microfluidic device for full blood count
US9778188B2 (en) 2009-03-11 2017-10-03 Industrial Technology Research Institute Apparatus and method for detection and discrimination molecular object
KR101714766B1 (en) 2009-04-09 2017-03-09 코닌클리케 필립스 엔.브이. Preparation of thin layers of a fluid containing cells for analysis
ES2903147T3 (en) 2009-04-27 2022-03-31 Roche Diagnostics Hematology Inc Systems and procedures for analyzing body fluids
US8891851B2 (en) 2009-07-15 2014-11-18 Glenn F. Spaulding Home healthcare management system and hardware
US8481303B2 (en) 2009-10-12 2013-07-09 Corning Incorporated Microfluidic device for cell culture
US8320655B2 (en) 2009-10-16 2012-11-27 General Electric Company Process and system for analyzing the expression of biomarkers in cells
CA2842723C (en) 2009-10-19 2016-02-16 Ventana Medical Systems, Inc. Imaging system and techniques
JP5394887B2 (en) 2009-10-29 2014-01-22 オリンパス株式会社 Microscope device and microscope observation method
US20120058504A1 (en) 2009-10-30 2012-03-08 Simon Fraser University Methods and apparatus for dielectrophoretic shuttling and measurement of single cells or other particles in microfluidic chips
CN102053051A (en) 2009-10-30 2011-05-11 西门子公司 Body fluid analysis system as well as image processing device and method for body fluid analysis
US9072772B2 (en) * 2009-11-05 2015-07-07 University of Pittsburgh—of the Commonwealth System of Higher Education Methods of treating disorders associated with protein aggregation
US9119573B2 (en) 2009-12-10 2015-09-01 Siemens Aktiengesellschaft Stent marker detection using a learning based classifier in medical imaging
US8748186B2 (en) 2009-12-22 2014-06-10 Abbott Laboratories Method for performing a blood count and determining the morphology of a blood smear
WO2011076413A1 (en) 2009-12-22 2011-06-30 Universität Heidelberg Means and methods for detecting plasmodia and for screening or diagnosing drug resistance or altered drug responsiveness of plasmodia
US8237786B2 (en) 2009-12-23 2012-08-07 Applied Precision, Inc. System and method for dense-stochastic-sampling imaging
ES2438841T3 (en) 2009-12-31 2014-01-20 Abbott Point Of Care, Inc. Method and apparatus for determining the average cell volume of red blood cells in the blood
US8906308B2 (en) 2010-01-15 2014-12-09 Abbott Laboratories Method for determining volume and hemoglobin content of individual red blood cells
CN102822657B (en) 2010-01-20 2016-01-20 耐克思乐生物科学有限责任公司 Cell count and sample chamber and assembly method thereof
WO2011094577A2 (en) 2010-01-29 2011-08-04 Micronics, Inc. Sample-to-answer microfluidic cartridge
JP5490568B2 (en) 2010-02-26 2014-05-14 オリンパス株式会社 Microscope system, specimen observation method and program
EP2550522B1 (en) * 2010-03-23 2016-11-02 California Institute of Technology Super resolution optofluidic microscopes for 2d and 3d imaging
SG174650A1 (en) 2010-03-31 2011-10-28 Agency Science Tech & Res A method of monitoring parasite development in blood
US8396269B2 (en) 2010-04-08 2013-03-12 Digital Pathco LLC Image quality assessment including comparison of overlapped margins
US8040517B1 (en) 2010-04-30 2011-10-18 General Electric Company Arc flash detection system and method
WO2011143075A2 (en) 2010-05-08 2011-11-17 Veridex, Llc A simple and affordable method for immuophenotyping using a microfluidic chip sample preparation with image cytometry
WO2012000102A1 (en) 2010-06-30 2012-01-05 The Governors Of The University Of Alberta Apparatus and method for microscope-based label-free microflutdic cytometry
US8813294B2 (en) 2010-07-07 2014-08-26 Clean & Go, Llc Grout and tile cleaning implement with replaceable member
WO2012006565A2 (en) 2010-07-08 2012-01-12 Life Technologies Corporation Systems and methods for assigning attributes to a plurality of samples
US20150032671A9 (en) 2010-07-23 2015-01-29 General Electric Company Systems and methods for selecting and analyzing particles in a biological tissue
US10139613B2 (en) 2010-08-20 2018-11-27 Sakura Finetek U.S.A., Inc. Digital microscope and method of sensing an image of a tissue sample
US8933927B2 (en) 2010-09-02 2015-01-13 Samsung Electronics Co., Ltd. Display system with image conversion mechanism and method of operation thereof
US8351676B2 (en) 2010-10-12 2013-01-08 Sony Corporation Digital image analysis using multi-step analysis
US8542274B2 (en) 2010-10-18 2013-09-24 Olympus America Inc. Wide field microscopic imaging system and method
USD655421S1 (en) 2010-11-03 2012-03-06 Life Technologies Corporation Cell counter
US9050595B2 (en) 2010-12-03 2015-06-09 Abbott Point Of Care Inc. Assay devices with integrated sample dilution and dilution verification and methods of using same
US9522396B2 (en) 2010-12-29 2016-12-20 S.D. Sight Diagnostics Ltd. Apparatus and method for automatic detection of pathogens
JP5331828B2 (en) 2011-01-14 2013-10-30 株式会社日立ハイテクノロジーズ Charged particle beam equipment
EP2686828A1 (en) 2011-03-14 2014-01-22 The University Of Warwick Histology analysis
EP2694932B1 (en) 2011-04-07 2018-02-21 The UWM Research Foundation, Inc High speed microscope with spectral resolution
US9064301B2 (en) 2011-04-14 2015-06-23 Abbott Point Of Care, Inc. Method and apparatus for compressing imaging data of whole blood sample analyses
CN111610138B (en) 2011-04-15 2023-06-09 罗氏血液诊断股份有限公司 Measurement of cell volume and composition
TWI493505B (en) 2011-06-20 2015-07-21 Mstar Semiconductor Inc Image processing method and image processing apparatus thereof
US10426356B2 (en) 2011-07-09 2019-10-01 Gauss Surgical, Inc. Method for estimating a quantity of a blood component in a fluid receiver and corresponding error
US8792693B2 (en) 2011-07-09 2014-07-29 Gauss Surgical System and method for estimating extracorporeal blood volume in a physical sample
EP2734955A1 (en) 2011-07-19 2014-05-28 Ovizio Imaging Systems NV/SA A method and system for detecting and/or classifying cancerous cells in a cell sample
US8964171B2 (en) 2011-07-22 2015-02-24 Roche Diagnostics Hematology, Inc. Identifying and measuring reticulocytes
