WO2022241245A2

WO2022241245A2 - Techniques for spore separation, detection, and quantification

Info

Publication number: WO2022241245A2
Application number: PCT/US2022/029239
Authority: WO
Inventors: Monika WEBER; David FRAEBEL; Robert Weber; Slawomir ANTOSZCZYK
Original assignee: Fluid-Screen, Inc.
Priority date: 2021-05-13
Filing date: 2022-05-13
Publication date: 2022-11-17
Also published as: WO2022241245A3

Abstract

Systems and methods distinguishing microbes in an image are provided. The image including first microbes of a first type and second microbes of a second type different from the first type. The method comprises segmenting the image to detect the first microbes and the second microbes in the image, classifying each microbe in the segmented image as being of the first type or the second type, wherein the classification is based, at least in part, on at least one characteristic of microbe, and outputting a result of the classifying the microbe as being of the first type or the second type.

Description

TECHNIQUES FOR SPORE SEPARATION, DETECTION, AND QUANTIFICATION

RELATED APPLICATIONS

[0001] This application claims priority under 35 U.S.C. § 119(e) to U.S. Provisional Application No.: 63/188,279 filed May 13, 2021 and entitled “TECHNIQUES FOR SPORE SEPARATION, DETECTION, AND QUANTIFICATION,” the entire contents of which is incorporated by reference herein.

BACKGROUND

[0002] Detection and identification of particles (e.g., bacterial and viral pathogens) present in cell containing solutions (e.g., blood, urine, CSF, mammalian cell culture, CHO cell matrix, CAR-T drug product, CAR-T specimen, CAR-NK drug product, body fluids, apheresis samples or samples related to immunotherapy), protein containing solutions (e.g., for pharmaceuticals during manufacturing, drug product, drug substance), analyte extraction from microbiome samples (including human microbiome samples), drug substance, drug product and drug samples along the manufacturing process, water, sterile fluids and other fluids is possible by employing isolation on cultural media and metabolic fingerprinting methods. Isozyme analysis, direct colony thin layer chromatography and gel electrophoresis techniques have been successfully applied for the detection of some bacterial pathogens. Immunoassay and nucleic acid-based assays are now widely accepted techniques, providing more sensitive and specific detection and quantification of bacteria.

[0003] Dielectrophoresis (DEP) relates to a force of an electric field gradient on objects having dielectric moments. DEP has shown promise for particle separation, but has not yet been applied in clinical settings, pharmaceutical quality assurance settings, or immunotherapy. DEP uses a natural or induced dipole to cause a net force on a particle in a region having an electric field gradient. The force depends on the Clausius-Mossotti factor associated with particle.

SUMMARY

[0004] Aspects of the technology described herein relate to separation, detection and quantification of spores in a fluid sample.

[0005] In some embodiments, a method for distinguishing microbes in an image including first microbes of a first type and second microbes of a second type different from the first type is provided. The method comprises segmenting the image to detect the first microbes and the second microbes in the image, classifying each microbe in the segmented image as being of the first type or the second type, wherein the classification is based, at least in part, on at least one characteristic of microbe, and outputting a result of the classifying the microbe as being of the first type or the second type.

[0006] In one aspect, the first microbes are endospores and the second microbes are vegetative cells. In one aspect, the image is color image including a plurality of color channels, and wherein the method further comprises removing at least one of the plurality of color channels prior to segmenting the image. In one aspect, removing at least one of the plurality of color channels comprises separating the plurality of color channels in the color image, and combining one or more of the plurality of color channels after removing the at least one of the plurality of color channels. In one aspect, the color image is a red-green-blue (RGB) image including red, green and blue color channels, and wherein removing at least one of the plurality of color channels comprises removing the blue color channel. In one aspect, the image is a color image, and wherein the method further comprises converting the color image to a grayscale image prior to segmenting the image.

[0007] In one aspect, the method further comprises performing background subtraction on the image prior to segmenting the image. In one aspect, performing background subtraction on the image comprises subtracting a same value from a value of each pixel in the image. In one aspect, the same value is determined based on a value of one or more pixels in the image representing an electrode of the microfluidic system. In one aspect, the same value is determined based on a value of one or more pixels in the image representing an inter-electrode space.

[0008] In one aspect, the image is a color image including a plurality of color channels, segmenting the image comprises defining an intensity range for each of the plurality of color channels, and classifying each microbe in the segmented image comprises classifying the microbe as being of the first type when its intensity falls within the intensity range for each of the plurality of color channels.

[0009] In one aspect, segmenting the image comprises generating a grayscale image based on the image, and classifying each microbe in the segmented image comprises defining an intensity phase for the first type and/or the second type of microbes, and classifying the microbe based, at least in part, on its intensity and the defined intensity phase for the first type and/or the second type of microbes. [0010] In one aspect, segmenting the image comprises generating a hue-saturation-value (HSV) image based on the image, the HSV image including a hue channel, a saturation channel and a value channel, and classifying each microbe in the segmented image comprises defining a value range for each of the hue channel, the saturation channel and the value channel, and classifying the microbe as being of the first type when its intensity value in the HSV image falls within the value range for each of the hue channel, the saturation channel and the value channel. [0011] In one aspect, the at least one characteristic includes a morphological characteristic.

In one aspect, the morphological characteristic comprises a size and/or shape of the microbe. In one aspect, the size of the microbe comprises a number of contiguous pixels representing the microbe in the image. In one aspect, the size of the microbe is determined based on at least one measurement selected from the group consisting of an area, a circumference, a diameter, an extent, and a bisector. In one aspect, the shape of the microbe is determined based on at least one measurement selected from the group consisting of an aspect ratio, an elongation value, a convexity value, a shape factor, and a sphericity value.

[0012] In one aspect, classifying each microbe in the segmented image as being of the first type or the second type comprises performing principal component analysis on each microbe in the segmented image, and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the principal component analysis. In one aspect, classifying each microbe in the segmented image as being of the first type or the second type comprises performing singular value decomposition on each microbe in the segmented image, and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the singular value decomposition.

[0013] In one aspect, classifying the microbe as being of the first type or the second type comprises providing, as input to a trained machine learning model, the image and/or one or more features derived from the image, and classifying the microbe as being of the first type or the second type based, at least in part, on an output of the trained machine learning model. In one aspect, the first microbes are endospores and the second microbes are vegetative cells, and wherein the trained machine learning model has been trained to recognize endospores and/or vegetative cells.

[0014] In one aspect, the method further comprises filtering the image prior to classifying the microbe in the segmented image as being of the first type or the second type. In one aspect, filtering the image comprises filtering the image prior to segmenting the image. [0015] In one aspect, the method further comprises prior to the classifying, filtering from the detected first microbes and second microbes in the segmented image, objects having a diameter greater than a predetermined number of pixels.

[0016] In some embodiments, a system for distinguishing microbes in an image captured by a microfluidic system, the image including first microbes of a first type and second microbes of a second type different from the first type is provided. The system comprises a microfluidic passage for receiving a sample, the sample comprising the first microbes and the second microbes, at least one electrode disposed in the microfluidic passage, the at least one electrode configured to immobilize, when activated, the first microbes and the second microbes onto a surface of the at least one electrode using dielectrophoresis, an optical system configured to capture the image while the first microbes and the second microbes are immobilized on the surface of the at least one electrode, and at least one computing device. The at least one computing device is configured to segment the image to detect the first microbes and the second microbes in the image, classify each microbe in the segmented image as being of the first type or the second type, wherein the classification is based, at least in part, on at least one characteristic of microbe, and output a result of the classifying the microbe as being of the first type or the second type.

[0017] In one aspect, the first microbes are endospores and the second microbes are vegetative cells. In one aspect, the image is color image including a plurality of color channels, and wherein the at least one computing device is further configured to remove at least one of the plurality of color channels prior to segmenting the image. In one aspect, removing at least one of the plurality of color channels comprises separating the plurality of color channels in the color image, and combining one or more of the plurality of color channels after removing the at least one of the plurality of color channels. In one aspect, the color image is a red-green-blue (RGB) image including red, green and blue color channels, and wherein removing at least one of the plurality of color channels comprises removing the blue color channel.

[0018] In one aspect, the image is a color image, and wherein the method further comprises converting the color image to a grayscale image prior to segmenting the image. In one aspect, the at least one computing device is further configured to perform background subtraction on the image prior to segmenting the image. In one aspect, performing background subtraction on the image comprises subtracting a same value from a value of each pixel in the image. In one aspect, the same value is determined based on a value of one or more pixels in the image representing an electrode of the microfluidic system. In one aspect, the same value is determined based on a value of one or more pixels in the image representing an inter-electrode space.

[0019] In one aspect, the image is a color image including a plurality of color channels, segmenting the image comprises defining an intensity range for each of the plurality of color channels, and classifying each microbe in the segmented image comprises classifying the microbe as being of the first type when its intensity falls within the intensity range for each of the plurality of color channels.

[0020] In one aspect, segmenting the image comprises generating a grayscale image based on the image, and classifying each microbe in the segmented image comprises defining an intensity phase for the first type and/or the second type of microbes, and classifying the microbe based, at least in part, on its intensity and the defined intensity phase for the first type and/or the second type of microbes.

[0021] In one aspect, segmenting the image comprises generating a hue-saturation-value (HSV) image based on the image, the HSV image including a hue channel, a saturation channel and a value channel, and classifying each microbe in the segmented image comprises defining a value range for each of the hue channel, the saturation channel and the value channel, and classifying the microbe as being of the first type when its intensity value in the HSV image falls within the value range for each of the hue channel, the saturation channel and the value channel. [0022] In one aspect, the at least one characteristic includes a morphological characteristic.

[0023] In one aspect, classifying each microbe in the segmented image as being of the first type or the second type comprises performing principal component analysis on each microbe in the segmented image, and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the principal component analysis. In one aspect, classifying each microbe in the segmented image as being of the first type or the second type comprises performing singular value decomposition on each microbe in the segmented image, and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the singular value decomposition. In one aspect, classifying the microbe as being of the first type or the second type comprises providing, as input to a trained machine learning model, the segmented image and/or one or more features derived from the segmented image, and classifying the microbe as being of the first type or the second type based, at least in part, on an output of the trained machine learning model. In one aspect, the first microbes are endospores and the second microbes are vegetative cells, and wherein the trained machine learning model has been trained to recognize endospores and/or vegetative cells.

[0024] In one aspect, the at least one computing device is further configured to filter the image prior to classifying the microbe in the segmented image as being of the first type or the second type. In one aspect, filtering the image comprises filtering the image prior to segmenting the image.

[0025] In one aspect, the at least one computing device is further configured to prior to the classifying, filtering from the detected first microbes and second microbes in the segmented image, objects having a diameter greater than a predetermined number of pixels.

[0026] In some embodiments, a method for separating spores from vegetative bacteria in a fluid sample is provided. The method comprises providing the fluid sample as input to a microfluidic passage of a microfluidic device, wherein the microfluidic device includes at least one electrode disposed adjacent to the microfluidic passage, and activating the at least one electrode to separate the spores from the vegetative bacteria in the fluid sample based, at least in part, on a different dielectrophoretic response for the spores and the vegetative bacteria when the at least one electrode is activated.

[0027] In one aspect, activating the at least one electrode comprises applying a voltage to the at least one electrode, the voltage having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to edges of the at least one electrode while not attracting the spores to the edges of the at least one electrode.

[0028] In one aspect, the microfluidic device comprises a microfluidic chip, and wherein providing the fluid sample as input to the microfluidic passage comprises loading the fluid sample onto the microfluidic chip.

[0029] In one aspect, activating the at least one electrode comprises applying a first voltage to the at least one electrode having a first frequency that generates a first dielectrophoretic force to attract the vegetative bacteria and the spores to a surface of the at least one electrode, and applying a second voltage to the at least one electrode having a second frequency that generates a second dielectrophoretic force to release one of the vegetative bacteria or the spores from the surface of the at least one electrode. In one aspect, providing the fluid sample as input to the microfluidic passage comprises pumping the fluid sample through the microfluidic passage. In one aspect, the second frequency of the second voltage is configured to selectively release the spores from the surface of the at least one electrode. In one aspect, the method further comprises collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores released from the surface of the at least one electrode.

[0030] In one aspect, the second frequency of the second voltage is configured to selectively release the vegetative cells from the surface of the at least one electrode. In one aspect, the method further comprises capturing at least one image of the at least one electrode following release of the vegetative cells from the surface of the at least one electrode and while the spores remain attracted to the surface of the at least one electrode. In one aspect, the method further comprises processing the at least one image to quantify an amount of spores in the fluid sample. In one aspect, the method further comprises passing a fluid comprising a stain through the microfluidic passage, the stain configured to stain the spores, wherein quantifying the amount of spores comprises counting a number of stained spores in the at least one image. In one aspect, providing the fluid sample as input to the microfluidic passage comprises pumping the fluid sample through the microfluidic passage, and activating the at least one electrode comprises applying a voltage to the at least one electrode having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to a surface of the at least one electrode while not attracting the endospores to the surface of the at least one electrode as the fluid sample flows past the at least one electrode. In one aspect, the method further comprises collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores. In one aspect, the voltage applied to the at least one electrode has an amplitude greater than 40V.

