CN117456222A - Hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria - Google Patents
Hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria Download PDFInfo
- Publication number
- CN117456222A CN117456222A CN202311110480.2A CN202311110480A CN117456222A CN 117456222 A CN117456222 A CN 117456222A CN 202311110480 A CN202311110480 A CN 202311110480A CN 117456222 A CN117456222 A CN 117456222A
- Authority
- CN
- China
- Prior art keywords
- bacteria
- hyperspectral
- classification
- mixed
- identification
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 241000894006 Bacteria Species 0.000 title claims abstract description 80
- 238000003384 imaging method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 title claims abstract description 14
- 230000001580 bacterial effect Effects 0.000 claims abstract description 31
- 238000001228 spectrum Methods 0.000 claims abstract description 15
- 241000894007 species Species 0.000 claims abstract description 9
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 238000000386 microscopy Methods 0.000 claims abstract description 4
- 239000000284 extract Substances 0.000 claims abstract 2
- 238000001514 detection method Methods 0.000 claims description 15
- 238000012706 support-vector machine Methods 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000000513 principal component analysis Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000004611 spectroscopical analysis Methods 0.000 claims description 4
- 238000000411 transmission spectrum Methods 0.000 claims description 3
- 208000035143 Bacterial infection Diseases 0.000 abstract description 5
- 208000022362 bacterial infectious disease Diseases 0.000 abstract description 5
- 206010040047 Sepsis Diseases 0.000 abstract description 2
- 238000010186 staining Methods 0.000 abstract description 2
- 244000052616 bacterial pathogen Species 0.000 description 3
- 238000003759 clinical diagnosis Methods 0.000 description 3
- 230000001717 pathogenic effect Effects 0.000 description 3
- 244000063299 Bacillus subtilis Species 0.000 description 2
- 235000014469 Bacillus subtilis Nutrition 0.000 description 2
- 241000588724 Escherichia coli Species 0.000 description 2
- 241000589517 Pseudomonas aeruginosa Species 0.000 description 2
- 241000607142 Salmonella Species 0.000 description 2
- 241000191967 Staphylococcus aureus Species 0.000 description 2
- 239000003242 anti bacterial agent Substances 0.000 description 2
- 229940088710 antibiotic agent Drugs 0.000 description 2
- 238000010790 dilution Methods 0.000 description 2
- 239000012895 dilution Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 244000052769 pathogen Species 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003115 biocidal effect Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003752 polymerase chain reaction Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria. The hyperspectral microscopy system comprises a microscopic imaging module, a hyperspectral light splitting module, a data classification processing module and the like. Hyperspectral images of different bacteria collected by the system are used for extracting spectra and morphologies as identification features and training a machine learning model. For a mixed bacterial sample, the system collects and extracts the spectrum and morphology of single bacteria in a hyperspectral image, and the species identification of each bacteria in the mixed bacterial sample is realized by combining a trained machine learning model. The invention can realize rapid identification and counting of mixed bacteria without staining, and has great application value for detecting multi-bacterial infection, sepsis bacteria and the like in clinic.
Description
Technical Field
The invention belongs to the field of biomedical detection, and particularly relates to a hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria.
Background
Pathogenic bacterial infection is one of the challenging problems in the world public health field and if not diagnosed and treated in time, can pose a significant threat to the physical health and life safety of the infected patient. Bacterial identification is critical to the quality of pathogenic infections and is the basis for the establishment of appropriate treatment regimens for patients in clinical diagnosis. However, the conventional detection method requires complicated bacterial culture, and is long in time and high in cost. Hyperspectral microscopic imaging can simultaneously acquire hyperspectral cube information of spectra and morphological characteristics of pathogens on a single bacteria level, and realizes rapid and effective bacteria classification and concentration detection. However, current bacterial identification studies based on hyperspectral imaging techniques have difficulty in extracting robust and fine bacterial species-related features for identification classification, often requiring staining means to aid identification; and only a single pathogenic bacterium is identified, and the identification of mixed bacteria cannot be realized. How to realize low-cost, high-sensitivity, high-automation and rapid pathogen recognition, fill the blank of the recognition and classification of mixed strains in multi-strain infection cases in the current bacterial detection scheme, provide accurate antibiotic use guidance for clinical diagnosis and treatment, and still be one of the difficulties to be solved in the current medical field.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention discloses a hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria.
A hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria is characterized by comprising the following steps of: and collecting a transmission hyperspectral image of the mixed bacteria by using an autonomously built hyperspectral microscopic system, extracting transmission spectrums and morphologies of all single bacterial areas in the transmission hyperspectral image as identification features, and combining a machine learning method to realize microscopic imaging rapid identification, classification and counting of the mixed bacteria under a dyeing-free condition.
The hyperspectral microscopy system sequentially comprises a microscopic imaging module, a hyperspectral light splitting module, a data classification processing module and the like. The microscopic imaging module comprises an illumination light source, an electric displacement platform, a microscope objective, a tube lens, a beam splitter and a first camera, wherein the light source irradiates the mixed bacteria sample in a transmission mode, the transmitted light is collimated into parallel light beams with different angles after passing through the microscope objective, and the parallel light beams are focused at the position of the first camera through the tube lens and the beam splitter to form a conjugated microscopic image. The conjugate microscopic image can be used for assisting in adjusting the position and the focusing depth of the sample so as to enable the hyperspectral image surface to be clear.
The hyperspectral light-splitting module sequentially comprises a slit, a collimating lens, a prism-grating-prism, a focusing lens and a second camera, and parallel light beams emitted from the microscope objective lens are focused on the slit through the tube lens and the beam splitter. Light emitted from the center of the slit is collimated into parallel light by the collimating lens, and after passing through the prism-grating-prism, the light with different wavelengths is focused on different positions of the second camera photosurface by the third focusing lens, so that a spectrum image is formed.
The data classification processing module is characterized in that the data classification processing module trains collected different types of bacteria data by taking the spectrum and the morphology information of single bacteria extracted after dilution in a certain proportion as identification features so as to perform classification detection on mixed bacteria. The invention takes principal component analysis and a support vector machine as examples to realize the species identification of bacteria. The principal component analysis is used for extracting principal component information of the bacteria hyperspectral image so as to reduce redundancy of the bacteria spectrum information and increase differences among different types of bacteria data. The support vector machine realizes different kinds of bacterial classification by establishing a decision boundary of bacterial samples.
The data classification processing module is characterized in that the data classification processing module performs image processing on hyperspectral images of collected mixed bacteria, the hyperspectral images comprise threshold segmentation and edge detection, spectrum and morphology information of each bacterial area in the images are extracted to serve as identification features, and trained principal component analysis and a support vector machine are combined to complete species identification of single bacteria, so that species identification of all bacteria in a mixed bacteria sample is achieved.
Other hyperspectral spectroscopy modules, including those based on tunable filters, are also included in the present invention.
The data classification processing module and other machine learning methods are also included in the invention for classifying bacteria.
The beneficial effects of the invention are that
The invention discloses a hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria, which can rapidly acquire stable and fine hyperspectral morphology information on a single bacteria level as identification characteristics of bacterial species, so as to realize precise identification and classification of mixed bacteria samples on the single bacteria level. The system is used as an effective and rapid diagnostic tool, has the effectiveness and capability of carrying out fine identification on mixed bacterial pathogen samples, and provides guidance for correctly using antibiotics in bacterial infection treatment in clinical diagnosis.
Compared with the traditional methods of bacterial detection, such as culture for microscopic detection, polymerase chain reaction detection and the like, the method has the advantages that the detection speed is high, time-consuming operations such as bacterial culture, dyeing and the like are not needed, and rapid and real-time identification can be realized; and aiming at mixed pathogenic bacteria samples, the method can realize accurate identification and classification on single bacteria level, and has great application value for clinical multi-bacterial infection diseases, biomedical bacteria detection, sepsis bacteria detection and the like.