JP5959814B2 (en) 2011-08-08 2016-08-02 ソニー株式会社 Blood analyzer and blood analysis method
EP2758765B1 (en) 2011-09-22 2020-08-12 FOCE Technology International B.V. Optical platelet counter method
US9046473B2 (en) 2011-09-28 2015-06-02 Abbott Point Of Care, Inc. Method and apparatus for detecting the presence of intraerythrocytic parasites
WO2013056379A1 (en) 2011-10-19 2013-04-25 Biovotion Ag System for noninvasive optical measurements of physiological properties in tissue
TWI431264B (en) 2011-10-20 2014-03-21 Lite On It Corp Optical detection apparatus and optical measurement system
US8885912B2 (en) 2011-11-03 2014-11-11 General Electric Company Generate percentage of positive cells for biomarkers by normalizing and autothresholding the image intensity produced by immunohistochemistry technique
WO2013098821A1 (en) 2011-12-29 2013-07-04 Parasight Ltd. Methods and systems for detecting a pathogen in a biological sample
ES2557125T3 (en) 2011-12-30 2016-01-22 Abbott Point Of Care, Inc. Method and apparatus for the automated identification of platelets in a whole blood sample from microscope images
US9322767B2 (en) 2012-04-17 2016-04-26 i-calQ, LLC Device for performing a blood, cell, and/or pathogen count and methods for use thereof
US20150283531A1 (en) 2012-04-18 2015-10-08 Biofire Diagnostics, Llc Microspotting Device
US20150072880A1 (en) 2012-05-09 2015-03-12 David A. Calderwood Rapid detection of analytes in liquid samples
US8873827B2 (en) 2012-06-29 2014-10-28 General Electric Company Determination of spatial proximity between features of interest in biological tissue
US8744165B2 (en) 2012-07-19 2014-06-03 Sony Corporation Method and apparatus for stain separation in digital pathology images
CN103580818B (en) 2012-07-31 2018-08-03 中兴通讯股份有限公司 A kind of feedback method of channel state information, base station and terminal
JP5333635B1 (en) 2012-08-23 2013-11-06 富士ゼロックス株式会社 Image processing apparatus, program, and image processing system
JP5464244B2 (en) 2012-08-24 2014-04-09 富士ゼロックス株式会社 Image processing apparatus, program, and image processing system
EP2731051A1 (en) 2012-11-07 2014-05-14 bioMérieux Bio-imaging method
US9400414B2 (en) 2012-11-19 2016-07-26 Raytheon Company Methods and apparatus for imaging without retro-reflection using a tilted image plane and structured relay optic
NZ708612A (en) 2012-11-28 2016-04-29 Japan Science & Tech Agency Cell monitoring device, cell monitoring method and program thereof
US20140170678A1 (en) 2012-12-17 2014-06-19 Leukodx Ltd. Kits, compositions and methods for detecting a biological condition
US9976963B2 (en) 2012-12-21 2018-05-22 Integrated Plasmonics Corporation Microcuvette cartridge
CA2903809A1 (en) 2013-03-13 2014-10-02 Tahoe Institute for Rural Health Research, LLC Portable blood count monitor
WO2014159620A1 (en) 2013-03-14 2014-10-02 Samuels Mark A Encoded calibration device and systems and methods thereof
EP2999988A4 (en) 2013-05-23 2017-01-11 S.D. Sight Diagnostics Ltd. Method and system for imaging a cell sample
IL227276A0 (en) 2013-07-01 2014-03-06 Parasight Ltd A method and system for preparing a monolayer of cells, particularly suitable for diagnosis
WO2015029032A1 (en) 2013-08-26 2015-03-05 Parasight Ltd. Digital microscopy systems, methods and computer program products
JP6194791B2 (en) 2013-12-27 2017-09-13 富士ゼロックス株式会社 Image processing apparatus and program
WO2016030897A1 (en) 2014-08-27 2016-03-03 S.D. Sight Diagnostics Ltd System and method for calculating focus variation for a digital microscope
JP6352750B2 (en) 2014-09-26 2018-07-04 シスメックス株式会社 Blood analyzer and blood analysis method
US10724069B2 (en) 2014-09-29 2020-07-28 Chipcare Corporation Methods and devices for cell detection
US11478789B2 (en) 2014-11-26 2022-10-25 Medica Corporation Automated microscopic cell analysis
US20170328924A1 (en) 2014-11-26 2017-11-16 Ronald Jones Automated microscopic cell analysis
US10061972B2 (en) 2015-05-28 2018-08-28 Tokitae Llc Image analysis systems and related methods
JP6461739B2 (en) 2015-07-28 2019-01-30 富士フイルム株式会社 Image processing apparatus, endoscope system, and method of operating image processing apparatus
DE102015113557B4 (en) 2015-08-17 2019-05-02 Gerresheimer Regensburg Gmbh Sample device with reference mark
EP3859425B1 (en) 2015-09-17 2024-04-17 S.D. Sight Diagnostics Ltd. Methods and apparatus for detecting an entity in a bodily sample
EP3353278B1 (en) 2015-11-02 2021-03-10 BioFire Diagnostics, LLC Sample preparation for difficult sample types
JP6559555B2 (en) 2015-12-02 2019-08-14 株式会社日立エルジーデータストレージ Optical measurement method and apparatus
WO2017168411A1 (en) 2016-03-30 2017-10-05 S.D. Sight Diagnostics Ltd Image processing device for identifying blood parasites
EP3455610B1 (en) 2016-05-11 2023-01-04 S.D. Sight Diagnostics Ltd. Sample carrier for optical measurements
US10281386B2 (en) 2016-05-11 2019-05-07 Bonraybio Co., Ltd. Automated testing apparatus
CN109564209B (en) 2016-05-11 2022-05-31 思迪赛特诊断有限公司 Optical measurements performed on samples
EP3482189A4 (en) 2016-07-08 2020-08-19 Medica Corporation Automated microscopic cell analysis
EP3669171A1 (en) 2017-08-17 2020-06-24 Abbott Point of Care Inc. A single-use test device for imaging blood cells
JP6505792B2 (en) 2017-08-29 2019-04-24 富士フイルム株式会社 LIGHT SOURCE DEVICE FOR ENDOSCOPE AND ENDOSCOPE SYSTEM
CN111788471B (en) 2017-11-14 2023-12-12 思迪赛特诊断有限公司 Sample carrier for optical measurement
WO2019102277A1 (en) 2017-11-23 2019-05-31 Sigtuple Technologies Private Limited Method and system for determining hematological parameters in a peripheral blood smear
WO2019198094A1 (en) 2018-04-09 2019-10-17 Sigtuple Technologies Private Limited Method and system for estimating total count of blood cells in a blood smear
JP2019195304A (en) 2018-05-10 2019-11-14 学校法人順天堂 Image analysis method, device, computer program, and generation method of deep learning algorithm
MX2022004703A (en) 2019-10-22 2022-05-11 S D Sight Diagnostics Ltd Accounting for errors in optical measurements.
WO2021188580A1 (en) 2020-03-17 2021-09-23 Detect, Inc. Rapid diagnostic test