[0031] In some embodiments, a system for separating spores from vegetative bacteria in a fluid sample is provided. The system comprises a microfluidic passage for receiving the fluid sample, the fluid sample comprising the spores and the vegetative bacteria, and at least one electrode disposed in the microfluidic passage, the at least one electrode configured to separate, when activated, the spores from the vegetative bacteria in the fluid sample based, at least in part, on a different dielectrophoretic response for the spores and the vegetative bacteria when the at least one electrode is activated. [0032] In one aspect, the system further comprises a controller configured to activate the at least one electrode by applying a voltage to the at least one electrode, the voltage having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to edges of the at least one electrode while not attracting the spores to the edges of the at least one electrode. In one aspect, the microfluidic passage is included on a microfluidic chip, and wherein receiving the fluid sample comprises receiving the sample via loading the fluid sample onto the microfluidic chip.

[0033] In one aspect, the system further comprises a controller configured to activate the at least one electrode by applying a first voltage to the at least one electrode having a first frequency that generates a first dielectrophoretic force to attract the vegetative bacteria and the spores to a surface of the at least one electrode, and applying a second voltage to the at least one electrode having a second frequency that generates a second dielectrophoretic force to release one of the vegetative bacteria or the spores from the surface of the at least one electrode. In one aspect, the system further comprises a pump configured to pump the fluid sample through the microfluidic passage. In one aspect, the second frequency of the second voltage is configured to selectively release the spores from the surface of the at least one electrode. In one aspect, the system further comprises an effluent fluid container configured to collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores released from the surface of the at least one electrode. In one aspect, the second frequency of the second voltage is configured to selectively release the vegetative cells from the surface of the at least one electrode.

[0034] In one aspect, the system further comprises an optical system configured to capture at least one image of the at least one electrode following release of the vegetative cells from the surface of the at least one electrode and while the spores remain attracted to the surface of the at least one electrode. In one aspect, the system further comprises at least one computing device configured to process the at least one image to quantify an amount of spores in the fluid sample. In one aspect, the system further comprises a pump configured to pump a fluid comprising a stain through the microfluidic passage, the stain configured to stain the spores, wherein quantifying the amount of spores comprises counting a number of stained spores in the at least one image. In one aspect, the pump is configured to pump the fluid sample through the microfluidic passage, and the controller is further configured to activate the at least one electrode by applying a voltage to the at least one electrode having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to a surface of the at least one electrode while not attracting the endospores to the surface of the at least one electrode as the fluid sample flows past the at least one electrode. In one aspect, the system further comprises an effluent fluid container configured to collect at an outlet of the microfluidic passage, effluent fluid comprising the spores. In one aspect, the voltage applied to the at least one electrode has an amplitude greater than 40V.

[0035] In some embodiments, a method for quantifying spores in a fluid sample is provided. The method comprises providing the fluid sample as input to a microfluidic passage of a microfluidic device, wherein the microfluidic device includes at least one electrode disposed adjacent to the microfluidic passage, activating the at least one electrode to attract the spores to a surface of the at least one electrode using dielectrophoresis, capturing at least one first image of the at least one electrode while the spores are attracted to the surface of the at least one electrode, and quantifying an amount of spores in the fluid sample based, at least in part, on analyzing the at least one first image.

[0036] In one aspect, the microfluidic device comprises a microfluidic chip, and wherein providing the fluid sample as input to the microfluidic passage comprises loading the fluid sample onto the microfluidic chip. In one aspect, the fluid sample comprises a fecal sample. In one aspect, the fluid sample comprises a bioreactor sample for a mammalian cell culture, a bacterial culture, a plant culture, or a soil culture. In one aspect, the fluid sample comprises a liquefied sample of food.

[0037] In one aspect, providing the fluid sample as input to the microfluidic passage comprises pumping the fluid sample through the microfluidic passage. In one aspect, the sample comprises spores and other microbes and the method further comprises activating, in a first sample run, the at least one electrode using a voltage having first characteristics prior to activating the at least one electrode to attract the spores to the surface of the at least one electrode, the first characteristics selected to selectively attract the other microbes to the surface of the at least one electrode and not attract the spores to the surface of the at least one electrode, collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores not attracted to the surface of the at least one electrode, and providing the effluent sample as input to the microfluidic passage in a second sample run, wherein activating the at least one electrode to attract the spores to the surface of the at least one electrode is performed during the second sample run. In one aspect, the method further comprises capturing, during the first sample run, at least one second image of the at least one electrode while the other microbes are attracted to the surface of the at least one electrode.

[0038] In one aspect, quantifying the amount of spores in the fluid sample is further based, at least in part, on analyzing the at least one second image. In one aspect, the method further comprises quantifying an amount of other microbes in the fluid sample based, at least in part, on analyzing the at least one second image, and determining a ratio of spores to other microbes in the fluid sample based on the quantified amount of spores and the quantified amount of other microbes.

[0039] In one aspect, quantifying the amount of spores in the fluid sample comprises detecting spores in the at least one first image based, at least in part on spore morphology. In one aspect, quantifying the amount of spores in the fluid sample comprises providing the at least one first image as input to a trained machine learning model, and detecting spores in the at least one first image based, at least in part, on an output of the trained machine learning model. In one aspect, the trained machine learning model is a neural network trained to recognize spores in an image. In one aspect, quantifying the amount of spores in the fluid sample further comprises quantifying the amount of spores in the fluid sample based, at least in part, on a statistical distribution of an area of the at least one electrode represented in the at least one first image. [0040] In some embodiments, a system for quantifying spores in a fluid sample is provided. The system comprises a microfluidic passage for receiving the fluid sample, the fluid sample comprising endospores, at least one electrode disposed in the microfluidic passage, the at least one electrode configured to attract, when activated, the spores in the fluid sample to a surface of that least one electrode using dielectrophoresis, an optical system configured to capture at least one first image of the at least one electrode while the spores are attracted to the surface of the at least one electrode, and at least one computer processor configured to process the at least one first image to quantify an amount of spores in the fluid sample.

[0041] In one aspect, the microfluidic passage is included in a microfluidic chip, and receiving the fluid sample comprises receiving the fluid sample via loading the fluid sample onto the microfluidic chip. In one aspect, the fluid sample comprises a fecal sample. In one aspect, the fluid sample comprises a bioreactor sample for a mammalian cell culture, a bacterial culture or a plant culture. In one aspect, the fluid sample comprises a liquefied sample of food. [0042] In one aspect, the system further comprise a pump configured to pump the fluid sample through the microfluidic passage. In one aspect, the sample comprises spores and other microbes and the system further comprises a controller configured to activate, in a first sample run, the at least one electrode using a voltage having first characteristics prior to activating the at least one electrode to attract the spores to the surface of the at least one electrode, the first characteristics selected to selectively attract the other microbes to the surface of the at least one electrode and not attract the spores to the surface of the at least one electrode, and an effluent fluid container configured to collect at an outlet of the microfluidic passage, effluent fluid comprising the spores not attracted to the surface of the at least one electrode, wherein the effluent sample is provided as input to the microfluidic passage in a second sample run, wherein activating the at least one electrode to attract the spores to the surface of the at least one electrode is performed during the second sample run.

[0043] In one aspect, the optical system is further configured to capture, during the first sample run, at least one second image of the at least one electrode while the other microbes are attracted to the surface of the at least one electrode. In one aspect, quantifying the amount of spores in the fluid sample is further based, at least in part, on analyzing the at least one second image. In one aspect, the at least one computer processor is further configured to quantify an amount of other microbes in the fluid sample based, at least in part, on analyzing the at least one second image, and determine a ratio of spores to other microbes in the fluid sample based on the quantified amount of spores and the quantified amount of other microbes.

[0044] In one aspect, quantifying the amount of spores in the fluid sample comprises detecting spores in the at least one first image based, at least in part on spore morphology. In one aspect, quantifying the amount of spores in the fluid sample comprises providing the at least one first image as input to a trained machine learning model, and detecting spores in the at least one first image based, at least in part, on an output of the trained machine learning model. In one aspect, the trained machine learning model is a neural network trained to recognize spores in an image. In one aspect, quantifying the amount of spores in the fluid sample further comprises quantifying the amount of spores in the fluid sample based, at least in part, on a statistical distribution of an area of the at least one electrode represented in the at least one first image. [0045] It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein. BRIEF DESCRIPTION OF THE DRAWINGS [0046] Various non-limiting embodiments of the technology will be described with reference to the following figures. It should be appreciated that the figures are not necessarily drawn to scale.

[0047] FIG. 1 schematically illustrates a system for separation, detection and/or quantification of spores in a sample, according to some embodiments of the present technology; [0048] FIG. 2 illustrates a microfluidic system for separation, detection and/or quantification of spores in a sample, according to some embodiments of the present technology;

[0049] FIG. 3 illustrates a static system for separation, detection and/or quantification of spores in a sample, according to some embodiments of the present technology;

[0050] FIG. 4 is a flowchart of a process for separating spores and vegetative cells in a fluid sample using dielectrophoresis, according to some embodiments of the present technology; [0051] FIG. 5 is a flowchart of a process for quantifying an amount of spores in a fluid sample, according to some embodiments of the present technology;

[0052] FIG. 6A illustrates a mix of endospores and vegetative cells cultured on DSM media, for use with some embodiments of the present technology;

[0053] FIG. 6B illustrates purified endospores cultured on DSM media, for use with some embodiments of the present technology;

[0054] FIG. 6C illustrates purified endospores stained with a fluorescent dye, for use with some embodiments of the present technology;

[0055] FIG. 7 A illustrates a bright field image showing endospores not being attracted to the electrode surface in the presence of an electric field, according to some embodiments of the present technology;

[0056] FIG. 7B illustrates a fluorescent image showing vegetative cells being attracted to the electrode surface in the presence of an electric field, according to some embodiments of the present technology;

[0057] FIGS. 8A-8B show images of vegetative cells, being attracted to the edges of the electrode in the presence of an electric field, according to some embodiments of the present technology;

[0058] FIGS. 8C-8D show images of plating an effluent sample containing only endospores, according to some embodiments of the present technology; [0059] FIGS. 8E-8F show images that when the effluent sample containing only endospores is processed with a microfluidic system, only endospores are attracted to the edges of the electrode in the presence of an electric field, according to some embodiments of the present technology;

[0060] FIG. 9 schematically illustrates a process for quantifying a number of spores and/or a number of vegetative bacteria in a fluid sample, according to some embodiments of the present technology;

[0061] FIG. 10 is a flowchart of a process for classifying microbes in an image captured by a microfluidic system, according to some embodiments of the present technology;

[0062] FIG. 11 illustrates an image showing both spores and vegetative cells being attracted to an electrode surface, according to some embodiments of the present technology;

[0063] FIG. 12 illustrates a grayscale image derived from the image in FIG. 11, according to some embodiments of the present technology;

[0064] FIG. 13A illustrates red, green, and blue color channel images derived from a color image, according to some embodiments of the present technology;

[0065] FIG. 13B illustrates an image in which the red and green color channel images of FIG. 13A have been recombined into a multi-channel color image, according to some embodiments of the present technology;

[0066] FIG. 14A illustrates an image in which background subtraction based on an electrode pixel value has been applied, according to some embodiments of the present technology;

[0067] FIG. 14B illustrates an image in which background subtraction based on an inter electrode space pixel value has been applied, according to some embodiments of the present technology;

[0068] FIG. 15A illustrates an image in which segmentation for spores and vegetative cells based on distinct threshold ranges has been performed, according to some embodiments of the present technology;

[0069] FIGS. 15B-15C illustrate example settings for the spores and vegetative cells threshold ranges, respectively, used to segment the image of FIG. 15 A;

[0070] FIG. 16A illustrates an image in which segmentation for spores and vegetative cells based on intensity threshold ranges on a grayscale image has been performed, according to some embodiments of the present technology; [0071] FIG. 16B illustrates example settings for the threshold ranges used to segment the image of FIG. 16 A;

[0072] FIGS. 17A-C illustrate respective hue, saturation, and value channel images, used for HSV segmentation, according to some embodiments of the present technology;

[0073] FIG. 18A illustrates an image in which segmentation for spores and vegetative cells based on HSV threshold ranges has been performed, according to some embodiments of the present technology;

[0074] FIGS. 18B-18C illustrate example settings for the spores and vegetative cells HSV threshold ranges, respectively, used to segment the image of FIG. 18A;

[0075] FIG. 19 illustrates the image of FIG. 18A after removal of unwanted objects, according to some embodiments of the present technology;

[0076] FIGS. 20A-20C illustrate images corresponding to different segmentation techniques applied to classify spores and vegetative cells, according to some embodiments of the present technology;

[0077] FIGS. 21A-C illustrate respective images with different bright field imaging intensities used to generate a training set of labeled data for a machine learning classifier, according to some embodiments of the present technology;

[0078] FIG. 22 illustrates results of validating a trained machine learning model for use in classifying spores in an image, according to some embodiments of the present technology; and [0079] FIG. 23 show a plot of time series of capturing spores and vegetative cells during an electrical sequence of a microfluidic system, according to some embodiments of the present technology.