Drawings
FIG. 1 is a schematic diagram of a system for detecting mixed bacteria;
in the figure, an illumination light source 1, an electric displacement table 2, a microscope objective 3, a tube lens 4, a beam splitter 5, a hyperspectral beam splitter 12, a first camera 6, a slit 7, a collimating lens 8, a prism-grating-prism 9, a focusing lens 10, and a second camera 11
FIG. 2 shows the results of detection of mixed bacteria. FIG. 2 (a) is a transmission hyperspectral image of a mixed bacterial sample in which five bacteria are mixed in approximately equal amounts. Fig. 2 (b) is a binarized image processed using a thresholding and edge detection algorithm, wherein individual bacterial areas can be extracted from the image background. FIG. 2 (c) shows the identification result of the mixed bacteria. And extracting the morphology and hyperspectral features of all bacteria as input data of a principal component analysis-support vector machine algorithm, and realizing identification, identification and classification of the bacteria. According to experimental recognition results, the five mixed bacterial distributions of escherichia coli, staphylococcus aureus, bacillus subtilis, salmonella and pseudomonas aeruginosa are marked as 1, 2, 3, 4 and 5.
Detailed Description
The invention is further elucidated below in connection with the accompanying drawings.
A hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria is characterized by comprising the following steps of: and collecting a transmission hyperspectral image of the mixed bacteria by using an autonomously built hyperspectral microscopic system, extracting transmission spectrums and morphologies of all single bacterial areas in the transmission hyperspectral image as identification features, and combining a machine learning method to realize microscopic imaging rapid identification, classification and counting of the mixed bacteria under a dyeing-free condition.
The hyperspectral microscopy system comprises a microscopic imaging module, a hyperspectral light splitting module, a data classification processing module and the like. The microscopic imaging module comprises an illumination light source, an electric displacement platform, a microscope objective, a tube lens, a beam splitter and a first camera, wherein light transmitted by a sample to be detected is collimated into parallel light beams with different angles after passing through the microscope objective, and the parallel light beams are focused at the position of the first camera through the tube lens and the beam splitter to form a conjugate microscopic image. The conjugate microscopic image can be used to assist in adjusting the sample position so that the hyperspectral image plane is clear. The hyperspectral light-splitting module sequentially comprises a slit, a collimating lens, a prism-grating-prism, a focusing lens and a second camera, wherein parallel light beams emitted from the microscope objective lens are focused on the slit through the tube lens and the beam-splitting lens, and the second light path is focused on the slit. Light emitted from the center of the slit is collimated into parallel light by the collimating lens, and after passing through the prism-grating-prism, the light with different wavelengths is focused on different positions of the second camera photosurface by the third focusing lens, so that a spectrum image is formed.
The data classification processing module is characterized in that the data classification processing module trains collected different types of bacteria data by taking the spectrum and the morphology information of single bacteria extracted after dilution in a certain proportion as identification features so as to perform classification detection on mixed bacteria. The invention takes principal component analysis and a support vector machine as examples to realize the species identification of bacteria. The principal component analysis is used for extracting principal component information of the bacteria hyperspectral image so as to reduce redundancy of the bacteria spectrum information and increase differences among different types of bacteria data. The support vector machine realizes different kinds of bacterial classification by establishing a decision boundary of bacterial samples.
The data classification processing module is characterized in that the data classification processing module performs image processing on hyperspectral images of collected mixed bacteria, the image processing comprises threshold segmentation and edge detection, spectrum and morphology information of each bacterial area in the images are extracted to serve as identification features, trained principal component analysis and a support vector machine are combined, type identification of single bacteria is completed, and then type identification of all bacteria in a mixed bacteria sample is achieved, and concentration of each bacteria is calculated.
Other hyperspectral spectroscopy modules, including those based on tunable filters, are also included in the present invention.
The data classification processing module and other machine learning methods are also included in the invention for classifying bacteria.
The embodiments in the foregoing description may be further combined or replaced, and the embodiments are merely illustrative of the preferred embodiments of the present invention and are not intended to limit the spirit and scope of the present invention, and various changes and modifications made by those skilled in the art to which the present invention pertains without departing from the spirit of the present invention. The scope of the invention is given by the appended claims and any equivalents thereof.