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020028471A1 (en) * 1998-02-20 2002-03-07 Oberhardt Bruce J. Cell analysis methods and apparatus
US20030231791A1 (en) * 2002-06-12 2003-12-18 Torre-Bueno Jose De La Automated system for combining bright field and fluorescent microscopy
US20040241677A1 (en) * 2003-05-29 2004-12-02 Lin Jeffrey S Techniques for automated diagnosis of cell-borne anomalies with digital optical microscope
US20100136570A1 (en) * 2003-07-12 2010-06-03 Goldberg David A Sensitive and rapid determination of antimicrobial susceptibility
US20060063185A1 (en) * 2004-09-09 2006-03-23 Edouard Vannier Methods for detection of pathogens in red blood cells
US20080118399A1 (en) * 2004-12-13 2008-05-22 Roger Fleming Self-Contained Test Sensor
US20100068747A1 (en) * 2005-12-01 2010-03-18 Evotec Technologies Gmbh Generic Assay for Monitoring Endocytosis
US20080059135A1 (en) * 2006-07-24 2008-03-06 Sangeeta Murugkar Pathogen Detection Using Coherent Anti-Stokes Raman Scattering Microscopy
US20090128618A1 (en) * 2007-11-16 2009-05-21 Samsung Electronics Co., Ltd. System and method for object selection in a handheld image capture device
US20100295998A1 (en) * 2009-05-21 2010-11-25 Canon Kabushiki Kaisha Image processing apparatus and method of controlling the apparatus and program thereof
US20100300563A1 (en) * 2009-05-27 2010-12-02 John Ramunas Modular device and method for moving fluids to and from a sample delivery element

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12005443B2 (en) 2010-12-29 2024-06-11 S.D. Sight Diagnostics Ltd. Apparatus and method for analyzing a bodily sample
US10843190B2 (en) 2010-12-29 2020-11-24 S.D. Sight Diagnostics Ltd. Apparatus and method for analyzing a bodily sample
US10640807B2 (en) 2011-12-29 2020-05-05 S.D. Sight Diagnostics Ltd Methods and systems for detecting a pathogen in a biological sample
US11584950B2 (en) 2011-12-29 2023-02-21 S.D. Sight Diagnostics Ltd. Methods and systems for detecting entities in a biological sample
US11100634B2 (en) 2013-05-23 2021-08-24 S.D. Sight Diagnostics Ltd. Method and system for imaging a cell sample
US10176565B2 (en) 2013-05-23 2019-01-08 S.D. Sight Diagnostics Ltd. Method and system for imaging a cell sample
US11803964B2 (en) 2013-05-23 2023-10-31 S.D. Sight Diagnostics Ltd. Method and system for imaging a cell sample
US11295440B2 (en) 2013-05-23 2022-04-05 S.D. Sight Diagnostics Ltd. Method and system for imaging a cell sample
US11434515B2 (en) 2013-07-01 2022-09-06 S.D. Sight Diagnostics Ltd. Method and system for imaging a blood sample
US10093957B2 (en) 2013-07-01 2018-10-09 S.D. Sight Diagnostics Ltd. Method, kit and system for imaging a blood sample
US9329129B2 (en) 2013-07-01 2016-05-03 S.D. Sight Diagnostics Ltd. Method, kit and system for imaging a blood sample
US10831013B2 (en) 2013-08-26 2020-11-10 S.D. Sight Diagnostics Ltd. Digital microscopy systems, methods and computer program products
CN107077732B (en) * 2014-08-27 2020-11-24 思迪赛特诊断有限公司 System and method for calculating focus variation for digital microscope
CN107077732A (en) * 2014-08-27 2017-08-18 思迪赛特诊断有限公司 System and method for calculating digital microscope focus variations
US10482595B2 (en) 2014-08-27 2019-11-19 S.D. Sight Diagnostics Ltd. System and method for calculating focus variation for a digital microscope
US11100637B2 (en) 2014-08-27 2021-08-24 S.D. Sight Diagnostics Ltd. System and method for calculating focus variation for a digital microscope
US11721018B2 (en) 2014-08-27 2023-08-08 S.D. Sight Diagnostics Ltd. System and method for calculating focus variation for a digital microscope
US11262571B2 (en) 2015-09-17 2022-03-01 S.D. Sight Diagnostics Ltd. Determining a staining-quality parameter of a blood sample
EP3859425A1 (en) 2015-09-17 2021-08-04 S.D. Sight Diagnostics Ltd. Methods and apparatus for detecting an entity in a bodily sample
US10663712B2 (en) 2015-09-17 2020-05-26 S.D. Sight Diagnostics Ltd. Methods and apparatus for detecting an entity in a bodily sample
WO2017046799A1 (en) 2015-09-17 2017-03-23 S.D. Sight Diagnostics Ltd Methods and apparatus for detecting an entity in a bodily sample
US11914133B2 (en) 2015-09-17 2024-02-27 S.D. Sight Diagnostics Ltd. Methods and apparatus for analyzing a bodily sample
US10488644B2 (en) 2015-09-17 2019-11-26 S.D. Sight Diagnostics Ltd. Methods and apparatus for detecting an entity in a bodily sample
US11199690B2 (en) 2015-09-17 2021-12-14 S.D. Sight Diagnostics Ltd. Determining a degree of red blood cell deformity within a blood sample
US11796788B2 (en) 2015-09-17 2023-10-24 S.D. Sight Diagnostics Ltd. Detecting a defect within a bodily sample
WO2017168411A1 (en) 2016-03-30 2017-10-05 S.D. Sight Diagnostics Ltd Image processing device for identifying blood parasites
US11733150B2 (en) 2016-03-30 2023-08-22 S.D. Sight Diagnostics Ltd. Distinguishing between blood sample components
US11099175B2 (en) 2016-05-11 2021-08-24 S.D. Sight Diagnostics Ltd. Performing optical measurements on a sample
US11808758B2 (en) 2016-05-11 2023-11-07 S.D. Sight Diagnostics Ltd. Sample carrier for optical measurements
US11307196B2 (en) 2016-05-11 2022-04-19 S.D. Sight Diagnostics Ltd. Sample carrier for optical measurements
US11614609B2 (en) 2017-11-14 2023-03-28 S.D. Sight Diagnostics Ltd. Sample carrier for microscopy measurements
US11609413B2 (en) 2017-11-14 2023-03-21 S.D. Sight Diagnostics Ltd. Sample carrier for microscopy and optical density measurements
US11921272B2 (en) 2017-11-14 2024-03-05 S.D. Sight Diagnostics Ltd. Sample carrier for optical measurements
GB2600719B (en) * 2020-11-05 2023-10-11 Oxford Nanoimaging Ltd Fluorescence assay
WO2022096648A1 (en) * 2020-11-05 2022-05-12 Oxford NanoImaging Limited Fluorescence assay for identifying pathogens in a sample, and computer-implemented systems for carrying out such assays

Also Published As

Publication number Publication date
US10843190B2 (en) 2020-11-24
IN2012DN05069A (en) 2015-10-09
US20240293812A1 (en) 2024-09-05
US20160279633A1 (en) 2016-09-29
US12005443B2 (en) 2024-06-11
US20120169863A1 (en) 2012-07-05
US20210101147A1 (en) 2021-04-08
US9522396B2 (en) 2016-12-20
WO2012090198A3 (en) 2012-11-15

Similar Documents

Publication Publication Date Title
US12005443B2 (en) Apparatus and method for analyzing a bodily sample
Gopakumar et al. Convolutional neural network‐based malaria diagnosis from focus stack of blood smear images acquired using custom‐built slide scanner
US20230296495A1 (en) Distinguishing between blood sample components
EP3859425B1 (en) Methods and apparatus for detecting an entity in a bodily sample
CN105143850B (en) Autofocus system and method for the particle analysis in blood sample
JP4911172B2 (en) Analytical apparatus and use thereof
CN112106061A (en) Method and system for digital staining of unlabeled fluorescent images using deep learning
US11419590B2 (en) Biopsy device for coherent Raman imaging
JP5469070B2 (en) Method and system using multiple wavelengths for processing biological specimens
WO2012060163A1 (en) Cell analyzer
JP2012255810A (en) Biochip
JP5580117B2 (en) Cell analyzer
Shaw et al. Optical mesoscopy, machine learning, and computational microscopy enable high information content diagnostic imaging of blood films
Rupp et al. Fully automated detection of the counting area in blood smears for computer aided hematology
Münzenmayer et al. HemaCAM–A computer assisted microscopy system for hematology
Pozzi et al. Artificial intelligence in imaging flow cytometry
WO2024137310A1 (en) Point-of-care devices and methods for biopsy assessment
Fathi Artificial Intelligence in Diagnostic Medical Parasitology: The State of the Art
JP2014183854A (en) Cell analyzer
EP4238072A1 (en) A method for automated determination of platelet count based on microscopic images of peripheral blood smears

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 5069/DELNP/2012

Country of ref document: IN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 11853846

Country of ref document: EP

Kind code of ref document: A2

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 11853846

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 11853846

Country of ref document: EP

Kind code of ref document: A2