DETAILED DESCRIPTION

[0080] Aspects of the technology described herein relate to an apparatus and methods for separating, detecting and/or quantifying biological organisms (e.g., endospores, also referred to herein more generally as “spores”) present in a fluid sample. In particular, the technology described herein provides techniques for separation, detection and/or quantification of spores in a sample using a microfluidic system comprising one or more electrodes configured to generate dielectrophoretic forces that act on the sample.

[0081] Microbial (e.g., bacterial, yeast, viral and fungal) contamination is a serious and growing global threat to human health and economic development, including pharmaceutical manufacturing and immunotherapy manufacturing and treatment. An example of a conventional technique to assess the presence and degree of microbial contamination in a sample is the Plate Counting Method (PCM). PCM typically includes at least four steps. In step 1, a sample to be analyzed is manually placed in each of multiple test tubes, and the sample in each test tube is diluted to a desired concentration using a buffer solution. In step 2, the diluted samples are plated onto petri dishes containing agar media. Petri dishes including dilution media only (i.e., without the sample) are also plated for use as controls for comparison against the plated diluted samples. In step 3, the plurality of plated samples, the dilution media plates, and empty agar plates are cultured for 24 hours to 14 days to enable microbial particles to grow on the media within the petri dishes. In step 4, the number of bacterial colonies on each of the plates cultured in step 3 is determined, for example, using a microscope.

[0082] PCM is routinely used in medical, pharmacological and food industries to identify bacterial contamination. However, PCM is slow, only moderately sensitive, labor intensive and prone to human errors. For instance, the entire PCM process takes 1-14 days, includes several manual steps in which human intervention is needed, and requires a large number of plated samples at different dilutions and controls. There is therefore a need for new technologies that allow for faster, more sensitive and/or more reliable assessment of microbial contamination in fluid samples.

[0083] Dielectrophoresis (DEP) has shown promise for particle separation; however, it has not yet been applied in clinical settings, pharmaceutical quality control, or manufacturing. For instance, only small sample volumes with unrealistically high bacterial concentrations on the order of 10³-10⁷ CFU/mL have been processed, which limits the applicability of DEP microbial capture methods. DEP particle separation has been achieved only to a limited extent and the separation is restricted to specific cell types, (e.g., separation of Escherichia coli from Bacillus subtilis). Unfortunately, separation of small cells (~lpm in diameter, the size of many bacteria) using DEP has been notoriously difficult. For instance, small bacterial particles undergo significant Brownian motion that adds a time dependent variation in their position, and thus the specificity of separation decreases for small cells, which has previously been thought to limit the applicability of the DEP technique for detecting and/or separating bacteria in a sample.

[0084] Some embodiments of the technology described herein relate to a novel DEP bacterial capture and separation technique (also referred to herein as “Fluid- Screen” or “FS”) that addresses at least some of the limitations of prior DEP techniques. [0085] Although capture and separation of bacteria from a sample is described herein, it should be appreciated that biological particles other than bacteria, for example, different cells, yeast, mold, fungus, viruses, etc. can also be detected, quantified, separated, and/or enriched using one or more of the techniques described herein. Indeed, the technology described herein has been shown to effectively capture, detect, quantify, and separate a wide range of diverse microorganisms including, but not limited to, both Gram (-) and Gram (+) bacteria, multiple bacterial morphologies, both individual bacteria and cell aggregates, yeasts or molds (including conidia, conidiophores and hyphae), and viruses. Table 1 below illustrates a summary of some microorganisms that have been successfully captured and detected using the techniques described herein.

Table 1: Example microorganisms c etected using the techniques described herein

[0086] In accordance with some embodiments, a fluid sample containing bacteria is processed in a microfluidic system that includes a microfluidic device. For example, within the microfluidic device, the sample may be subjected to DEP forces to enable separation, detection, enrichment and/or quantification of microorganisms in the fluid sample. Examples of a microfluidic system suitable for use in accordance with the techniques described herein, include the Fluid-Screen Microfluidic System, aspects of which are described in U.S. Patent Application

No. 16/093,883 titled “ANALYTE DETECTION METHODS AND APPARATUS USING DIELECTROPHORESIS AND ELECTROOSMOSIS,” filed on October 15, 2018, and U.S. Patent Application No. 14/582,525 titled “APPARATUS FOR PATHOGEN DETECTION” filed on December 24, 2014, each of which is hereby incorporated by reference in its entirety. [0087] FIG. 1 illustrates an example system 100 for detecting bacteria in a sample, in accordance with some embodiments. As shown in FIG. 1, the system 100 comprises a microfluidic device 104 in communication with a computing device 110.

[0088] The microfluidic device 104 may be any suitable device, examples of which are provided herein. In some embodiments, microfluidic device 104 is implemented as a microfluidic chip having one or more passages (e.g., microfluidic channels or chambers) through which a fluid sample 102 is provided for analysis. Although the term “microfluidic channel” or simply “channel” is used herein to describe a passage through which fluid flows through microfluidic device 104, it should be appreciated that a fluid passage having any suitable dimensions may be used as said channel, and embodiments are not limited in this respect. Microfluidic device 104 may comprise a single channel or multiple channels configured to receive a single sample 102 (e.g., to perform different analyses on the sample) or multiple channels configured to receive different samples for analysis. In embodiments having multiple channels, the microfluidic device may be configured to process the single sample or multiple samples in parallel (e.g., at the same or substantially the same time).

[0089] As described herein, sample 102 may include any fluid containing bacteria or other microorganism of interest. In some embodiments, the sample comprises a biological fluid such as saliva, urine, blood, water, any other fluid such as an environmental sample or potentially contaminated fluid, protein matrices, mammalian cell culture, immunotherapy drug product, cell and gene therapy drug product, cell and gene therapy drug sample, bacterial culture, growth media, active pharmaceutical ingredients, enzyme products, or substances used in biomanufacturing, etc.

[0090] As shown, microfluidic device 104 includes at least one electrode 106. The at least one electrode 106 may be configured to receive one or more voltages to generate positive and/or negative dielectrophoresis (DEP) force(s) that act on a sample arranged proximate to the at least one electrode. In some embodiments, the at least one electrode 106 may be configured to receive one or more voltages (e.g., one or more AC voltages) to generate at least one dielectrophoresis force that acts on the sample. The at least one DEP force may cause certain components of the sample to move relative to (e.g., be ahracted to or repulsed from) a surface of the at least one electrode 106. For example, in the absence of an electric field, bacteria and other components of the sample 102 may move freely relative to the surface of the electrode. In the presence of the electric field, at least some components (e.g., bacteria) in the sample may be attracted to the electrode surface.

[0091] The small size of bacteria presents an obstacle to optical observation and quantification of bacteria in the sample. The inventors have recognized that activation of the at least one electrode 106 results in an electric field that may be used to selectively trap bacteria on the surface of the electrode(s). When used with an optical system, capturing bacteria on the surface of the electrode(s) may prevent the bacteria from moving in and out of focus of the optical system to enable real-time bacteria detection and quantification, a process referred to herein as “on-chip quantification.”

[0092] The electric field used to capture the bacteria concentrates the bacteria, which enables imaging with fluorescence microcopy or another optical detection technique. Accordingly, bacterial capture using the techniques described herein allows for detection and quantification of bacteria at significantly lower limits compared to some conventional methods, such as the PCM technique described above. The ability to detect and/or quantify bacteria in a sample, even in small amounts, may be useful in applications including, but not limited to, biomanufacturing, gene therapy, analysis of patient samples, vaccine development and/or biothreat detection, antibiotic susceptibility testing.

[0093] For example, the at least one DEP force acting on the sample may cause bacteria (or certain bacteria) to separate from other components of the sample (e.g., via positive DEP). Bacteria in the sample may be attracted to the surface of the at least one electrode 106 allowing for enhanced detection and/or quantification, despite the small size and/or small amount of the bacteria in the sample. Although, microfluidic device 104 is illustrated as having a single electrode, it should be understood that in some embodiments, microfluidic device 104 comprises multiple electrodes arranged in any suitable configuration.

[0094] System 100 may further comprise a computing device 110 configured to control one or more aspects of microfluidic device 104. For example, computing device 110 may be configured to direct the sample 102 into a channel of the microfluidic device. In some embodiments, computing device 110 is configured to control the at least one electrode 106 to generate the at least one DEP force acting on the sample 102. In some embodiments, computing device 110 may cause one or more components of an optical system (not shown) to perform one or more of detection or quantification of the bacteria or other microorganisms in the sample. Non-limiting examples of a computing device 110 that may be used in accordance with some embodiments are further described herein.

[0095] FIG. 2 illustrates an example microfluidic system 200 for detecting the presence of microorganisms (e.g., bacteria) in a sample, in accordance with some embodiments. System 200 includes microfluidic device 208 (e.g., indicated in FIG. 2 as a microfluidic chip) that includes one or more electrodes for generating DEP forces that act on a sample 204 provided as input to the system. Sample 204 may contain microorganisms for which separation, detection, enrichment, and/or quantification may be performed. The one or more electrodes may be arranged in any suitable configuration within the microfluidic device 208. For instance, in embodiments that include multiple electrodes, the electrodes may be arranged in one-dimension along the flow direction of the fluid, perpendicular to fluid flow direction or on a diagonal relative to the fluid flow direction. In some embodiments, a multidimensional (e.g., 2- dimensional, 3 -dimensional) array of electrodes may be used. For instance, a dense array of electrodes arranged both along the direction of fluid flow and perpendicular to the direction of fluid flow may be used.

[0096] As shown in FIG. 2, a flow system 202 is provided. The flow system 202 may provide a solution for transporting the sample 204 to the microfluidic device 208. A first pump 206 may be used to pump the solution and the sample 204 to the microfluidic device 208 at a predetermined flow rate. First pump 206 may be of any suitable type. In some embodiments, first pump 206 is omitted and sample 204 is manually loaded (e.g., using a pipette or capillary flow) as input to one or more channels of microfluidic device 208.

[0097] Microfluidic device 208 is configured to receive sample 204 for processing. Microfluidic device 208 may include one or more passages through which the sample 204 flows. The one or more passages may include at least one electrode formed therein or adjacent thereto. For instance, the at least one electrode may be formed within a passage. The at least one electrode, when activated, is configured to generate an electric field that acts on the sample 204 as it flows through the one or more passages. An electrical system 212 (e.g., a signal generator or controller) is configured to provide one or more voltages to the at least one electrode of the microfluidic device 208 to tune the properties of the electric field for capture of a particular microorganism or microorganisms of interest. Further aspects of the electrical system 212, including example protocols for operating the microfluidic device 208 are provided herein. [0098] Microfluidic system 200 may include an optical system 210 to facilitate analysis of the sample 204 by performing on-chip quantification. For example, optical system 210 may comprise one or more optical sensors (e.g., a red-green-blue camera) for viewing and/or imaging the sample. The optical sensor(s) may provide for enhanced detection and/or quantification of the captured microorganisms and/or the other components of the sample 204 relative to detection and quantification techniques that require separate culturing of captured microorganisms or an effluent sample from the device. Any suitable optical sensor(s) may be used. In some embodiments, the optical sensor(s) comprises a digital camera. In some embodiments, the optical sensor(s) includes a monochrome camera having a plurality of color filters. The monochrome camera may be configured to capture a plurality of monochrome images with different color filters, and a color image may be formed based on superposition of the plurality of monochrome images. For instance, the different color filters may include a red filter and a green filter, and the color image may be a superposition of a monochrome image captured with the red filter and a monochrome image captured with the green filter.

[0099] In some embodiments, the optical sensor(s) comprises electronic sensors including CMOS compatible technology. In some embodiments, the optical sensor(s) comprise fiber optics. However, any suitable optical sensor(s) may be used. In some embodiments, bacteria in the sample are stained (e.g., with a fluorescent dye) and the optical system 210 is configured to perform microscopy (e.g., fluorescence microscopy) of captured stained bacteria. In some embodiments, optical system 210 is configured to capture one or more images (e.g., color images) of the at least one electrode while the sample is flowing through the microfluidic device 208. In some embodiments, the detector comprises nanowire and/or nanoribbon sensors. In some embodiments, the field of view of the optical system 210 at a particular magnification is insufficient to capture the entire surface of the one or more electrodes. In such embodiments, the optical system 210 may be configured to capture multiple partially overlapping images that collectively cover the entire surface of the one or more electrodes. The multiple captured images may then be analyzed to detect and/or quantify the microorganisms of interest in the sample. [00100] Microfluidic system 200 also includes computer 230 configured to control an operation of optical system 210 and/or to receive images from optical system 210 and to perform processing on the received images (e.g., to count a number of microorganisms trapped by the microfluidic device 208). In some embodiments, the received images are analyzed to determine the number of microorganisms captured by the at least one electrode. For instance, microorganisms may be identified in the received images as spots (e.g., fluorescent spots) located on the edges of the electrodes. In this way, a captured target microorganism species may be differentiated from other components in the sample that are not captured and may appear as floating above the at least one electrode or located between electrodes.