The detection results of the mixed bacteria are shown in FIG. 2. Fig. 2 (a) shows a transmission hyperspectral image of a mixed bacterial sample, with approximately equal amounts of the five bacteria mixed. An imaging processing method of threshold segmentation and edge detection is adopted, and a single bacterial area is extracted from an image background, so that a black-and-white binarized image as shown in fig. 2 (b) is obtained. The morphology and hyperspectral features of all bacteria are extracted as input data of a principal component analysis-support vector machine algorithm for identification, identification and classification of the bacteria. The identification result of the mixed bacteria is shown in FIG. 2 (c). According to experimental recognition results, the five mixed bacterial distributions of escherichia coli, staphylococcus aureus, bacillus subtilis, salmonella and pseudomonas aeruginosa are marked as 1, 2, 3, 4 and 5. After the principal component analysis-support vector machine classification, the concentration ratio of the five bacteria is approximately equal and is basically consistent with the equal mixing result. Experiments prove that the provided hyperspectral bacteria identification method is effective in extracting, identifying and classifying various mixed bacteria, has potential application in bacterial infection analysis, and provides diagnosis basis for correctly using antibiotics.
Claims (5)
1. A hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria is characterized by comprising the following steps of: and collecting a transmission hyperspectral image of the mixed bacteria by using an autonomously built hyperspectral microscopic system, extracting transmission spectrums and morphologies of all single bacterial areas in the transmission hyperspectral image as identification features, and combining a machine learning method to realize rapid identification, classification and counting of the mixed bacteria under a dyeing-free condition.
2. The hyperspectral microscopy system of claim 1, comprising a microscopic imaging module, a hyperspectral spectroscopy module, a data classification processing module, and the like in sequence. The microscopic imaging module comprises an illumination light source, an electric displacement platform, a microscope objective, a tube lens, a beam splitter and a first camera. The transmitted light of the mixed bacterial sample is collimated into parallel light beams with different angles after passing through the microscope objective lens, and the parallel light beams are focused at the first camera position through the tube lens and the beam splitter to form a conjugate microscopic image. The conjugate microscopic image can be used to assist in adjusting the sample position so that the hyperspectral image plane is clear.
3. The hyperspectral spectroscopic module according to claim 2, comprising in order a slit, a collimator lens, a prism-grating-prism, a focusing lens, a second camera, a parallel light beam exiting from the microscope objective lens being focused on the slit position via the tube lens and the beam splitter. Light emitted from the center of the slit is collimated into parallel light by the collimating lens, and after passing through the prism-grating-prism, the light with different wavelengths is focused on different positions of the second camera photosurface by the focusing lens, so that a spectrum image is formed. Other hyperspectral spectroscopy modules, including those based on tunable filters, are also included in the present invention.
4. The data classification module of claim 2, wherein the data classification module trains to collect different types of bacteria hyperspectral data for classification detection of mixed bacteria. The invention takes a principal component analysis and a support vector machine as an example, and realizes the classification of mixed bacteria by extracting spectrum and morphology information of single bacteria as identification features. The principal component analysis is used for extracting principal component information of the bacteria hyperspectral image so as to reduce redundancy of the bacteria spectrum information and increase differences among different types of bacteria data. The support vector machine realizes different kinds of bacterial classification by establishing a decision boundary of bacterial samples. Other machine learning methods for bacterial classification are also encompassed by the present invention.
5. The data classification processing module according to claim 2, wherein the data classification processing module performs image processing on hyperspectral images of collected mixed bacteria, including threshold segmentation and edge detection, extracts spectrum and morphology information of a single bacterial area as identification features, and combines principal component analysis and a support vector machine to complete species identification of the single bacteria, thereby realizing species identification of all bacteria in a mixed bacterial sample and calculating concentration of each bacteria respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311110480.2A CN117456222A (en) | 2023-08-31 | 2023-08-31 | Hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311110480.2A CN117456222A (en) | 2023-08-31 | 2023-08-31 | Hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117456222A true CN117456222A (en) | 2024-01-26 |