[00101] After the sample 204 is processed by the microfluidic device 208 and/or optical system 210 to capture and/or quantify microorganism immobilized on the electrode(s), the sample 204 may be removed from the microfluidic device 208. For example, a second pump 216 may be provided for pumping the sample 204 out of the microfluidic device 208. The second pump 216 may be of any suitable type. In some embodiments, microfluidic system 200 comprises a flow sensor 214 for measuring a flow rate at which the sample 204 is removed from the microfluidic device 208. The flow sensor 214 and the second pump 216 may be in communication to control a flow rate at which the sample 204 is removed from the microfluidic device 208.

[00102] As described herein, microfluidic system 200 may be used for separating bacteria from other components (or for separating certain bacteria from other bacteria) in sample 204. Microfluidic system 200 comprises a waste region 218 arranged to receive other components of the sample 204 which have been separated from the bacteria by the microfluidic device 208 and subsequently removed from the sample 204, for example, using the second pump 216. In the description below, analysis of the fluid collected in waste region 218 may be referred to as analysis of the “effluent sample.” Microfluidic system 200 may further include effluent region 220 for receiving a purified version of sample 204 containing substantially only target microorganisms that were captured using microfluidic device 208.

[00103] In some embodiments, an amount of time needed to process a sample using microfluidic system 200 is substantially less than an amount of time required to process a sample using a conventional PCM sample processing system. As shown in FIG. 2, processing a sample using system 200 may include at least three steps. In step 250, a sample is provided as input to microfluidic system 208 and bacteria are captured from the sample in the presence of an applied electric field. In step 260, automated on-chip quantification is performed, for example, using computer 230 to analyze one or more images recorded by optical system 210. In step 270, further analysis may be performed on waste 218 and/or effluent sample 220, as desired. In sum, the entire process for detecting and/or quantifying microorganisms in a sample using system 200 may take on the order of minutes or an hour to a few hours, which is substantially faster than the multiple days (e.g., 1 to 14 days) typically required to process samples using PCM.

[00104] In some embodiments, rather than pumping sample 204 through one or more passages through which the sample flows, sample 204 may be manually provided as input to microfluidic device 208 for analysis. For instance, one or more droplets of sample 204 may be provided as input to microfluidic device 208 using a pipette or other suitable technique. In such embodiments, the sample is analyzed in a “static” condition rather than in a condition in which microorganisms are captured by the at least one electrode as the sample flows past the electrode(s) (e.g., as in the case of microfluidic system 200 as shown in FIG. 2). FIG. 3 illustrates a microfluidic system 300 for detecting microorganisms in a sample, according to some embodiments. As shown, microfluidic system 300 may include many of the same components as microfluidic system 200, but may omit certain components of the microfluidic system 200, such as the first pump 206, which are not needed when the sample is manually provided as input to the microfluidic device 308 (indicated in FIG. 3 as a static microfluidic chip).

[00105] Microfluidic systems used in accordance with some embodiments of the present technology provide a precise and rapid system for qualitative and/or quantitative differentiation between spores and other organisms (e.g., vegetative bacteria). This differentiation may be based on measurements obtained from a single organism (e.g., bacteria, virus, fungi, yeast, etc.) or from a mix of organisms. Such measurements may provide information useful in quality assurance, product sterility and biomanufacturing processes, among others. For example, pharmaceutical companies which are developing drugs in the microbiome space may use one or more of the techniques described herein to perform quality control of manufacturing.

[00106] Existing techniques for detecting spores in fluid samples (e.g., water and other fluids) may be inefficient in several ways including, but not limited to, their inability to detect low levels of spores and/or their inability to culture certain types of microorganisms. In some instances, existing detection methods may take days to provide results. While faster methods such as quantitative polymerase chain reaction (qPCR) can reduce the response time to a few hours, such methods require complex sample preparation, high costs, have limited portability, and cannot be used for process streamlining.

[00107] Some embodiments described herein relate to techniques for rapid detection, trapping/capture, purification, separation and/or quantification of bacterial spores (e.g., endospores) from vegetative bacteria using a system of electrodes configured to generate positive DEP forces, negative DEP forces and/or electroosmosis forces in a microfluidic device. The techniques described herein may be implemented using a microfluidic system (e.g., the microfluidic systems described in FIGS. 1-3). For example, as described above, the microfluidic system may control particle motion in a fluid by dielectrophoresis (DEP), which describes the motion of all particles in a non-uniform electric field gradient. Using DEP, spores and other cells can be captured on a surface of one or more electrodes used to generate an electric field having particular characteristics. The capture can be universal, capturing all particles within a range of sizes, or selective for a singular particle type, depending on the tuning of the electric field characteristics (e.g., amplitude, frequency) applied. The electrode(s) of the microfluidic system may be specially designed to maximize bacterial response to the electric field. In some embodiments, the techniques may be automated. In some embodiments, the techniques may be performed rapidly (e.g., 30 minutes or less).

[00108] FIG. 4 illustrates a process 400 for separating spores from vegetative bacteria in a fluid sample in accordance with some embodiments. In act 410, the fluid sample may be provided as input to a microfluidic passage of a microfluidic device. As described in more detail below, the fluid sample may contain vegetative bacteria (e.g., B. subtilis) and endospores. Process 400 then proceeds to act 420, where one or more electrodes disposed within and/or adjacent to the microfluidic passage are activated to separate spores and vegetative bacteria in the fluid sample based on a dielectrophoretic (DEP) force generated within the microfluidic passage. For instance, the properties (e.g., frequency) of the electric field may be tuned such that a positive DEP force causes the vegetative bacteria to be selectively attracted to the edges of the at least one electrode, while not attracting the spores to the edges of the at least one electrode. In some embodiments, the voltage applied to the one or more electrodes is sufficiently high (e.g., greater than or equal to 40 V) to cause the vegetative cells to permanently adhere to the surface of the electrode(s). In other instances, the electric field may be tuned such that a positive DEP force causes the spores to be attracted to a surface of the at least one electrode, while not attracting the vegetative bacteria to the electrode surface. In yet further instances, the electric field may be tuned such that both of the vegetative bacteria and the spores are initially attracted to the surface of the one or more electrodes and one or more properties of the electric field may then be changed to release one of the vegetative bacteria or the spores from the surface of the one or more electrodes. Non-limiting examples of separating spores and vegetative bacteria using a microfluidic system in accordance with some embodiments are discussed in more detail below.

[00109] FIG. 5 illustrates a process 500 for separating and quantifying spores in a complex sample in accordance with some embodiments. In act 510 the sample is provided as input to a microfluidic passage (e.g., a microfluidic passage included within a microfluidic device, examples of which are shown in FIGS. 2 and 3). Process 500 then proceeds to act 512, where one or more electrodes of the microfluidic device are activated to attract spores to the surface of the electrode(s) using positive dielectrophoresis. As described in some of the examples below, a fluid containing only spores may be provided by first separating the spores from vegetative bacteria in the sample in a first run through a microfluidic device, and collecting an effluent fluid that contains only spores. The fluid with the spores may than be processed in a second run during which the spores are attracted to the surface of the electrode(s) using dielectrophoresis. Process 500 then proceeds to act 514, where one or more images of the electrode surface are captured while the spores are attracted to the electrode surface. Process 500 then proceeds to act 516, where the amount of spores in the sample is quantified based on an analysis of the captured image(s). Below are provided some non-limiting examples of implementing processes 400 and 500 with different types of samples.

Protocols and sample generation

[00110] Bacterial endospores used in the example experiments described below were suspended/diluted in a sterile phosphate buffered saline (PBS) pH 7.4 without calcium chloride and magnesium chloride (Life Technologies, USA) and diluted 1:1000 with UltraPure Distilled Water (DI water, Life Technologies, USA). The conductivity of the PBS 1:1000 in DI water was in the range 19-23 pS/cm and was measured at room temperature (RT) using pH/mV/conductivity meter Accumet® XL200. Aliquots of diluted PBS were stored at 4°C. [00111] A Difco Sporulation Media (DSM) containing 8g per liter of Nutrient Broth (Difeo, USA) was suspended in 1 L of UltraPure DI water and was supplemented with 1 rnL of 1M MgSOr (Sigma, USA). After autoclaving sterile 1 mL of 10 mM MnCh (Sigma, USA), 0.5 rnL of 1 M CaCl (Sigma, USA) and 1 L of freshly prepared 1 M FeSOr (Sigma, USA) was used. [00112] To generate the bacterial endospores, Bacillus subtilis subsp. subtilis (6051) was obtained from ATCC and was used to grow spores. Briefly, endospores were prepared by growing of B. subtilis in Lysogeny Broth (LB) overnight at 37°C. The following day, the culture was diluted in fresh LB to an Oϋboo of around 0.1-0.2 in 10 mL of LB and was grown at 37°, 200 rpm. When bacteria reached Oϋboo 0.8 OD, the bacteria was spun down at 13,000 x g for 1 min, at room temperature (RT). The bacterial pellet was washed with PBS pH 7.4 without calcium chloride and magnesium chloride and was then re-suspended in DSM. Endospores were grown for 48-72 hr at 30°C, 200 rpm then purified. Before purification, endospores generation was confirmed by differential staining with malachite green and safranin (the Schaeffer-Fulton method) to distinguish between the vegetative cells and the endospores.

[00113] Endospore staining was performed with lipophilic dye FM 4-46 (N-(3- Triethylammoniumpropyl)-4-(6-(4-(Diethylamino) Phenyl) Hexatrienyl) Pyridinium Dibromide). FM 4-64 dye is a lipophilic styryl compound used to label (by incorporation) plasma and vacuolar membranes with red fluorescence (Ex/Em maxima -515/640 nm). To selectively visualize B. subtilis endospores, bacteria were cultured as described above. When bacteria reached Oϋboo 0.8 OD, the bacteria was spun down at 13,000 x g for 1 min, RT. The bacterial pellet was washed with PBS pH 7.4 without calcium chloride and magnesium chloride and was then re-suspended in DSM supplemented with 0.5 pg/mL of FM 4-64. Endospores were grown for 48-72 hr at 30°C, 200 rpm were then purified.

[00114] To purify the endospores, a mix of vegetative cells and endospores were spun down at 13,000 x g for 1 min, in RT and re-suspended in 5 mL of ice cold UltraPure DI water. The spinning down and re-suspend g steps were repeated 6 times. After final centrifugation, endospores were re-suspended in ice cold UltraPure DI water, filtrated through 1.2 pm membrane and stored in 4°C. The purified endospores with or without FM 4-46 labeling were used in the examples provided below.

[00115] To prepare a rmcrobiome drug sample solution, the content of one pill was dissolved in PBS 1: 1000 in DI water. The sample was incubated at RT and mixed occasionally by inverting until the entire content of freeze-dried bacteria/endospores had been reconstituted. To confirm full reconstitution and the total number of growing bacteria/endospores in cfu/mL, the sample was plated on selective agar medium.

[00116] A fecal sample was prepared using the Stomacher® 400 Circulator according to manufacturer protocol. All work involving bacteria or endospores handlings were performed in Class II biosafety cabinet.

Example 1: Detection ofB. subtillis endospores by dielectrophoretic forces (pDEP)

[00117] In this example, it was shown that endospores suspended in tested buffer responded to electric field by analogy to the vegetative bacteria. To induce sporulation, B. subtilis was cultured in DSM media for 72 hr. Endospore growth and purification was determined by the Schaeffer-Fulton and FM 4-64 staining, as shown in FIGS. 6A-6C. FIG. 6A shows a mix of vegetative bacteria (red-ish) and endospores (green) stained with malachite green and safranin (the Schaeffer-Fulton method), arrows indicate endospores. FIG. 6B shows purified endospores, with the arrows indicating endospores. FIG. 6C shows purified endospores stained with fluorescent dye FM 4-64. Each red dot (an example of which is pointed to by an arrow in the figure) represents a single endospore.

[00118] The mix of vegetative bacteria and endospores (without FM 4-64) was stained with SybrGreen I and after 30 minutes of incubation in darkness, the sample was loaded onto the static microfluidic device shown in FIG. 3. A voltage having particular amplitude and frequency characteristics was applied to the electrodes to generate an electric field having a positive DEP force on the vegetative bacteria in the sample. As shown in FIG. 7 A, in the presence of the electric field, the unstained endospores (arrows) were not attracted to the electrode surface. By contrast, as shown in FIG. 7B, the fluorescently-labeled vegetative bacteria (arrows) were attracted to the edges of the electrode based on the positive DEP force, when the electrode was activated. Accordingly, the results of this example demonstrate that the endospores, due to having a dissimilar chemical structure of cortex and coat relative to bacterial cell walls, respond differently to the applied electric field than vegetative bacteria, and as such can be separated from the vegetative bacteria using the techniques described herein.

Example 2: Endospore separation from vegetative bacteria on microfluidic flow chip [00119] In this example, it was shown that endospores can be separated from vegetative bacteria suspended in a buffer solution. The mix of vegetative bacteria and endospores (without FM 4-64) were stained with SybrGreen I and after 30 minutes of incubation in darkness, the sample was run through the flow-based microfluidic chip (e.g., the microfluidic system shown in FIG. 2). A voltage having particular amplitude and frequency characteristics was applied to the electrodes to generate an electric field having a positive DEP force on both the vegetative bacteria and the endospores in the sample as the sample flowed past the electrodes. As depicted in FIG. 8A, a 60x bright field image shows that vegetative cells are captured at the edges of the electrode in the presence the electric field. In a 60x fluorescent image, FIG. 8B shows that vegetative B. subtilis bacteria stained with SybrGreen I are also captured on the edges of electrodes in the presence of the electric field. Electrical conditions were then changed (e.g., the frequency of the applied signal was changed), such that only endospores and not vegetative bacteria were released from the electrodes and captured in effluent fluid at the output of the microfluidic device. The collected effluent containing only endospores was divided into two subsamples analysed on agar plates as shown in FIGS. 8C-D (dilution 10° and 10⁴, respectively). The collected effluent fluid was then loaded on the microfluidic device (e.g., the microfluidic device shown in FIG. 3). As shown in FIGS. 8E (bright field) and 8F (fluorescence), images taken when the electric field was generated, confirm that only spores (arrows) are captured on the edges of the electrode. In this example, it was demonstrated that endospores, because of a dissimilar chemical structure of cortex and coat relative to vegetative bacterial cell walls, respond differently to the electric field than vegetative bacteria. These unique structural properties allow rapid separation of endospores from vegetative bacteria in accordance with the techniques described herein.

Example 3: Detection, separation and quantification of endospores in microbiome medicine [00120] In this example, it was demonstrated that by using pDEP in accordance with the techniques described herein, it was possible to capture on a microfluidic chip, all bacteria and endospores derived from a single pill suspended in a buffer solution. FIG. 9 schematically illustrates a process for separating and quantifying vegetative bacteria and endospores in sample in accordance with some embodiments. In act 910, the pill suspension containing both vegetative bacteria and endospores was stained with SybrGreen I dye and after 30 minutes of incubation in darkness, the sample was loaded onto a microfluidic device (e.g., the microfluidic device shown in FIG. 3). In act 920, a voltage having particular amplitude and frequency characteristics was applied to the electrodes to generate an electric field having a positive DEP force that selectively acted on the vegetative bacteria but not the endospores in the sample, resulting in the vegetative bacteria being captured by the electrodes but not the endospores, which flowed past the electrodes and were collected in an effluent solution 930. As shown, the vegetative bacteria attracted to the surface of the electrodes in act 920 may be quantified by capturing one or more fluorescent images of the electrodes. The effluent solution 930 containing only endospores and was then further analysed in act 940 using another microfluidic device to capture the endospores in the effluent solution on the surface of one or more electrodes. As shown, the endospores attracted to the surface of the electrodes in act 940 may be quantified by capturing one or more images of the electrodes, which may be subjected to automated counting techniques, examples of which are described herein. Additionally, or alternatively an amount of endospores in the effluent fluid may be quantified by plating the effluent fluid on selective agar media. In this example, it was demonstrated that using the techniques described herein, a pDEP force could be used to detect, separate and quantify the total number of vegetative bacteria and endospores in a single pill of microbiome medicine.

Example 4: Detection of spores in fecal sample

[00121] In this example, it was demonstrated that spores suspended in a buffer solution and spiked to the fecal sample prepared in Stomacher® 400 Circulator according manufacture protocol responded to an applied electric field by analogy to the bacteria. In this example, a fecal sample containing spores was loaded to the chip and visualized using a microfluidic system (e.g., the static microfluidic chip in FIG. 3). As observed in other examples, when a certain voltage and frequency were used, spores responded to the electric field and were forced from any area of chip to the edges of electrodes in a manner characteristic to the applied pDEP force. The electrodes having the spores captured thereon were imaged and the amount of captured spores were automatically quantified using the techniques described herein. Following quantification of the spores, the electrodes were deactivated, resulting in the electric field being turned off, after which the spores were released from edges of electrodes for further analysis. In this example, it was shown that the spores in an analysed fecal sample responded to the electric field and were acted upon by dielectrophoretic force.

Example 5: Detection of endospores as a contaminates in bioreactors for mammalian cell, bacterial and plant culture

[00122] In this example, it was demonstrated that: (i) endospores suspended in mammalian cell culture medium (processed medium), bacterial cultured medium (any broth), and plant culture medium/inoculation in mist bioreactors respond to electric field as described in Example 1; (ii) the techniques described herein are suitable to detect endospore contamination of mammalian cell, bacterial or plant culture regardless of the scale/volume of culture and significantly less labor/time consuming compared to standard microbiology methods.

[00123] Media (as described above in the Protocols and sample preparation section) was provided being spiked with endospores, which were stained with SybrGreen I to distinguish from mammalian and bacterial cells, and any other culture debris. After 30 minutes of incubation in darkness, the sample was loaded onto a microfluidic system (e.g., the microfluidic system in FIG. 3) and visualized. When a certain voltage and frequency for capturing endospores was applied to the electrodes, endospores in the sample responded to the electric field in a characteristic manner as previously observed in Example 1. In the presence of the electric field, the endospores were forced from other areas of chip to the edges of electrodes demonstrating the characteristic response of the endospores to the applied pDEP force. The endospores were automatically quantified based on one or more images captured while the endospores were attracted to the surface of the electrodes. By analogy to the Example 1, when the electric field was switched off, endospores were released from edges of electrodes for further analysis. In this example, it was shown that the endospores, despite different chemical structure of cortex and coat than bacterial cell walls, respond to the electric field and undergo dielectrophoretic force similar to bacteria.

Example 6: Detection of endospores as a contaminates in bioreactors for microbiome drug manufacturing

[00124] In this example, (i) endospores suspended in microbiome drug in bioreactors respond to electric field as described in Example 1; (ii) the techniques described herein are suitable to detect endospore contamination of microbiome drug manufacturing regardless of the scale/volume of culture and significantly less labor/time consuming compared to standard microbiology methods.

Example 7: Detection of endospores as a food contamination/poisoning [00125] In this example, it was demonstrated that food poisoning-spores suspended in a buffer and spiked in liquefied samples of food in a buffer responded to electric field by analogy to the bacteria used in other examples. A Sample containing food poisoning-spores were loaded onto a microfluidic device (e.g., the microfluidic device shown in FIG. 3). When a voltage having certain characteristics (e.g., amplitude and frequency) was applied to the electrodes of the microfluidic device, the food poisoning-spores responded to the electric field in a characteristic manner as previously observed in other examples for bacteria. By forcing the food poisoning- spores from other areas of the microfluidic chip to the edges of electrodes the characteristic response of the endospores to the pDEP force was shown. The food poisoning spores were automatically quantified based on one or more images captured while the spores were attracted to the surface of the electrodes. When the electric field was turned off, the food poisoning-spores were then released from the edges of electrodes for further analysis (e.g., PCR and/or sequencing). In this example, it was shown that food contaminated with poisoning-spores in analysed liquefied of a sample of food responds to an electric field and an applied dielectrophoretic force, which enables the amount of poisoning spores to be accurately quantified in accordance with some embodiments. [00126] In the preceding sections, techniques for separating, detection and quantifying spores in a sample containing spores and vegetative cells have been described. Rather than separating spores and vegetative cells prior to imaging the surface of the electrode(s) configured to capture particles, a microfluidic device may be configured to use dielectrophoresis to capture both spores and vegetative cells on the surface of one or more electrodes. An image of the surface of the electrode(s) having both spores and vegetative cells attracted thereto may they be captured and analyzed to classify microbes in the image as being of a first type (e.g., spores) or of a second type (e.g., vegetative cells). Accordingly, some embodiments are directed to techniques for automated detection and classification of multiple, morphologically distinct types of microbes in microscope images.

[00127] In the example techniques described below, differentiation of Bacillus subtilis endospores from vegetative cells is described. However, it should be appreciated that the techniques described herein may be applied to any image containing multiple types of microbes that can be morphologically distinguished. For instance, some embodiments are configured to distinguish between multiple types of microbes based on different sizes, shapes, colors, brightnesses, among other distinctions.

[00128] FIG. 10 illustrates a process 1000 for distinguishing microbes in an image captured by a microfluidic system in accordance with some embodiments. In act 1010, an image of a surface of one or more electrodes of the microfluidic system (e.g., microfluidic systems as shown in FIGS. 2 and 3) is received. For instance, as described in the examples above, the microfluidic system may be configured to generate a positive dielectrophoretic force that results in two or more types of microbes (e.g., spores and vegetative bacteria) to be attracted to the surface of the electrode(s). While the microbes are attracted to the electrode surface, one or more images of the electrode surface may captured by an optical system of the microfluidic system. Such an image may be received in act 1010 by a computing device (e.g., computing device 110, computer 230, computer 330) for analysis.

[00129] FIG. 11 illustrates an example of an image in which B. subtilis endospores and vegetative cells are shown as being captured on an electrode of a microfluidic device due to positive dielectrophoresis, in accordance with some embodiments. As shown the spores are visible as the small black circles and the vegetative cells are the fainter lighter objects. The dark bands are the electrodes of the microfluidic system. The image shown in FIG. 11 was obtained at 60x magnification, however, it should be appreciated that the image analysis techniques described herein are not limited to any specific type of image capture setup.

[00130] Process 1000 then proceeds to act 1012, where the image captured by the optical system of the microfluidic system may be pre-processed. The inventors have recognized that in certain cases it may be challenging to obtain a satisfactory image segmentation using the original unprocessed “raw” captured image. Accordingly, in some embodiments, one or more pre-processing techniques may be performed to enhance the ability to automatically detect objects in the image and classify them correctly using the techniques described herein. The images obtained by one or more of the pre-processing techniques described below may serve as a useful starting point for image segmentation or other forms of analysis, examples of which are discussed below. Any suitable number of pre-processing techniques may be used. It should be understood, however, that in some embodiments, pre-processing may not be performed, and segmentation may be performed on the unprocessed image.

[00131] Examples of pre-processing techniques that may be used in accordance with some embodiments include, but are not limited to, grayscale conversion of a color image, removal of one or more color channels of a color image, and background subtraction. A color image may be subjected to pre-processing by converting the color image into a grayscale image. FIG. 12 shows an example of a grayscale image generated from the color image shown in FIG. 11.

[00132] Additionally or alternatively, color images may not contain useful information in all of their color channels (e.g., red, green and blue). In such cases, it may be beneficial to remove color channels that have less useful information. This may be accomplished, for example, by first separating the color image into its respective color channels, and subsequently recombining only a subset of the color channels. FIG. 13 A shows an example in which the color image of FIG. 11 is divided into red (left), green (middle) and blue (right) color channel image. In some instances it has been shown that neither endospores nor vegetative cells are clearly visualized in the blue channel compared to the red and green channels. Accordingly, in some embodiments, the blue channel of the color image may be removed during pre-processing, and the red and green color channel images may be recombined to produce the image shown in FIG. 13B. As shown in the modified image of FIG. 13, by discarding the blue channel information, the microbes in the image appear more distinctly compared to the original image in FIG. 11.

[00133] Additionally or alternatively, an image may be pre-processed by using background subtraction. In performing background subtraction, the ‘zero’ intensity level of the pixel data encoded in an image is redefined based on the image background and subtracting all pixel intensities by zero intensity value. The result of performing background subtraction is an image in which (typically) the darkest region of the original image becomes black and all other pixels in the image are scaled accordingly. In some embodiments, the pixel value assigned to the electrodes themselves are defined as the background zero intensity value. Using the pixel value assigned to the electrodes as the zero intensity value tends to make all pixels in the image darker as shown in FIG. 14A. In other embodiments, the pixel value for the inter-electrode space (space between the dark electrodes) is defined as the redefined zero intensity level. Using the pixel value for the inter-electrode spaces as the zero intensity level tends to remove the microchip features from the image, as shown in FIG. 14B, which may be useful for classifying images containing certain types of microbes.

[00134] Returning to process 1000, following optional pre-processing in act 1012, process 1000 proceeds to act 1014, where the image is segmented to detect first microbes and second microbes in the image. Image segmentation partitions the image into sections based on one or more criteria. The sections of the image generated from the segmentation may include the microbes desired to be detected, quantified, and measured in accordance with the techniques described herein. For clarity, the example segmented images shown in FIGS. 15-19 all use the original unprocessed image in FIG. 11 as its starting point. However, a gallery of each technique applied to each of the pre-processing techniques described herein is also provided in FIGS. 20A- 20C. In each example, light colored objects were detected as subtilis spores while dark colored objects were detected as subtilis vegetative cells.

[00135] Color images may contain unique information in each of their color channels (e.g., red, green, blue), as discussed above. Accordingly, in some embodiment an image is segmented by defining intensity ranges for each of the three channels, and determining whether a detected object in the image falls within the defined intensity ranges for one or more of the color channels. In some embodiments, an object may only be detected as a spore or a vegetative cell if it falls into the specified ranges for all of the color channels (e.g., red, green, and blue). Because vegetative cells may be distinct in color from spores in the image, separate thresholds may be set for each type of microbe for segmentation, which results in classification of the microbes as the output of the segmentation. FIG. 15 illustrates an example image in which cells and spores have been classified based on color channel thresholds in accordance with some embodiments. FIG. 15B illustrates example red, green, and blue channel threshold ranges that may be set for determining a microbe in the image to be classified as a spore. FIG. 15C illustrates example red, green, and blue channel threshold ranges that may be set for determining a microbe in the image to be classified as a vegetative cell.

[00136] In some embodiments, segmentation may be performed on a grayscale image. In such embodiments, distinct (e.g., non-overlapping) intensity phases may be defined for each microbe provided that the different types of microbes are of different brightness in the grayscale image. FIG. 16A illustrates an image in which spores and vegetative cells are classified based on a grayscale image using different intensity phases defined for each type of microbe. FIG. 16B illustrates example intensity thresholds that may be used to classify spores and vegetative cells from a grayscale image in accordance with some embodiments.

[00137] In some embodiments, rather than separating a color image into color channels, each pixel in a color image may be represented using a hue, saturation, and value (HSV) representation. Hue is an angular dimension with red, green and blue equally spaced around a color wheel at 120° increments. Saturation describes the intensity of the color, ranging from washed out and ‘grayish’ to vibrant. Value describes the lightness or darkness of the shade. Decomposing the example image shown in FIG. 11 into an HSV representation results in the images shown in FIGS. 17A (hue), 17B (saturation), and 17C (value). Similar to setting color channel thresholds as discussed in connection with FIGS. 15A-15C, ranges for hue, saturation and value may be determined to define the regions of the image to be segmented. For different types of microbes that can be distinguished in HSV space, the microbes can be classified using segmentation in accordance with the techniques described herein. FIG. 18A shows an example image in which vegetative cells and spores have been classified based on hue, saturation, and value threshold ranges. FIG. 18B shows example hue, saturation, and value (intensity) threshold ranges that may be used in some embodiments for classifying a microbe in an image as a spore. FIG. 18C shows example hue, saturation, and value (intensity) threshold ranges that may be used in some embodiments for classifying a microbe in an image as a vegetative cell.

[00138] Returning to process 1000, after the image has been segmented, process 1000 proceeds to act 1016, where each detected microbe in the image is classified as being of a first type (e.g., spore) or a second type (e.g., vegetative cell). As described above, in some embodiments, performing segmentation in act 1014 results in classification also being performed (e.g., using color, intensity, or some other threshold ranges that distinguish between the different types of microbes). In such embodiments, acts 1014 and 1016 are collapsed into a single act in which segmentation and classification are performed simultaneously. In other embodiments, classification may be performed as a separate step following segmentation. In such embodiments, microbes in the image may be classified using one or more morphological differences between the microbes. For example, if one type of microbe is consistently larger, longer, thicker, rounder, straighter, etc., this knowledge about the morphology of the microbes may be used to define classifiers to distinguish the different types of microbes represented in the image. In some embodiments, automated computational methods are used to divide the population of microbes along axes of measurement variance used for classification. Example computational methods include, but are not limited to, principal component analysis or singular value decomposition, and clustering-based approaches, such as k-means clustering.

[00139] After classifying the detected microbes as being of a first type or a second type, process 1000 proceeds to act 1018, where a result of classifying the microbes as being of the first type or the second type is output. The result of classifying may be output in any suitable way. For instance, an image such as those illustrated herein may be output. In some embodiments, no image may be output, and instead the number of microbes of the first type (e.g., spores) and/or the number of microbes of the second type (e.g., vegetative cells) may be quantified using one or more of the techniques described herein, and the output of the quantification may be provided to a user of the microfluidic system. In some embodiments, the number of microbes of a particular type (e.g. spores) may be compared to a threshold value, and an alarm may be output when the detected number of microbes of the particular type is greater than the threshold value. Other types of output are also contemplated, and embodiments are not limited in this respect.

[00140] Even with optimized segmentation parameters, unwanted objects may be included in the set of detected microbes. For example, dust, debris, and features of the microchip itself may falsely be detected as microbes. In some embodiments, such unwanted objects are removed by defining suitable filters for one or more characteristics of microbes represented in the image. For instance, the characteristics may include morphological characteristics including, but not limited to, size and/or shape of the microbe, a number of contiguous pixels representing the microbe in the image (e.g., the area of the microbe), a circumference of the microbe, a diameter of the microbe, an extent of the microbe, or a bisector of the microbe. In some embodiments, a shape of a microbe may be determined, at least in part, based on an aspect ratio, an elongation value, a convexity value, a shape factor and/or a sphericity value of the object in the image. In some embodiments, a detected object may be required to satisfy all of a set of morphological characteristics to be classified as a particular type of microbe.

[00141] In one non-limiting example of applying a morphological filter, lines traced along the electrode edges may be included as unwanted objects during segmentation. Since the lines representing the electrode edges are relatively thin compared to the actual microbes in the image, a width threshold may be set to filter out all objects with a small diameter (e.g., objects having a diameter less than three pixels).

[00142] FIG. 19 shows an example of using HSV segmentation as described above in connection with FIGS. 18A-B followed by application of the diameter filter described above. Automated spore quantification using the image in FIG. 19 obtained a spore count (light objects) of 147. For comparison, three independent manual counts performed by separate individuals obtained 145, 162, and 127 spores. Deleting the set of detected objects and re-running the detection three separate times without changing any of the parameters for segmentation or filtering yielded exactly 147 detected spores each time.

[00143] FIGS. 20A-20C show a gallery of segmented images in which different segmentation techniques described herein have been applied at different starting points. FIG. 20A shows color channel segmentation in which different pre-processing techniques may have also been applied prior to segmentation (original image - left; red-green channels only - 2^nd from left; background subtraction on electrodes - 2^nd from right; background subtraction on inter-electrode space - right). FIG. 20B shows grayscale segmentation in which different pre-processing techniques may have also been applied prior to segmentation (original image - left; red-green channels only - 2^nd from left; background subtraction on electrodes - 2^nd from right; background subtraction on inter-electrode space - right). FIG. 20C shows HSV segmentation in which different pre processing techniques may have also been applied prior to segmentation (original image - left; red-green channels only - 2^nd from left; background subtraction on electrodes - 2^nd from right; background subtraction on inter-electrode space - right).

[00144] In some embodiments, classifying microbes in an image in act 1016 of process 1000 may be performed, at least in part, by providing an image and/or one or more features of the image as input to a trained statistical learning model (e.g., a trained machine learning model). Described in more detail below is an example of a technique for training and applying a trained machine learning model to classify spores in an image in accordance with some embodiments. [00145] In the example described herein for performing spore quantification, B. subtilis spores are detected using bright field imaging and a trained machine learning model. A spore image data training set was generated using unpurified B. subtilis spore culture. The mixed sample was incubated with SYBR Green, to differentiate B. subtilis vegetative cells from spores. Images were acquired using a microfluidic system (e.g., the microfluidic system shown in FIGS. 2 or 3). Images were acquired at three different bright field light intensities and three different sample dilutions, to generate a high level of variability for training the spore detection machine learning model. The three different bright field imaging intensities are shown in FIGS. 21A-C recorded at different exposure times 100ms (FIG. 21 C), 200 ms (FIG. 21B), or 300 ms (FIG.

21 A). The bottom images in FIGS. 21 A-C are zoomed in from the box displayed in the full spiral electrode displayed in the upper images. All three images are from a lOx diluted unpurified B. subtilis spore sample captured at 1 MHz, 20 Vpp on an IMT F35NPS microfluidic device. High, medium, and low bright field intensity images were acquired using a 40x objective at 100 ms, 200 ms, or 300 ms exposures, respectively. Bright field imaging is represented in gray while the SYBR Green signal is represented in green (for 200ms, 300 ms images).

[00146] The spores in the images were manually labelled to generate the training data set used to train the machine learning model. Following training of the machine learning model, accuracy of the model was validated. Three B. subtilis spore images were processed using the trained machine learning model. FIG. 22 shows results of validating the trained machine learning model. The bottom images in FIG. 22 are zoomed in from the box in the full spiral electrode image shown in the top images of FIG. 22. The left and center images are from a lOx diluted unpurified B. subtilis spore sample imaged at 200s bright field exposure and the right image is an undiluted sample imaged at 300 ms bright field exposure. All cells were captured at 1 MHz, 20 Vpp on an IMT F35NPS microfluidic device and imaged with a 40x objective.

Bright field imaging is represented in red, the SYBR Green signal is represented in green as indicated, and detected spores are labelled in blue as indicated.

[00147] In this example, it has been demonstrated that machine learning can be successfully trained to detect spores from vegetative cells or other objects in an image (e.g., debris). In some embodiments, additional images at different sample dilutions may be added to the training set, and additional dilutions may be used to the test the trained machine learning model. Purified B. subtilis spore images may also be added to the training or testing data sets. An acceptable range of error in spore detection may be defined for the machine learning models configured to perform spore detection and quantification.

[00148] In some embodiments, rather than capturing an analyzing a single image, multiple images may be captured as the electrode(s) in a microfluidic system (e.g., the microfluidic system shown in FIG. 2 or 3) are controlled in an electrical time sequence. In such an example, a mixed population containing both vegetative cells and endospores of B. subtilis was flowed through a microfluidic device (e.g., the microfluidic device shown in FIG. 2). An electrical sequence was applied and microscope imaging was obtained during the electrical sequence as a video revealing microbial capture by the microfluidic system in real-time. The electrical sequence was designed with four distinct phases, each lasting approximately 20 seconds:

1. RF Off: No attraction, all microbes flow by the electrodes

2. Specific capture of vegetative cells (spores flow by): voltage applied - 10MHz, 25Vpp

3. Vegetative cells and spores both captured: voltage applied - 1MHz, 25Vpp

4. RF Off: No attraction, all microbes released from the electrodes

[00149] Each frame of the video was processed using one or more of the image analysis techniques described herein. Briefly, the computational approach takes advantage of the fact that vegetative cells are a different color (yellow) compared to endospores (brown). By performing two separate segmentations in these color regimes, separate counts for the endospores and the vegetative cells was obtained, as shown in FIG. 19. As discussed previously, a morphological filter on object size was used to exclude unwanted objects associated with the electrode edges. [00150] By applying the above technique to each frame of a video accompanying the capture sequence, counts for endospores and vegetative cells within each frame was determined, enabling quantification of the capture dynamics as separate time series for the two populations of microbes as shown in FIG. 23. Specifically, FIG. 23 illustrates a separate time series for B. subtilis endospores and vegetative cells. In a first time period, no electric field is applied and both species flow through the microfluidic passage without being captured. In a second time period, a 10MHz electric field causes specific accumulation of vegetative cells on the electrode surface as the spores are not captured. In a third time period, a 1MHz electric field attracts both vegetative cells and spores to the surface of the electrode, observed as a sharp increase in the captured population. In a fourth time period, the electric field is turned off and most of the microbes are released from the electrode surface, though a few remain due to non- dielectrophoretic interactions. [00151] Quantification of spores showed favorable agreement with manual enumeration on a (static) test image (Automated count = 147 c.f. manual count = 144±17, mean ± standard deviation of three independent counts). In some embodiments, a Watershed technique may be implemented, which is specifically suited to handle groups of objects that are adjacent to one another (e.g., the clusters of particles in FIG. 19). The direction of change in the vegetative cell time series provides meaningful information and, despite the noise present in the signal, clearly reflects the dynamics of capture and release observed in the time sequence of images captured during the electrical sequence.

[00152] Noise in both time series may be driven by errors in automatic detection as objects move across the microscope’s field of view. As described above, some embodiments replace the deterministic classification process with a machine learning approach which would instead describe the probability of a given object being a vegetative cell or endospore. Such an approach may be better equipped to handle the dynamic appearance of objects as they move around in the time sequence of images.

[00153] Having thus described several aspects and embodiments of the technology set forth in the disclosure, it is to be appreciated that various alterations, modifications, and improvements will readily occur to those skilled in the art. For example, while aspects of the present technology relate to an apparatus and methods for separation, detection and/or quantification of spores in a fluid sample as described herein, the inventors have recognized that such apparatus and methods are broadly applicable to other organisms of interest, e.g. viruses, yeast, and aspects of the technology are not limited in this respect.

[00154] Such alterations, modifications, and improvements are intended to be within the spirit and scope of the technology described herein. For example, those of ordinary skill in the art will readily envision a variety of other means and/or structures for performing the function and/or obtaining the results and/or one or more of the advantages described herein, and each of such variations and/or modifications is deemed to be within the scope of the embodiments described herein. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific embodiments described herein. It is, therefore, to be understood that the foregoing embodiments are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, inventive embodiments may be practiced otherwise than as specifically described. In addition, any combination of two or more features, systems, articles, materials, kits, and/or methods described herein, if such features, systems, articles, materials, kits, and/or methods are not mutually inconsistent, is included within the scope of the present disclosure.

[00155] The above-described embodiments can be implemented in any of numerous ways. One or more aspects and embodiments of the present disclosure involving the performance of processes or methods may utilize program instructions executable by a device (e.g., a computer, a processor, or other device) to perform, or control performance of, the processes or methods. In this respect, various inventive concepts may be embodied as a computer readable storage medium (or multiple computer readable storage media) (e.g., a computer memory, one or more floppy discs, compact discs, optical discs, magnetic tapes, flash memories, circuit configurations in Field Programmable Gate Arrays or other semiconductor devices, or other tangible computer storage medium) encoded with one or more programs that, when executed on one or more computers or other processors, perform methods that implement one or more of the various embodiments described above. The computer readable medium or media can be transportable, such that the program or programs stored thereon can be loaded onto one or more different computers or other processors to implement various ones of the aspects described above. In some embodiments, computer readable media may be non-transitory media.

[00156] The above-described embodiments of the present technology can be implemented in any of numerous ways. For example, the embodiments may be implemented using hardware, software or a combination thereof. When implemented in software, the software code can be executed on any suitable processor or collection of processors, whether provided in a single computer or distributed among multiple computers. It should be appreciated that any component or collection of components that perform the functions described above can be generically considered as a controller that controls the above-described function. A controller can be implemented in numerous ways, such as with dedicated hardware, or with general purpose hardware (e.g., one or more processor) that is programmed using microcode or software to perform the functions recited above, and may be implemented in a combination of ways when the controller corresponds to multiple components of a system.

[00157] Further, it should be appreciated that a computer may be embodied in any of a number of forms, such as a rack-mounted computer, a desktop computer, a laptop computer, or a tablet computer, as non-limiting examples. Additionally, a computer may be embedded in a device not generally regarded as a computer but with suitable processing capabilities, including a Personal Digital Assistant (PDA), a smartphone or any other suitable portable or fixed electronic device.

[00158] Also, a computer may have one or more input and output devices. These devices can be used, among other things, to present a user interface. Examples of output devices that can be used to provide a user interface include printers or display screens for visual presentation of output and speakers or other sound generating devices for audible presentation of output. Examples of input devices that can be used for a user interface include keyboards, and pointing devices, such as mice, touch pads, and digitizing tablets. As another example, a computer may receive input information through speech recognition or in other audible formats.

[00159] Such computers may be interconnected by one or more networks in any suitable form, including a local area network or a wide area network, such as an enterprise network, and intelligent network (IN) or the Internet. Such networks may be based on any suitable technology and may operate according to any suitable protocol and may include wireless networks, wired networks or fiber optic networks.

[00160] Also, as described, some aspects may be embodied as one or more methods. The acts performed as part of the method may be ordered in any suitable way. Accordingly, embodiments may be constructed in which acts are performed in an order different than illustrated, which may include performing some acts simultaneously, even though shown as sequential acts in illustrative embodiments.

[00161] All definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and/or ordinary meanings of the defined terms.

[00162] The indefinite articles “a” and “an,” as used herein in the specification and in the claims, unless clearly indicated to the contrary, should be understood to mean “at least one.” [00163] The phrase “and/or,” as used herein in the specification and in the claims, should be understood to mean “either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with “and/or” should be construed in the same fashion, i.e., “one or more” of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the “and/or” clause, whether related or unrelated to those elements specifically identified. Thus, as anon-limiting example, a reference to “A and/or B”, when used in conjunction with open-ended language such as “comprising” can refer, in one embodiment, to A only (optionally including elements other than B); in another embodiment, to B only (optionally including elements other than A); in yet another embodiment, to both A and B (optionally including other elements); etc.

[00164] As used herein in the specification and in the claims, the phrase “at least one,” in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed within the list of elements and not excluding any combinations of elements in the list of elements. This definition also allows that elements may optionally be present other than the elements specifically identified within the list of elements to which the phrase “at least one” refers, whether related or unrelated to those elements specifically identified. Thus, as a non-limiting example, “at least one of A and B” (or, equivalently, “at least one of A or B,” or, equivalently “at least one of A and/or B”) can refer, in one embodiment, to at least one, optionally including more than one, A, with no B present (and optionally including elements other than B); in another embodiment, to at least one, optionally including more than one, B, with no A present (and optionally including elements other than A); in yet another embodiment, to at least one, optionally including more than one, A, and at least one, optionally including more than one, B (and optionally including other elements); etc.

[00165] Also, the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of "including," "comprising," or "having," “containing,” “involving,” and variations thereof herein, is meant to encompass the items listed thereafter and equivalents thereof as well as additional items.

[00166] In the claims, as well as in the specification above, all transitional phrases such as “comprising,” “including,” “carrying,” “having,” “containing,” “involving,” “holding,” “composed of,” and the like are to be understood to be open-ended, i.e., to mean including but not limited to. Only the transitional phrases “consisting of’ and “consisting essentially of’ shall be closed or semi-closed transitional phrases, respectively.

[00167] The terms “substantially”, “approximately”, and “about” may be used to mean within ±20% of a target value in some embodiments, within ±10% of a target value in some embodiments, within ±5% of a target value in some embodiments, within ±2% of a target value in some embodiments. The terms “approximately” and “about” may include the target value. [00168] Use of ordinal terms such as “first,” “second,” “third,” etc., in the claims to modify a claim element does not by itself connote any priority, precedence, or order of one claim element over another or the temporal order in which acts of a method are performed, but are used merely as labels to distinguish one claim element having a certain name from another element having a same name (but for use of the ordinal term) to distinguish the claim elements.

Claims

1. A method for distinguishing microbes in an image, the image including first microbes of a first type and second microbes of a second type different from the first type, the method comprising: segmenting the image to detect the first microbes and the second microbes in the image; classifying each microbe in the segmented image as being of the first type or the second type, wherein the classification is based, at least in part, on at least one characteristic of microbe; and outputting a result of the classifying the microbe as being of the first type or the second type.

2. The method of claim 1, wherein the first microbes are endospores and the second microbes are vegetative cells.

3. The method of claim 1, wherein the image is color image including a plurality of color channels, and wherein the method further comprises removing at least one of the plurality of color channels prior to segmenting the image.

4. The method of claim 3, wherein removing at least one of the plurality of color channels comprises: separating the plurality of color channels in the color image; and combining one or more of the plurality of color channels after removing the at least one of the plurality of color channels.

5. The method of claim 3, wherein the color image is a red-green-blue (RGB) image including red, green and blue color channels, and wherein removing at least one of the plurality of color channels comprises removing the blue color channel.

6. The method of claim 1, wherein the image is a color image, and wherein the method further comprises converting the color image to a grayscale image prior to segmenting the image.

7. The method of claim 1, further comprising performing background subtraction on the image prior to segmenting the image.

8. The method of claim 7, wherein performing background subtraction on the image comprises subtracting a same value from a value of each pixel in the image.

9. The method of claim 8, wherein the same value is determined based on a value of one or more pixels in the image representing an electrode of the microfluidic system.

10. The method of claim 8, wherein the same value is determined based on a value of one or more pixels in the image representing an inter-electrode space.

11. The method of claim 1 , wherein the image is a color image including a plurality of color channels, segmenting the image comprises defining an intensity range for each of the plurality of color channels, and classifying each microbe in the segmented image comprises classifying the microbe as being of the first type when its intensity falls within the intensity range for each of the plurality of color channels.

12. The method of claim 1 , wherein segmenting the image comprises generating a grayscale image based on the image, and classifying each microbe in the segmented image comprises: defining an intensity phase for the first type and/or the second type of microbes, and classifying the microbe based, at least in part, on its intensity and the defined intensity phase for the first type and/or the second type of microbes.

13. The method of claim 1 , wherein segmenting the image comprises generating a hue-saturation-value (HSV) image based on the image, the HSV image including a hue channel, a saturation channel and a value channel, and classifying each microbe in the segmented image comprises: defining a value range for each of the hue channel, the saturation channel and the value channel; and classifying the microbe as being of the first type when its intensity value in the HSV image falls within the value range for each of the hue channel, the saturation channel and the value channel.

14. The method of claim 1, wherein the at least one characteristic includes a morphological characteristic.

15. The method of claim 14, wherein the morphological characteristic comprises a size and/or shape of the microbe.

16. The method of claim 15, wherein the size of the microbe comprises a number of contiguous pixels representing the microbe in the image.

17. The method of claim 15, wherein the size of the microbe is determined based on at least one measurement selected from the group consisting of an area, a circumference, a diameter, an extent, and a bisector.

18. The method of claim 15, wherein the shape of the microbe is determined based on at least one measurement selected from the group consisting of an aspect ratio, an elongation value, a convexity value, a shape factor, and a sphericity value.

19. The method of claim 14, wherein classifying each microbe in the segmented image as being of the first type or the second type comprises: performing principal component analysis on each microbe in the segmented image; and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the principal component analysis.

20. The method of claim 14, wherein classifying each microbe in the segmented image as being of the first type or the second type comprises: performing singular value decomposition on each microbe in the segmented image; and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the singular value decomposition.

21. The method of claim 1 , wherein classifying the microbe as being of the first type or the second type comprises: providing, as input to a trained machine learning model, the image and/or one or more features derived from the image; and classifying the microbe as being of the first type or the second type based, at least in part, on an output of the trained machine learning model.

22. The method of claim 21, wherein the first microbes are endospores and the second microbes are vegetative cells, and wherein the trained machine learning model has been trained to recognize endospores and/or vegetative cells.

23. The method of claim 1, further comprising filtering the image prior to classifying the microbe in the segmented image as being of the first type or the second type.

24. The method of claim 23, wherein filtering the image comprises filtering the image prior to segmenting the image.

25. The method of claim 1, further comprising: prior to the classifying, filtering from the detected first microbes and second microbes in the segmented image, objects having a diameter greater than a predetermined number of pixels.

26. A system for distinguishing microbes in an image captured by a microfluidic system, the image including first microbes of a first type and second microbes of a second type different from the first type, the system comprising: a microfluidic passage for receiving a sample, the sample comprising the first microbes and the second microbes; at least one electrode disposed in the microfluidic passage, the at least one electrode configured to immobilize, when activated, the first microbes and the second microbes onto a surface of the at least one electrode using dielectrophoresis; an optical system configured to capture the image while the first microbes and the second microbes are immobilized on the surface of the at least one electrode; and at least one computing device configured to: segment the image to detect the first microbes and the second microbes in the image; classify each microbe in the segmented image as being of the first type or the second type, wherein the classification is based, at least in part, on at least one characteristic of microbe; and output a result of the classifying the microbe as being of the first type or the second type.

27. The system of claim 26, wherein the first microbes are endospores and the second microbes are vegetative cells.

28. The system of claim 26, wherein the image is color image including a plurality of color channels, and wherein the at least one computing device is further configured to remove at least one of the plurality of color channels prior to segmenting the image.

29. The system of claim 28, wherein removing at least one of the plurality of color channels comprises: separating the plurality of color channels in the color image; and combining one or more of the plurality of color channels after removing the at least one of the plurality of color channels.

30. The system of claim 28, wherein the color image is a red-green-blue (RGB) image including red, green and blue color channels, and wherein removing at least one of the plurality of color channels comprises removing the blue color channel.

31. The system of claim 26, wherein the image is a color image, and wherein the method further comprises converting the color image to a grayscale image prior to segmenting the image.

32. The system of claim 26, wherein the at least one computing device is further configured to perform background subtraction on the image prior to segmenting the image.

33. The system of claim 32, wherein performing background subtraction on the image comprises subtracting a same value from a value of each pixel in the image.

34. The system of claim 33, wherein the same value is determined based on a value of one or more pixels in the image representing an electrode of the microfluidic system.

35. The system of claim 33, wherein the same value is determined based on a value of one or more pixels in the image representing an inter-electrode space.

36. The system of claim 26, wherein the image is a color image including a plurality of color channels, segmenting the image comprises defining an intensity range for each of the plurality of color channels, and classifying each microbe in the segmented image comprises classifying the microbe as being of the first type when its intensity falls within the intensity range for each of the plurality of color channels.

37. The system of claim 26, wherein segmenting the image comprises generating a grayscale image based on the image, and classifying each microbe in the segmented image comprises: defining an intensity phase for the first type and/or the second type of microbes, and classifying the microbe based, at least in part, on its intensity and the defined intensity phase for the first type and/or the second type of microbes.

38. The system of claim 26, wherein segmenting the image comprises generating a hue-saturation-value (HSV) image based on the image, the HSV image including a hue channel, a saturation channel and a value channel, and classifying each microbe in the segmented image comprises: defining a value range for each of the hue channel, the saturation channel and the value channel; and classifying the microbe as being of the first type when its intensity value in the HSV image falls within the value range for each of the hue channel, the saturation channel and the value channel.

39. The system of claim 26, wherein the at least one characteristic includes a morphological characteristic.

40. The system of claim 39, wherein the morphological characteristic comprises a size and/or shape of the microbe.

41. The system of claim 40, wherein the size of the microbe comprises a number of contiguous pixels representing the microbe in the image.

42. The system of claim 40, wherein the size of the microbe is determined based on at least one measurement selected from the group consisting of an area, a circumference, a diameter, an extent, and a bisector.

43. The system of claim 40, wherein the shape of the microbe is determined based on at least one measurement selected from the group consisting of an aspect ratio, an elongation value, a convexity value, a shape factor, and a sphericity value.

44. The system of claim 38, wherein classifying each microbe in the segmented image as being of the first type or the second type comprises: performing principal component analysis on each microbe in the segmented image; and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the principal component analysis.

45. The system of claim 38, wherein classifying each microbe in the segmented image as being of the first type or the second type comprises: performing singular value decomposition on each microbe in the segmented image; and classifying the microbe as being of the first type or the second type based, at least in part, on a result of the singular value decomposition.

46. The system of claim 26, wherein classifying the microbe as being of the first type or the second type comprises: providing, as input to a trained machine learning model, the image and/or one or more features derived from the image; and classifying the microbe as being of the first type or the second type based, at least in part, on an output of the trained machine learning model.

47. The system of claim 46, wherein the first microbes are endospores and the second microbes are vegetative cells, and wherein the trained machine learning model has been trained to recognize endospores and/or vegetative cells.

48. The system of claim 26, wherein the at least one computing device is further configured to filter the image prior to classifying the microbe in the segmented image as being of the first type or the second type.

49. The system of claim 48, wherein filtering the image comprises filtering the image prior to segmenting the image.

50. The system of claim 26, wherein the at least one computing device is further configured to prior to the classifying, filtering from the detected first microbes and second microbes in the segmented image, objects having a diameter greater than a predetermined number of pixels.

51. A method for separating spores from vegetative bacteria in a fluid sample, the method comprising: providing the fluid sample as input to a microfluidic passage of a microfluidic device, wherein the microfluidic device includes at least one electrode disposed adjacent to the microfluidic passage; and activating the at least one electrode to separate the spores from the vegetative bacteria in the fluid sample based, at least in part, on a different dielectrophoretic response for the spores and the vegetative bacteria when the at least one electrode is activated.

52. The method of claim 51, wherein activating the at least one electrode comprises applying a voltage to the at least one electrode, the voltage having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to edges of the at least one electrode while not attracting the spores to the edges of the at least one electrode.

53. The method of claim 51, wherein the microfluidic device comprises a microfluidic chip, and wherein providing the fluid sample as input to the microfluidic passage comprises loading the fluid sample onto the microfluidic chip.

54. The method of claim 51, wherein activating the at least one electrode comprises: applying a first voltage to the at least one electrode having a first frequency that generates a first dielectrophoretic force to attract the vegetative bacteria and the spores to a surface of the at least one electrode; and applying a second voltage to the at least one electrode having a second frequency that generates a second dielectrophoretic force to release one of the vegetative bacteria or the spores from the surface of the at least one electrode.

55. The method of claim 54, wherein providing the fluid sample as input to the microfluidic passage comprises pumping the fluid sample through the microfluidic passage.

56. The method of claim 54 or 55, wherein the second frequency of the second voltage is configured to selectively release the spores from the surface of the at least one electrode.

57. The method of claim 56, further comprising collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores released from the surface of the at least one electrode.

58. The method of claim 54 or 55, wherein the second frequency of the second voltage is configured to selectively release the vegetative cells from the surface of the at least one electrode.

59. The method of claim 58, further comprising capturing at least one image of the at least one electrode following release of the vegetative cells from the surface of the at least one electrode and while the spores remain attracted to the surface of the at least one electrode.

60. The method of claim 59, further comprising processing the at least one image to quantify an amount of spores in the fluid sample.

61. The method of claim 60, further comprising: passing a fluid comprising a stain through the microfluidic passage, the stain configured to stain the spores, wherein quantifying the amount of spores comprises counting a number of stained spores in the at least one image.

62. The method of claim 61, wherein: providing the fluid sample as input to the microfluidic passage comprises pumping the fluid sample through the microfluidic passage, and activating the at least one electrode comprises applying a voltage to the at least one electrode having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to a surface of the at least one electrode while not attracting the endospores to the surface of the at least one electrode as the fluid sample flows past the at least one electrode.

63. The method of claim 62, further comprising collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores.

64. The method of claim 62, wherein the voltage applied to the at least one electrode has an amplitude greater than 40V.

65. A system for separating spores from vegetative bacteria in a fluid sample, the system comprising: a microfluidic passage for receiving the fluid sample, the fluid sample comprising the spores and the vegetative bacteria; and at least one electrode disposed in the microfluidic passage, the at least one electrode configured to separate, when activated, the spores from the vegetative bacteria in the fluid sample based, at least in part, on a different dielectrophoretic response for the spores and the vegetative bacteria when the at least one electrode is activated.

66. The system of claim 65, further comprising a controller configured to activate the at least one electrode by applying a voltage to the at least one electrode, the voltage having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to edges of the at least one electrode while not attracting the spores to the edges of the at least one electrode.

67. The system of claim 65, wherein the microfluidic passage is included on a microfluidic chip, and wherein receiving the fluid sample comprises receiving the sample via loading the fluid sample onto the microfluidic chip.

68. The system of claim 65, further comprising a controller configured to activate the at least one electrode by: applying a first voltage to the at least one electrode having a first frequency that generates a first dielectrophoretic force to attract the vegetative bacteria and the spores to a surface of the at least one electrode; and applying a second voltage to the at least one electrode having a second frequency that generates a second dielectrophoretic force to release one of the vegetative bacteria or the spores from the surface of the at least one electrode.

69. The system of claim 68, further comprising a pump configured to pump the fluid sample through the microfluidic passage.

70. The system of claim 68 or 69, wherein the second frequency of the second voltage is configured to selectively release the spores from the surface of the at least one electrode.

71. The system of claim 70, further comprising an effluent fluid container configured to collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores released from the surface of the at least one electrode.

72. The system of claim 68 or 69, wherein the second frequency of the second voltage is configured to selectively release the vegetative cells from the surface of the at least one electrode.

73. The system of claim 72, further comprising an optical system configured to capture at least one image of the at least one electrode following release of the vegetative cells from the surface of the at least one electrode and while the spores remain attracted to the surface of the at least one electrode.

74. The system of claim 73, further comprising at least one computing device configured to process the at least one image to quantify an amount of spores in the fluid sample.

75. The system of claim 74, further comprising: a pump configured to pump a fluid comprising a stain through the microfluidic passage, the stain configured to stain the spores, wherein quantifying the amount of spores comprises counting a number of stained spores in the at least one image.

76. The system of claim 75, wherein: the pump is configured to pump the fluid sample through the microfluidic passage, and the controller is further configured to activate the at least one electrode by applying a voltage to the at least one electrode having a frequency that generates a dielectrophoretic force to selectively attract the vegetative bacteria to a surface of the at least one electrode while not attracting the endospores to the surface of the at least one electrode as the fluid sample flows past the at least one electrode.

77. The system of claim 76 further comprising an effluent fluid container configured to collect at an outlet of the microfluidic passage, effluent fluid comprising the spores.

78. The system of claim 76, wherein the voltage applied to the at least one electrode has an amplitude greater than 40V.

79. A method for quantifying spores in a fluid sample, the method comprising: providing the fluid sample as input to a microfluidic passage of a microfluidic device, wherein the microfluidic device includes at least one electrode disposed adjacent to the microfluidic passage; activating the at least one electrode to attract the spores to a surface of the at least one electrode using dielectrophoresis; capturing at least one first image of the at least one electrode while the spores are attracted to the surface of the at least one electrode; and quantifying an amount of spores in the fluid sample based, at least in part, on analyzing the at least one first image.

80. The method of claim 79, wherein the microfluidic device comprises a microfluidic chip, and wherein providing the fluid sample as input to the microfluidic passage comprises loading the fluid sample onto the microfluidic chip.

81. The method of claim 79 or 80, wherein the fluid sample comprises a fecal sample.

82. The method of claim 79 or 80, wherein the fluid sample comprises a bioreactor sample for a mammalian cell culture, a bacterial culture or a plant culture.

83. The method of claim 79 or 80, wherein the fluid sample comprises a liquefied sample of food.

84. The method of claim 79, wherein providing the fluid sample as input to the microfluidic passage comprises pumping the fluid sample through the microfluidic passage.

85. The method of claim 84, wherein the sample comprises spores and other microbes, the method further comprising: activating, in a first sample run, the at least one electrode using a voltage having first characteristics prior to activating the at least one electrode to attract the spores to the surface of the at least one electrode, the first characteristics selected to selectively attract the other microbes to the surface of the at least one electrode and not attract the spores to the surface of the at least one electrode; collecting at an outlet of the microfluidic passage, effluent fluid comprising the spores not attracted to the surface of the at least one electrode; and providing the effluent sample as input to the microfluidic passage in a second sample run, wherein activating the at least one electrode to attract the spores to the surface of the at least one electrode is performed during the second sample run.

86. The method of claim 85, further comprising capturing, during the first sample run, at least one second image of the at least one electrode while the other microbes are attracted to the surface of the at least one electrode.

87. The method of claim 86, wherein quantifying the amount of spores in the fluid sample is further based, at least in part, on analyzing the at least one second image.

88. The method of claim 86, further comprising: quantifying an amount of other microbes in the fluid sample based, at least in part, on analyzing the at least one second image; and determining a ratio of spores to other microbes in the fluid sample based on the quantified amount of spores and the quantified amount of other microbes.

89. The method of any of claims 79, 80 or 85, wherein quantifying the amount of spores in the fluid sample comprises detecting spores in the at least one first image based, at least in part on spore morphology.

90. The method of any of claims 79, 80 or 85, wherein quantifying the amount of spores in the fluid sample comprises: providing the at least one first image as input to a trained machine learning model; and detecting spores in the at least one first image based, at least in part, on an output of the trained machine learning model.

91. The method of claim 90, wherein the trained machine learning model is a neural network trained to recognize spores in an image.

92. The method of any of claims 89-91, wherein quantifying the amount of spores in the fluid sample further comprises quantifying the amount of spores in the fluid sample based, at least in part, on a statistical distribution of an area of the at least one electrode represented in the at least one first image.

93. A system for quantifying spores in a fluid sample, the system comprising: a microfluidic passage for receiving the fluid sample, the fluid sample comprising endospores; at least one electrode disposed in the microfluidic passage, the at least one electrode configured to attract, when activated, the spores in the fluid sample to a surface of that least one electrode using dielectrophoresis; an optical system configured to capture at least one first image of the at least one electrode while the spores are attracted to the surface of the at least one electrode; and at least one computer processor configured to process the at least one first image to quantify an amount of spores in the fluid sample.

94. The system of claim 93, wherein the microfluidic passage is included in a microfluidic chip, and wherein receiving the fluid sample comprises receiving the fluid sample via loading the fluid sample onto the microfluidic chip.

95. The system of claim 93 or 94, wherein the fluid sample comprises a fecal sample.

96. The system of claim 93 or 94, wherein the fluid sample comprises a bioreactor sample for a mammalian cell culture, a bacterial culture or a plant culture.

97. The system of claim 93 or 94, wherein the fluid sample comprises a liquefied sample of food.

98. The system of claim 93, further comprising a pump configured to pump the fluid sample through the microfluidic passage.

99. The system of claim 98, wherein the sample comprises spores and other microbes, the system further comprising: a controller configured to activate, in a first sample run, the at least one electrode using a voltage having first characteristics prior to activating the at least one electrode to attract the spores to the surface of the at least one electrode, the first characteristics selected to selectively attract the other microbes to the surface of the at least one electrode and not attract the spores to the surface of the at least one electrode; and an effluent fluid container configured to collect at an outlet of the microfluidic passage, effluent fluid comprising the spores not attracted to the surface of the at least one electrode, wherein the effluent sample is provided as input to the microfluidic passage in a second sample run, wherein activating the at least one electrode to attract the spores to the surface of the at least one electrode is performed during the second sample run.

100. The system of claim 99, wherein the optical system is further configured to capture, during the first sample run, at least one second image of the at least one electrode while the other microbes are attracted to the surface of the at least one electrode.

101. The system of claim 100, wherein quantifying the amount of spores in the fluid sample is further based, at least in part, on analyzing the at least one second image.

102. The system of claim 100, wherein the at least one computer processor is further configured to: quantify an amount of other microbes in the fluid sample based, at least in part, on analyzing the at least one second image; and determine a ratio of spores to other microbes in the fluid sample based on the quantified amount of spores and the quantified amount of other microbes.

103. The system of any of claims 93, 94 or 99, wherein quantifying the amount of spores in the fluid sample comprises detecting spores in the at least one first image based, at least in part on spore morphology.

104. The system of any of claims 93, 94 or 99, wherein quantifying the amount of spores in the fluid sample comprises: providing the at least one first image as input to a trained machine learning model; and detecting spores in the at least one first image based, at least in part, on an output of the trained machine learning model.

105. The system of claim 105, wherein the trained machine learning model is a neural network trained to recognize spores in an image.

106. The system of any of claims 103-105, wherein quantifying the amount of spores in the fluid sample further comprises quantifying the amount of spores in the fluid sample based, at least in part, on a statistical distribution of an area of the at least one electrode represented in the at least one first image.