Family
ID=89586224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311110480.2A Pending CN117456222A (en) | 2023-08-31 | 2023-08-31 | Hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117456222A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107064019A (en) * | 2017-05-18 | 2017-08-18 | 西安交通大学 | The device and method for gathering and splitting for dye-free pathological section high spectrum image |
| CN112861627A (en) * | 2021-01-07 | 2021-05-28 | 中国科学院西安光学精密机械研究所 | Pathogenic bacteria species identification method and system based on microscopic hyperspectral technology |
| CN113065403A (en) * | 2021-03-05 | 2021-07-02 | 浙江大学 | Hyperspectral imaging-based machine learning cell classification method and device |
| CN113267252A (en) * | 2021-05-17 | 2021-08-17 | 浙江大学 | Staring type confocal microscopic morphology spectrum four-dimensional detection system |
| WO2022254332A1 (en) * | 2021-06-01 | 2022-12-08 | Microtechnix | Device and method for counting and identification of bacterial colonies using hyperspectral imaging |
-
2023
- 2023-08-31 CN CN202311110480.2A patent/CN117456222A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107064019A (en) * | 2017-05-18 | 2017-08-18 | 西安交通大学 | The device and method for gathering and splitting for dye-free pathological section high spectrum image |
| CN112861627A (en) * | 2021-01-07 | 2021-05-28 | 中国科学院西安光学精密机械研究所 | Pathogenic bacteria species identification method and system based on microscopic hyperspectral technology |
| CN113065403A (en) * | 2021-03-05 | 2021-07-02 | 浙江大学 | Hyperspectral imaging-based machine learning cell classification method and device |
| CN113267252A (en) * | 2021-05-17 | 2021-08-17 | 浙江大学 | Staring type confocal microscopic morphology spectrum four-dimensional detection system |
| WO2022254332A1 (en) * | 2021-06-01 | 2022-12-08 | Microtechnix | Device and method for counting and identification of bacterial colonies using hyperspectral imaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20160279633A1 (en) | Apparatus and Method for Analyzing a Bodily Sample | |
| DE102006053540B3 (en) | Optospectroscopic analysis of biological sample in fluid, comprises: fixing the biological sample in a sample holding unit, categorizing particles in biological sample based on an analysis of the image data and analyzing biological sample | |
| Taylor et al. | The new vision of light microscopy | |
| WO2017157555A1 (en) | High accuracy 5-part differential with digital holographic microscopy and untouched leukocytes from peripheral blood | |
| CN101167101A (en) | Automated image analysis | |
| CN104094118A (en) | Method and apparatus for automated platelet identification within whole blood sample from microscopy images | |
| Deglint et al. | Investigating the automatic classification of algae using the spectral and morphological characteristics via deep residual learning | |
| El-Melegy et al. | Automatic detection of tuberculosis bacilli from microscopic sputum smear images using faster r-cnn, transfer learning and augmentation | |
| Govindan et al. | Automated tuberculosis screening using Zeihl Neelson image | |
| CN116380795A (en) | Phytoplankton bright field and fluorescence dual-light path synchronous imaging device | |
| CN112861627A (en) | Pathogenic bacteria species identification method and system based on microscopic hyperspectral technology | |
| CN117456222A (en) | Hyperspectral microscopic imaging rapid identification, classification and counting method for mixed bacteria | |
| WO2018020433A1 (en) | Combined optical-spectroscopic method for identifying microbial pathogens | |
| JP2016185075A (en) | Sample analysis method and sample analyzer | |
| Ahn et al. | Human-level blood cell counting on lens-free shadow images exploiting deep neural networks | |
| Tian et al. | Graded diagnosis of Helicobacter pylori infection using hyperspectral images of gastric juice | |
| Sun et al. | A rapid procedure for bacterial identification and antimicrobial susceptibility testing directly from positive blood cultures | |
| CN116685405A (en) | Fluorescent assay for identifying pathogens in a sample and computer-implemented system for performing such an assay | |
| Katar et al. | Automatic classification of white blood cells using pre-trained deep models | |
| Zhu et al. | High-Accuracy Rapid Identification and Classification of Mixed Bacteria Using Hyperspectral Transmission Microscopic Imaging and Machine Learning. | |
| Xue et al. | Multiline orthogonal scanning temporal focusing (mosTF) microscopy for scattering reduction in high-speed in vivo brain imaging | |
| Makau-Barasa et al. | Performance evaluation of the AiDx multi-diagnostic automated microscope for the detection of schistosomiasis in Abuja, Nigeria | |
| Radhakrishnan et al. | Rapid handheld screening device to detect skin and soft tissue infections | |
| Thomas et al. | Image Recognition, Recusion Cellular Classification Using Different Techniques and Detecticting Microscopic Deformities | |
| CN117571683A (en) | Raman optical rapid detection method and system for microorganisms in tears |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |