Systems and methods of for integrating stained and unstained sample processing

Abstract

A patient sample may be processed via a method which comprises preparing first and second portions of the patient sample, capturing first and second pluralities of images, determining first and second counts of one or more types of particles, and generating an output corresponding to at least one of those types of particles based on the first and second counts for that type of particle.

Description

[0001] SYSTEMS AND METHODS OF FOR INTEGRATING STAINED AND UNSTAINED SAMPLE PROCESSING

[0002] PRIORITY

[0003] This claims the benefit of U.S. provisional patent application 63 / 615,161, entitled “Systems and Methods for Integrating Stained and Unstained Sample Processing,” filed December 27, 2023, the disclosure of which is hereby incorporated by reference in its entirety.

[0004] BACKGROUND

[0005] Blood cell analysis is one of the most commonly performed medical tests for providing an overview of a patient's health status. A sample (e.g., a blood sample) can be drawn from a patient’s body and stored in a test tube containing an anticoagulant to prevent clotting. The sample can then be processed to determine information such as the number or percent of cells of various different categories that it includes. This information, in turn, can be applied in treatment and / or diagnosis of a patient.

[0006] While traditional cell processing technology can be effective, it does have drawbacks. For example, while analyzers used for processing patient samples may be optimized to provide results for samples in a normal (i.e., to be expected for a healthy individual) range, the results may be less accurate for samples from patients who are suffering from or at elevated risk of a disease or disorder. Accordingly, there is a need for improved sample processing systems, such as systems which account for accuracy impacts which may be caused by patients having measurements outside of a normal range.

[0007] SUMMARY

[0008] Described herein are devices, systems and methods which can be used for the generation of output(s) based on both stained and unstained counts for types of particles in a patient sample.

[0009] An illustrative implementation of such technology relates to a method which comprises preparing first and second portions of the patient sample, capturing first and second pluralities of images, determining first and second counts of one or more types of particles, and generating an output corresponding to at least one of those types of particles based on the first and second counts for that type of particle. In such a method, preparing the first and second portions of the patient sample may comprise staining a plurality of particle in the first portion of the patient sample. The first plurality of images may be images of the first portion of the patient sample captured after staining the plurality of particles in the first portion of the sample, and the second plurality of images may be images of the second portion of the patient sample, wherein no particles comprised by the second portion of the patient sample are stained when the plurality of images of the second portion of the patient sample are captured. Similarly, in this type of method the first count for each of the one or more types of particles may be determined based on the plurality of images of the first portion of the patient sample and the second count for each of the one or more types of particles may be determined based on the plurality of images of the second portion of the patient sample.

[0010] While multiple examples are described herein, still other examples of the described subject matter will become apparent to those skilled in the art from the following detailed description and drawings, which show and describe illustrative examples of disclosed subject matter. As will be realized, the disclosed subject matter is capable of modifications in various aspects, all without departing from the spirit and scope of the described subject matter. Accordingly, the drawings and detailed description are to be regarded as illustrative in nature and not restrictive.

[0011] BRIEF DESCRIPTION OF THE DRAWINGS

[0012] While the specification concludes with claims which particularly point out and distinctly claim the invention, it is believed the present invention will be better understood from the following description of certain examples taken in conjunction with the accompanying drawings, in which like reference numerals identify the same elements and in which:

[0013] FIG. 1 is a schematic illustration, partly in section and not to scale, showing operational aspects of an exemplary flow cell and high optical resolution imaging device for sample image analysis using digital image processing.

[0014] FIG. 2 illustrates a slide-based vision inspection system in which aspects of the disclosed technology may be used. FIG. 3 illustrates a process which may be used to gather and integrate information from stained and unstained portions of a patient sample.

[0015] FIG. 4 illustrates an example machine learning model.

[0016] FIG. 5 illustrates an example of a layer such as may be included in a machine learning model as shown in FIG. 4.

[0017] FIG. 6 illustrates an exemplary process which may be used in staining a portion of a patient sample.

[0018] The drawings are not intended to be limiting in any way, and it is contemplated that various embodiments of the invention may be carried out in a variety of other ways, including those not necessarily depicted in the drawings. The accompanying drawings incorporated in and forming a part of the specification illustrate several aspects of the present invention, and together with the description serve to explain the principles of the invention; it being understood, however, that this invention is not limited to the precise arrangements shown.

[0019] DETAILED DESCRIPTION

[0020] The present disclosure relates to apparatus, systems, compositions, and methods for analyzing a sample containing particles. In one embodiment, the invention relates to an automated particle imaging system which comprises an analyzer which may be, for example, a visual analyzer. In some embodiments, the visual analyzer may further comprise a processor to facilitate automated analysis of the images.

[0021] According to some aspects of this disclosure, a system comprising a visual analyzer may be provided for obtaining images of a sample comprising particles suspended in a liquid. Such a system may be useful, for example, in characterizing particles in biological fluids, such as detecting and quantifying erythrocytes, reticulocytes, nucleated red blood cells, platelets, and white blood cells, including white blood cell differential counting, categorization and subcategorization and analysis. Other similar uses such as characterizing blood cells from other fluids are also contemplated. The classification of blood cells in a blood sample is an exemplary application for which the subject matter is particularly well suited, though other types of body fluid samples may be used. For example, aspects of the disclosed technology may be used in analysis of a non-blood body fluid sample comprising blood cells (e.g., white blood cells and / or red blood cells), such as serum, bone marrow, lavage fluid, effusions, exudates, cerebrospinal fluid, pleural fluid, peritoneal fluid, and amniotic fluid. It is also possible that the sample can be a solid tissue sample, e.g., a biopsy sample that has been treated to produce a cell suspension. The sample may also be a suspension obtained from treating a fecal sample. A sample may also be a laboratory or production line sample comprising particles, such as a cell culture sample. The term sample may be used to refer to a sample obtained from a patient or laboratory or any fraction, portion or aliquot thereof. The sample can be diluted, divided into portions, or stained in some processes.

[0022] In some aspects, samples are presented, imaged and analyzed in an automated manner. In the case of blood samples, the sample may be substantially diluted with a suitable diluent or saline solution, which reduces the extent to which the view of some cells might be hidden by other cells in an undiluted or less-diluted sample. The cells can be treated with agents that enhance the contrast of some cell aspects, for example using permeabilizing agents to render cell membranes permeable, and histological stains to adhere in and to reveal features, such as granules and the nucleus. In some cases, it may be desirable to stain an aliquot of the sample for counting and characterizing particles which include reticulocytes, nucleated red blood cells, and platelets, and for white blood cell differential, characterization and analysis. In other cases, samples containing red blood cells may be diluted before introduction to the flow cell and / or imaging in the flow cell or otherwise.

[0023] The particulars of sample preparation apparatus and methods for sample dilution, permeabilizing and histological staining, generally may be accomplished using precision pumps and valves operated by one or more programmable controllers. Examples can be found in patents such as U.S. Pat. No. 7,319,907. Likewise, techniques for distinguishing among certain cell categories and / or subcategories by their attributes such as relative size and color can be found in U.S. Pat. No. 5,436,978 in connection with white blood cells. The disclosures of these patents are hereby incorporated by reference in their entirety.

[0024] I. IMAGING SYSTEMS Turning now to the drawings, FIG. 1 schematically shows an exemplary flow cell 22 for conveying a sample fluid through a viewing zone 23 of a high optical resolution imaging device 24 in a configuration for imaging microscopic particles in a sample flow stream 32 using digital image processing. Flow cell 22 is coupled to a source 25 of sample fluid which may have been subjected to processing, such as contact with a particle contrast agent composition and heating. Flow cell 22 is also coupled to one or more sources 27 of a particle and / or intracellular organelle alignment liquid (PIO AL), such as a clear glycerol solution having a viscosity that is greater than the viscosity of the sample fluid.

[0025] The sample fluid is injected through a flattened opening at a distal end 28 of a sample feed tube 29, and into the interior of the flow cell 22 at a point where the PIOAL flow has been substantially established resulting in a stable and symmetric laminar flow of the PIOAL around / surrounding (e.g., circumferentially in a circular cross-sectional arrangement, or surrounding a plurality of sides of in a non-circular (e.g., rectangular) cross-sectional arrangement) the ribbon-shaped sample stream. The sample and PIOAL streams may be supplied by precision metering pumps that move the PIOAL with the injected sample fluid along a flowpath that narrows substantially. The PIOAL envelopes and compresses the sample fluid in the zone 21 where the flowpath narrows. Hence, the decrease in flowpath thickness at zone 21 can contribute to a geometric focusing of the sample stream 32. The sample fluid ribbon 32 is enveloped and carried along with the PIOAL downstream of the narrowing zone 21, passing in front of, or otherwise through the viewing zone 23 of, the high optical resolution imaging device 24 where images are collected, for example, using a CCD 48. In this way, flow imaging is performed where images from the flowing sample stream and the cellular material contained therein are collected. Processor 18 can receive, as input, pixel data from CCD 48. The sample fluid ribbon flows together with the PIOAL to a discharge 33.

[0026] As shown here, the narrowing zone 21 can have a proximal flowpath portion 21a having a proximal thickness PT and a distal flowpath portion 21b having a distal thickness DT, such that distal thickness DT is less than proximal thickness PT. The sample fluid can therefore be injected through the distal end 28 of sample tube 29 at a location that is distal to the proximal portion 21a and proximal to the distal portion 21b. Hence, the sample fluid can enter the PIOAL envelope as the PIOAL stream is compressed by the zone 21. wherein the sample fluid injection tube has a distal exit port through which sample fluid is injected into flowing sheath fluid, the distal exit port bounded by the decrease in flowpath size of the flow cell.

[0027] The digital high optical resolution imaging device 24 with objective lens 46 is directed along an optical axis that intersects the ribbon-shaped sample stream 32. The relative distance between the objective 46 and the flow cell 33 is variable by operation of a motor drive 54, for resolving and collecting a focused digitized image on a photosensor array. Additional information regarding the construction and operation of an exemplary flow cell such as shown in FIG. 1 is provided in U.S. Patent 9,322,752, entitled “Flow cell Systems and Methods for Particle Analysis in Blood Samples,” filed on March 17, 2014, the disclosure of which is hereby incorporated by reference in its entirety.

[0028] Aspects of the disclosed technology may also be applied in contexts other than flow cell systems such as shown in FIG. 1. For example, FIG. 2 illustrates a slide-based vision inspection system 200 in which aspects of the disclosed technology may be used. In the system shown in FIG. 2, a slide 202 comprising a sample, such as a blood sample, is placed in a slide holder 204. The slide holder 204 may be adapted to hold a number of slides or only one, as illustrated in FIG. 2. An image capturing device 206, comprising an optical system 208 and an image sensor 210, is adapted to capture image data depicting the sample in the slide 202.

[0029] The image data captured by the image capturing device 206 can be transferred to an image processing device 212. The image processing device 112 may be an external apparatus, such as a personal computer, connected to the image capturing device 206. Alternatively, the image processing device 212 may be incorporated in the image capturing device 206. The image processing device 212 can comprise a processor 214, associated with a memory 216, configured to determine changes needed to determine differences between the actual focus and a correct focus for the image capturing device 206. When the difference is determined an instruction can be transferred to a steering motor system 218. The steering motor system 218 can, based upon the instruction from the image processing device 212, alter the distance z between the slide 202 and the optical system 208. Descriptions of approaches which may be used for focusing using this type of setup are provided in U.S. provisional patent application 63 / 291,044 titled “Autofocusing Through Multi-Layer Processing,” filed on December 17, 2021, U.S. patent 9,857,361 titled “Flowcell, sheath fluid, and autofocus systems and methods for particle analysis in urine samples”, filed on March 17, 2014, U.S. patent 10,705,008 titled “autofocus systems and methods for particle analysis in blood samples”, filed on March 17, 2014, U.S. patent 10,705,011, titled “Dynamic focus system and methods”, filed October 5, 2017, and international application WO2023 / 150064 titled “Measure image quality of blood cell images”, filed January 27, 2023, the disclosures of each of which are hereby incorporated by reference in their entirety.

[0030] IL STAINED AND UNSTAINED SAMPLE PROCESSING

[0031] Systems such as shown in FIGS. 1 and 2 may be used to capture data regarding both stained and unstained portions of patient samples, and the data from each of these portions may be used to provide results which may not be possible based on data from either stained or unstained portions alone. A high level method which may be performed in gathering and integrating such data is described below in the context of FIG. 3.

[0032] A. Sample Preparation

[0033] Initially, in the process of FIG. 3, first and second portions of a patient sample may be prepared 301 for processing, such as by staining a plurality of particles in the first portion of the sample. This type of staining may be done by, for example, using a process such as that shown in FIG. 6. Initially, in the process of FIG. 6, a staining agent may be delivered 2601, e g., via a stain dispenser, to a sample preparation chamber. The staining agent may then be pre-heated 2602 within the chamber such as via induction heating. Next, the first portion of the sample (e.g., an aliquot of the patient sample extracted by an aliquoter, which aliquoter may also be used to extract the second portion as well) may be delivered 2603 to the chamber. After the stain and the first portion of the sample have both been delivered to the chamber, they may be mixed so as to form 2604 a homogenous mixture. This may comprise, for example, using fluid energy to mix the sample with the stain, such as by cyclically pulling the sample out of and pushing the sample back into the chamber via a corresponding tangential port of the chamber’s housing to perform a regurgitative mixing. Alternatively, this may comprise using a magnet to drive a spherical ferromagnetic ball placed within the chamber to perform an agitative mixing. As another example, this may comprise introducing one or more bubbles at the bottom of the chamber to create a vortex. This homogenous mixture may then be incubated 2605, such as via inductive or resistive heating. In some embodiments, once the homogenous mixture has been heated to a threshold temperature, it may be maintained at that temperature via a maintenance heater. Thereafter, it may be routed for imaging, such as by being conveyed to a flow cell (e.g., flow cell 22 of FIG. 1 for imaging by the high resolution optical resolution imaging device 24).

[0034] Preparing 301 first and second portions of a sample may involve more than simply staining a plurality of particles in the first portion of the sample. For example, in some cases preparation 301 may include applying a lysing agent to the first and / or second portions of the sample so that particles of interest for that portion will not be obscured in the subsequently captured images. To illustrate, consider a case where the first portion of the sample is being prepared for subsequent processing in a white blood cell workflow (a set of operations which an analyzer would be programmed to perform to obtain information about white blood cells, like a white blood cell count), and the second portion of the sample is being prepared for subsequent processing in a red blood cell workflow (a set of operations which an analyzer would be programmed to perform to obtain information about red blood cells, like a red blood cell count). In such a case, because the concentration of red blood cells in a patient sample can be expected to be much greater than the concentration of white blood cells, a lysing agent may be added to only the first portion of the patient sample, so that the more numerous red blood cells would not interfere with imaging of white blood cells in the white blood cell workflow. This lysing agent may be included in the stain (i.e., a single substance would be used for both lysing and staining), or separate lysing and staining agents may be used (assuming that a lysing agent is used at all, in the embodiment in question).

[0035] As another example of an activity which may be included in the preparation 301, consider the addition of diluent to the first and / or second portions of the patient sample. Such diluent addition may make it less likely that subsequently captured images would include multiple particles and, as with the application of a lysing agent, may vary depending on the subsequent processing of the portion in question. To illustrate, consider again the example of a case where the first portion of the sample is being prepared for subsequent processing in a white blood cell workflow, and the second portion of the sample is being prepared for subsequent processing in a red blood cell workflow. In such a case, the second portion of the sample may have more diluent added than the first portion of the sample (which may not have any diluent added at all), since the concentration of particles (largely red blood cells) in the second portion would be expected to be higher than the concentration of particles in the first portion, especially after the red blood cells in the first portion had been lysed. Other types of activities which may be included in sample preparation, such as the application of different staining agents to stain different types of particles, and / or those described in U.S. patent application 18 / 224,947, the disclosure of which is incorporated herein by reference in its entirety, are also possible, and will be immediately apparent to those of skill in the art in light of this disclosure. Accordingly, the above description of activities which may take place as part of sample preparation should be treated as being illustrative only, and should not be treated as implying limitations on the protection provided by this document or any related document.

[0036] Just as variations are possible on acts which may be included in sample preparation, variations are also possible on the physical devices with which those acts are performed. For example, while the formation and induction heating of a sample mixture has been described as occurring within a sample preparation chamber, it will be appreciated that alternative arrangements may include tubing having a lumen in which the sample mixture may he formed and induction heated in manners similar to those described above. Similarly, in some cases there may be multiple sample preparation chambers (or multiple other structures, such as tubing) used for preparing 301 first and second portions of a sample. To illustrate, consider again the case where the first portion of the sample is being prepared for subsequent processing in a white blood cell workflow, and the second portion of the sample is being prepared for subsequent processing in a red blood cell workflow. In such a case, an analyzer where the sample portions were being prepared 301 may be configured to prepare all portions which would be processed in the white blood cell workflow in a dedicated chamber (which may be referred to as a white blood cell chamber), and to prepare all portions which would be processed in the red blood cell workflow in a different dedicated chamber (which may be referred to as a red blood cell chamber). However, it is also possible that an analyzer may be configured to prepare portions of a sample in one or more chambers which were not dedicated to particular workflows or particle types (e.g., using a single chamber for preparing 301 the first and second portions in series, rather than multiple chambers to prepare 301 the first and second portions in parallel). In addition, or alternatively, any one or more of the teachings herein may be combined with any one or more of the teachings disclosed in U.S. Pat. No. 9,429,524, entitled “Systems and Methods for Imaging Fluid Samples,” issued on August 30, 2016, and / or U.S. published patent application 2024 / 0027327, entitled “Lighting Module for Biological Analysis and Biological Analysis Systems and Methods.” filed on July 21, 2023, the disclosures of each of which are hereby incorporated by reference in their entirety. Accordingly, as with the description of acts which may be included in sample preparation, the description of components which may be used to prepare 301 first and second portions of a sample should be understood as being illustrative only, and should not be treated as limiting.

[0037] B. Capturing Images

[0038] In the process of FIG. 3, after first and second portions of a patient sample have been prepared, those first and second portions may be used in capturing 302 first and second pluralities of images. This may comprise, for example, in a system such as that illustrated in FIG. 1 , establishing 303 a flow of alignment fluid from an alignment fluid reservoir into a flow cell. It may also include creating 304 a sample stream comprising the applicable sample portion and a sheath of alignment fluid surrounding the sample based on injecting the sample portion from a channel into the flow of alignment fluid. With the sample stream established 304, a camera focused on a viewing area of the flow cell may be used to capture 305 a plurality of images as the sample stream is flowing through the viewing area of the flow cell. These image capture activities may be performed in series for the first and second pluralities of images - e.g., in an analyzer comprising a single flow cell, that flow cell may first be used for capturing the first plurality of images, and may then be used for capturing the second plurality of images. Alternatively, in some cases the first and second pluralities of images may be captured in parallel. For example, in the case of an analyzer configured to process some portions of patient samples using a white blood cell workflow and other portions of patient samples using a red blood cell workflow, there may be different sets of components (e.g., separate flow cells, separate cameras) for the different workflows, and one set of components may be used to capture the first plurality of images while another set of components is used to capture the second plurality of images. Once the images have been captured 305 they may be subjected to some level of image analysis and / or manipulation to be more suitable for subsequent processing. For example, captured 305 images may be filtered or subdivided so that each image which would subsequently be processed would only depict a single cell. Additionally, or alternatively, portions of images which do not represent a cell (e.g., background) may be removed through processes such as detecting a cell boundary and removing portions of images outside of that boundary (and / or replacing portions of images outside of that boundary with uniform values which had previously been determined to be used for background portions of images). Additionally, in some cases, images (either before or after further processing such as described above) may be transmitted 306 to a remote location (e.g., a cloud processing platform in communication with the location where the images were captured 305 via a wide area network) for further processing, though it should be understood that this transmission 306 may not be present in all cases, and that in some embodiments cell representations may be processed (e.g., through determination 307 of immature granulocyte subtypes, described in more detail below) at the same location where the images were captured 305.

[0039] It is also possible that first and second pluralities of images may be captured 302 in a different manner entirely. For example, in some cases capturing 302 the pluralities of images may be performed using a slice based system such as that shown in FIG. 2, rather than a flow cell based system such as that shown in FIG. 1. Accordingly, the above description of acts which may be involved in capturing 302 the first and second pluralities of images should be understood as being illustrative only, and should not be treated as liming on the scope of protection provided by this document or any related document.

[0040] C. Determining Counts

[0041] After the first and second pluralities of images had been captured 302, those pluralities of images may be used as a basis for, for each of one or more types of particles (e.g., white blood cells and platelets) of interest, determining 307 first and second counts for that type of particle. This may be done by using one machine learning model (a stained particle machine learning model) to classify images of stained particles, and another machine learning classifier (an unstained particle machine learning model) to classify images of unstained particles. These types of machine learning models may be implemented in a variety of manners, such as using the example architecture illustrated and described below in the context of FIGS. 4 and 5.

[0042] Turning now to FIG. 4, that figure illustrates a machine learning model which can be used in some embodiments in identifying images which depicted particular types of particles as part of determining 307 the first and second counts. In the architecture of FIG. 4, an input image 401 would be analyzed in a series of stages 402a-402n, each of which may be referred to as a “layer,” and which are illustrated in more detail in FIG. 5. As shown in FIG. 5, an input 501 (which, in the initial layer 502a of FIG. 5 would be the input image 401, and otherwise would be the output of the preceding layer) is provided to a layer 502 where it would be processed to generate one or more transformed images 503a-503n. This processing may include convolving the input 501 with a set of filters 504a-504n, each of which would identify a type of feature from the underlying image that would then be captured in that filter’s corresponding transformed image. For instance, as a simple example, convolving an image with the filter shown in table 1 could generate a transformed image capturing the edges from the input image 501.

[0043] [ -1 -1 -1 ]

[0044] [ -1 8 -1 ]

[0045] [ -1 -1 -1 ]

[0046] Table 1

[0047] As shown in FIG. 5, in addition to generating transformed images 503a-503n a layer may also generate a pooled image 505a-505n for each of the transformed images 503a-503n. This may be done, for example, by organizing the appropriate transformed image into a set of regions, and then replacing the values in that region with a single value, such as the maximum value for the region or the average of the values for the region. The result would be a pooled image whose resolution would be reduced relative to its corresponding transformed image based on the size of the regions it was split into (e.g., if the transformed image had NxN dimensions, and it was split into 2x2 regions, then the pooled image would have size (N / 2)x(N / 2)). These pooled images 505a-505n could then be combined into a single output image 506, in which each of the pooled images 505a-505n is treated as a separate channel in the output image 506. This output image 506 can then be provided as input to the next layer as shown in FIG. 4. Returning to the discussion of FIG. 4, after a final output image 403 has been created through the various stages 402a-402n of processing, the final output image 403 could be provided as input to a neural network 404. This may be done, for example, by providing the value of each channel of each pixel in the output image 403 to an input node of a densely connected single layer network. The output of the neural network 404 could then be treated a classification of the original input image 401. For example, in the case such as shown in FIG. 4, where a neural network 404 has multiple output nodes each of those output nodes may be treated as corresponding to a type of particle, such as “white blood cell,” “platelet” or “other.” The corresponding classification for the output node with the highest value could be treated as the type of particle depicted in the input image that resulted in that value being reached.

[0048] A machine learning model such as a model following the architecture discussed in the context of FIGS. 4 and 5 can be trained to make particle type determinations using the type of images it would be expected to see in production (e.g., images of stained particles in the case of a stained particle machine learning model, or images of unstained particles in the case of an unstained particle machine learning model) annotated with labels indicating the correct type of particle that those training images should be identified as depicting (e.g., labels as added by a human annotator). This training may include comparing labels applied by the model being trained with the ground truth labels provided by the annotation, and adjusting the values of the machine learning model ’ s parameters to minimize a loss function (e.g., cross entropy loss) for that comparison. The training can also include splitting the annotated images into multiple subsets, or folds, and then training and evaluating the model multiple times, with a different fold of training images being held back as a validation set each time (i.e., K-fold cross validation). In this way, performance metrics from each training instance can be averaged to verify the model’s generalization performance and, assuming the performance is acceptable, a final trained version of the model (e.g., whichever trained model had the best individual performance) can be used to make inferences (i.e., classify cell images) in production.

[0049] However the training takes place, once stained and unstained particle machine learning models are available, those models may be used in determining 307 first and second counts for the type(s) of particles that are of interest in a particular case. To illustrate, consider a scenario where the disclosed technology is applied to generate 310 outputs regarding white blood cells and platelets in a patient sample. In this case, first counts for both white blood cells and platelets could be determined 308 based on providing the first plurality of images to a stained particle machine learning model with output nodes corresponding to “white blood cell,” “platelet” and “other” (i.e., neither a white blood cell nor platelet), while second counts for both white blood cells and platelets could be determined 309 based on providing the second plurality of images to an unstained particle machine learning model with output nodes corresponding to “white blood cell,” “platelet” and “other”. Alternatively, in some cases counts for particular types of particles may be obtained by providing the applicable images to machine learning models trained specifically to identify particular types of particles. For example, first and second counts for “white blood cells” may be determined by providing first and second pluralities of images to machine learning models with output nodes of “white blood cell” and “other,” rather than “white blood cell,” “platelet” and “other.”

[0050] It is also possible that first and / or second counts may be determined other than using machine learning models. For instance, techniques utilizing masks to analyze pixels of an image can be utilized, as well as alternative pixel-mathematics based approaches involving analysis of pixels within an image(e.g., using techniques such as described in U.S. Pat. No. 11,403,751, issued on August 2, 2022 titled “System and method of classification of biological particles”, the entirety of which is hereby incorporated by reference)Alternatively, techniques using machine learning models which are trained to identify types of particles other than (or in addition to) those which may be of interest in a particular scenario may be utilized. For example, in a case where the disclosed technology is used to generate 310 outputs for platelets and white blood cells, the determination of first and / or second counts may be made using machine learning models trained to identify other types of particles (such as red blood cells) and / or trained to identify subtypes of particle types of interest (e.g., neutrophils, monocytes, eosinophils, basophils and lymphocytes, each of which is a type of white blood cell). In such a case, when performing a method such as shown in FIG. 3, the classification(s) which did not correspond to a particle type of interest (e.g., red blood cells) may be disregarded, while the classification(s) corresponding to a particle type of interest may be combined to determine counts for that particle type (e.g., images of neutrophils, monocytes, eosinophils, basophils and lymphocytes may simply be treated as images of white blood cells for determining a white blood cell count). Other types of variations, such as using machine learning models other than those following the architecture discussed in the context of FIGS. 4 and 5 (e.g., decision trees or support vector machines) are also possible, and will be immediately apparent to those of skill in the art in light of this disclosure. Accordingly, the above description of how implementations of the disclosed technology may determine 307 first and second counts should be understood as being illustrative only, and should not be treated as limiting.

[0051] D. Generating Output

[0052] With the requisite first and second counts having been determined 307, the process of FIG. 3 continues with generating 310 output for at least one of the one or more types of particles based on the first and second counts. This may include, for example, comparing the first and second counts (or information derived from the first and second counts) for a particular type of particle and generating 314 a flag for that type of particle. To illustrate, consider a case where the disclosed technology is used to provide assurance that a reported white blood cell concentration is accurate. In such a case, generating 310 the output may include generating 311 first and second white blood cell concentrations using calculations such as equations 1 and 2, below.

[0053] WBC_Co

[0054] Equation

[0055] WBC_Concentration_U = N_WBC_U / volume_U

[0056] Equation 2

[0057] In those equations, WBC_Concentration_S is the concentration of white blood cells in the patient sample as determined based on images of a stained portion of the patient sample (e.g., the first plurality of images). N_WBC_S is the number of white blood cells depicted in images of the stained portion of the patient sample, which may be determined based on classification of those images using a stained particle machine learning model as described previously. volume_S is the volume of the portion of the sample which was imaged in capturing the stained particle images, and may be determined by configuring the system used to capture images to capture images frame by frame without overlap between consecutive frames and multiplying the number of frames captured for the stained portion of the sample by a defined volume per frame value. This defined volume per frame value may be set by direct measurement or control of the amount of fluid in the stained portion of the patient sample. However, it may also be set by a method comprising (1) running a set of samples on both the instrument which would be used to capture the images of the stained portion of the patient sample and a predicate instrument; (2) calculate the average of N_WBC_S / N_frame_S for those samples (where N_frame_S is the number of frames captured while capturing the images of the stained portion of the patient sample); (3) calculating the average white blood cell concentration for the predicate instrument for those samples; and (4) use regression to set the defined volume per frame value as equal to the average N_WBC_S I N_frame_S divided by the average of the predicate WBC concentration. WBC_Concentration_U, N_WBC_U and volume_U would have corresponding meanings and could be determined in corresponding manners, with the differences between the sets of parameters being that the postfix “_U” indicates that applies to processing an unstained portion of the patient sample.

[0058] The concentration values - i.e., WBC_Concentration_S and WBC_Concentration_U - may then be compared with each other, and if the difference between them is greater than some threshold amount (e.g., greater than 5% of the average of WBC_Concentration_U and WBC_Concentration_S) a flag may be generated 314 indicating that the white blood cell concentration may be unreliable and / or require further action (e.g., rerunning the test to obtain a new concentration measurement). This approach may also be applied to other particle types. For example, first and second concentrations of platelets may be calculated and compared, either in addition to or as an alternative to the calculation and comparison of first and second concentrations of white blood cells. Different thresholds for generating 314 a flag may also be used. For example, in some cases a flag may be generated if the discrepancy is greater than 10% rather than 5%, or a flag may be generated if the discrepancy is 5% for one type of particle (e.g., white blood cells) but may require a 10% discrepancy for another type of particle (e.g., platelets). It is also possible that, in some cases, flags may be generated based on comparing counts themselves, rather than based on comparing values which are themselves based on counts. Accordingly, the above description of how some implementations of the disclosed technology may generate 314 flags should be understood as being illustrative only, and should not be treated as limiting. Variations are also possible in the types of outputs which may be generated 310 by implementations of the disclosed technology. To illustrate, consider a case where, rather than (or instead of) finding discrepancies between stained and unstained concentration values, stained and unstained concentration values are integrated to provide a reportable concentration which may be more accurate than either the stained or unstained concentration values. In some embodiments, this type of integration may be relatively straightforward. For example, first and second concentrations may be generated using counts derived from the stained and unstained portions of a patient sample, respectively, and then instructions may be executed 313 to cause a computer to average the first and second concentrations, thereby generating a reportable concentration value for the patient sample. However, more complicated types of integration are also possible. For example, in some cases, after it has been generated 311, a first concentration (e.g., a concentration based on images of the stained portion of the patient sample) may be compared 312 with one or more thresholds, and instructions may then be executed 313 to use those comparisons to evaluate decision rules and / or perform one or more functions to generate the ultimate reportable concentration. To illustrate, consider tables 2-4, below, which provide exemplary decision rules which an implementation of the disclosed technology may use to determine a reportable white blood cell concentration.

[0059] Table 2

[0060] Table 3

[0061] Table 4

[0062] In tables 2-4, WBC_Concentration_S and WBC_Concentration_U have the same meanings as set forth above in the context of equations 1 and 2. WBC_Concentration_final is a reportable concentration for white blood cells, threshold- 1 is a threshold below which a white blood cell concentration from a workflow optimized for normal concentrations of white blood cells (e.g., a workflow which includes staining particles in the patient sample) can expected to be statistically robust (e.g., 100 * 103white blood cells / pL). threshold_2 is a threshold above which a workflow which does not include staining particles (e.g., a workflow normally used for red blood cells, which includes greater dilution than a workflow normally used for white blood cells, and therefore is less likely to result in overlapping white blood cells when white blood cell concentration is elevated) in the patient sample can be expected to be more accurate than the workflow optimized for normal concentrations of white blood cells (e.g., 200 * 103white blood cells / pL). F(WBC_Concentration_S) is a function (e.g., a linear function, a quadratic function, a hyperbolic function, etc.) ranging from 0 to 1, which approaches 1 as WBC_Concentration_S approaches threshold_l from the right, and approaches 0 as WBC_Concentration_S approaches threshold_2 from the left. Similar instructions could also be implemented for other types of particles, and variations on the decision rules and functions from tables 2-4 (e.g., different thresholds, depending on the particle type in question and / or analyzer being used to anlayze a patient sample in a particular case) are also possible. Accoridngly, the above examples of how outputs could be generated 310 based on first and second counts without necessarily generating 314 a flag should be understood as being illustrative only, and should not be treated as limiting on the scope of protection provided by this document or any related document.

[0063] In various examples, a biological blood sample is conveyed to a hematology machine and aspirated to result in a plurality of sample portions (e.g., a first and second portion). One portion (e.g., the first portion) undergoes a staining process in order to stain at least one cell type (e.g., platelets and / or white blood cells) and a lysing process to remove another particular cell type (e.g., red blood cells). In some examples, the staining and lysing process can utilize a single reagent containing both a staining component and a lysing component (described, for instance, in US Pat. No. 9,279,750 and US Pub. No. 2021 / 0108994 which are hereby incorporated by reference in their entirety), or separate reagents which utilize a first staining reagent containing a staining component and a second, separate lysing component containing a lysing agent. The first portion can also undergo additional processing such as heating or incubation to help take on the stain, and dilution to create an even distribution. The second portion does not undergo a staining process but instead utilizes simpler sample processing such as dilution (and optionally heating). The first portion of the sample is imaged to identify particular stained cell types (e.g., white blood cells and / or platelets), and the second portion of the sample is separately imaged (e.g., before or after the first portion) to identify at least one similar cell type as the process of the first portion (e.g., white blood cells and / or platelets). This will then result in at least once cell type (e.g., white blood cells or platelets) which will have two counts or concentrations (one based on the staining process, and one based on the non-staining process).

[0064] In one example specific for white blood cell analysis utilizing two imaging counts or concentrations, the staining process will result in differentiation or subtyping among white blood cells, by identification of at least a 5-part differential (monocyte, eosinophils, basophil, neutrophil, lymphocytes, and optionally immature granulocytes) - since, for instance, the staining helps identify nuclear features that a classification algorithm (e.g., one based on machine learning techniques or pixel math analysis techniques) can use to help differentiate, as well as an overall count of white blood cells. The second process which does not utilize staining will also result in an overall count or concentration of white blood cells but not differentiation within the differential since the lack of staining will make it difficult to subtype into the respective white blood cell populations. The two processes will result in dual counts or concentrations for at least one particular cell type (e.g., white blood cells and / or platelets). These dual counts can then be used in various ways, for instance by flagging the result if two counts are significantly different (e.g., the differences exceed a certain numerical or percentage threshold), utilizing a confidence assessment to report the more plausible result (e.g., each number being reported with an associated confidence level, which can be part of the cell reporting process), utilizing a confidence assessment to flag one or both results if the confidence assessment is below a particular threshold, reporting both results to the user, or averaging both results / counts to present to the user.

[0065] The term count and concentration are to be construed broadly and are not intended to be limited. For instance, count can refer to an actual numerical count of cells or refer to a concentration value which would report a count relative to a volumetric parameter.

[0066] III. Examples

[0067] As a further illustration of potential implementations and applications of the disclosed technology, the following examples are provided of non-exhaustive ways in which the teachings herein may be combined or applied. It should be understood that the following examples are not intended to restrict the coverage of any claims that may be presented at any time in this application or in subsequent filings of this application. No disclaimer is intended. The following examples are being provided for nothing more than merely illustrative purposes. It is contemplated that the various teachings herein may be arranged and applied in numerous other ways. It is also contemplated that some variations may omit certain features referred to in the below examples. Therefore, none of the aspects or features referred to below should be deemed critical unless otherwise explicitly indicated as such at a later date by the inventors or by a successor in interest to the inventors. If any claims are presented in this application or in subsequent filings related to this application that include additional features beyond those referred to below, those additional features shall not be presumed to have been added for any reason relating to patentability.

[0068] Example 1

[0069] A method comprising: preparing first and second portions of a patient sample, wherein preparing the first and second portions comprises staining a plurality of particles in the first portion of the patient sample; capturing a first plurality of images and a second plurality of images, wherein: the first plurality of images is a plurality of images of the first portion of the patient sample captured after staining the plurality of particles in the first portion of the patient sample; the second plurality of images is a plurality of images of the second portion of the patient sample, wherein no particles comprised by the second portion of the patient sample are stained when the plurality of images of the second portion of the patient sample are captured; for each of one or more types of particles, determining a first count for that type of particle and a second count for that type of particle, wherein the first count for that type of particles is determined based on the plurality of images of the first portion of the patient sample and the second count for that type of particles is determined based on the plurality of images of the second portion of the patient sample; and for at least one of the one or more types of particles, generating an output corresponding to that type of particle based on the first count for that type of particle and the second count for that type of particle.

[0070] Example 2

[0071] The method of example 1 , wherein the one or more types of particles are platelets and white blood cells.

[0072] Example 3

[0073] The method of any of examples 1-2, wherein, for each of the one or more types of particles: determining the first count for that type of particle is performed using a stained particle machine learning model corresponding to that type of particle, wherein the stained particle machine learning model corresponding to that type of particle is trained to identify images depicting stained particles of that type of particle; determining the second count for that type of particle is performed using an unstained particle machine learning model corresponding to that type of particle, wherein the unstained particle machine learning model for that type of particle is trained to identify images depicting unstained particles of that type of particle; and neither the first machine learning model corresponding to that type of particle nor the second machine learning model corresponding to that type of particle is used in determining any count for any other type of particle.

[0074] Example 4

[0075] The method of any of examples 1 -2, wherein, for each of the one or more types of particles: determining the first count for that type of particle is performed using a stained particle machine learning model, wherein the stained particle machine learning model is trained to classify images of stained particles into classes corresponding to the one or more types of particles; determining the second count for that type of particle is performed using an unstained particle machine learning model, wherein the unstained particle machine learning model is trained to classify images of unstained particles into classes corresponding to the one or more types of particles; and the stained particle machine learning model and the unstained particle machine learning model used in determining the first and second counts for that type of particle are the same machine learning models used for determining counts for each other type of particle from the one or more types of particles.

[0076] Example 5

[0077] The method of any of examples 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; and executing computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to average the first concentration for that type of particle and the second concentration for that type of particle.

[0078] Example 6 The method of any of examples 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle; comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is greater than a concentration threshold for that type of particle; and executing computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to: in the event that the first concentration for that type of particle is greater than the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle; and in the event that the first concentration for that type of particle is less than or equal to the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle.

[0079] Example 7

[0080] The method of any of examples 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle; comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is less than a first concentration threshold for that type of particle; and executing computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to: in the event that the first concentration for that type of particle is less than the first concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle; in the event that the first concentration for that type of particle is greater than or equal to the first concentration threshold for that type of particle and is also less than a second concentration threshold for that type of particle, define the reportable concentration for that type of particle as being an average of the first concentration for that type of particle and a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle; and in the event that the first concentration for that type of particle is greater than or equal to the second concentration threshold for that type of particle, define the reportable concentration for that type of particle as equal to the second concentration for that type of particle.

[0081] Example 8

[0082] The method of any of examples 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; and executing computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to determine the output corresponding to that type of particle based on a confidence for the first concentration for that type of particle and a confidence for the second concentration for that type of particle.

[0083] Example 9

[0084] The method of example 8, wherein the computer executable instructions stored on the non- transitory computer readable medium comprise instructions to generate a flag for that type of particle based on the confidence for the first concentration and the confidence for the second concentration both being below a confidence threshold.

[0085] Example 10

[0086] The method of any of examples 1-9, wherein for the at least one of the one or more types of particles, generating the output corresponding to that type of particle comprises generating a flag for that type of particle based on a discrepancy between a first value based on the first count for that type of particle and a second value based on the second count for that type of particle.

[0087] Example 11

[0088] The method of any of examples 1-10, wherein, for each portion of the patient sample, capturing the plurality of images of that portion of the patient sample comprises: establishing a flow of alignment fluid from an alignment fluid reservoir into a flow cell; creating a sample stream comprising sample fluid from that portion of the patient sample and a sheath of alignment fluid surrounding the sample fluid based on injecting the sample fluid from a channel into the flow of alignment fluid; and using a camera focused on a viewing area of the flow cell to capture the plurality of images of that portion of the patient sample as the sample stream is flowing through the viewing area of the flow cell.

[0089] Example 12

[0090] The method of example 11, wherein: the method comprises, after capturing the plurality of images of the first portion of the patient sample and capturing the plurality of images of the second portion of the patient sample, transferring the plurality of images of the first portion of the patient sample and the plurality of images of the second portion of the patient sample to a remote location over a network connection; and for each of the one or more types of particles, determining the first count for that type of particle, and determining the second count for that type of particle are both performed at the remote location.

[0091] Example 13

[0092] A biological analysis system comprising: one or more processors; and a non-transitory computer readable medium having stored thereon instructions operable to, when executed by the one or more processors, perform the method of any of examples 1-12.

[0093] Example 14

[0094] A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of any one of the methods of examples 1 to 12. Example 15

[0095] A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of any one of the methods of examples 1 to 12.

[0096] Example 16

[0097] A biological analysis system, comprising: one or more processors; and one or more non- transitory computer readable mediums storing instructions operable to, when executed by the one or more processors, perform acts comprising: preparing first and second portions of a patient sample, wherein preparing the first and second portions comprises staining a plurality of particles in the first portion of the patient sample; capturing a first plurality of images and a second plurality of images, wherein: the first plurality of images is a plurality of images of the first portion of the patient sample captured after staining the plurality of particles in the first portion of the patient sample; the second plurality of images is a plurality of images of the second portion of the patient sample, wherein no particles comprised by the second portion of the patient sample are stained when the plurality of images of the second portion of the patient sample are captured; for each of one or more types of particles determining a first count for that type of particle and a second count for that type of particle, wherein the first count for that type of particles is determined based on the plurality of images of the first portion of the patient sample and the second count for that type of particles is determined based on the plurality of images of the second portion of the patient sample; and for at least one of the one or more types of particles, generating an output corresponding to that type of particle based on the first count for that type of particle and the second count for that type of particle.

[0098] Example 17

[0099] The system of example 16, wherein the one or more types of particles are platelets and white blood cells.

[0100] Example 18

[0101] The system of any of examples 16-17, wherein, for each of the one or more types of particles: determining the first count for that type of particle is performed using a stained particle machine learning model corresponding to that type of particle, wherein the stained particle machine learning model corresponding to that type of particle is trained to identify images depicting stained particles of that type of particle; determining the second count for that type of particle is performed using an unstained particle machine learning model corresponding to that type of particle, wherein the unstained particle machine learning model for that type of particle is trained to identify images depicting unstained particles of that type of particle; and neither the first machine learning model corresponding to that type of particle nor the second machine learning model corresponding to that type of particle is used in determining any count for any other type of particle.

[0102] Example 19

[0103] The system of any of examples 16-17, wherein, for each of the one or more types of particles: determining the first count for that type of particle is performed using a stained particle machine learning model, wherein the stained particle machine learning model is trained to classify images of stained particles into classes corresponding to the one or more types of particles; determining the second count for that type of particle is performed using an unstained particle machine learning model, wherein the unstained particle machine learning model is trained to classify images of unstained particles into classes corresponding to the one or more types of particles; and the stained particle machine learning model and the unstained particle machine learning model used in determining the first and second counts for that type of particle are the same machine learning models used for determining counts for each other type of particle from the one or more types of particles.

[0104] Example 20

[0105] The system of any of examples 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; and executing computer executable instructions comprising instructions to average the first concentration for that type of particle and the second concentration for that type of particle.

[0106] Example 21

[0107] The system of any of examples 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle; comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is greater than a concentration threshold for that type of particle; and executing computer executable instructions comprising instructions to: in the event that the first concentration for that type of particle is greater than the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle; and in the event that the first concentration for that type of particle is less than or equal to the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle.

[0108] Example 22

[0109] The system of any of examples 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle; comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is less than a first concentration threshold for that type of particle; and executing computer executable instructions comprising instructions to: in the event that the first concentration for that type of particle is less than the first concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle ; in the event that the first concentration for that type of particle is greater than or equal to the first concentration threshold for that type of particle and is also less than a second concentration threshold for that type of particle, define the reportable concentration for that type of particle as being an average of the first concentration for that type of particle and a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle; and in the event that the first concentration for that type of particle is greater than or equal to the second concentration threshold for that type of particle, define the reportable concentration for that type of particle as equal to the second concentration for that type of particle.

[0110] Example 23

[0111] The system of any of examples 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; and executing computer executable instructions comprising instructions to determine the output corresponding to that type of particle based on a confidence for the first concentration for that type of particle and a confidence for the second concentration for that type of particle.

[0112] Example 24

[0113] The system of example 23, wherein, for each of the at least one of the one or more types of particles, the computer executable instructions stored on the one or more non-transitory computer readable mediums comprise instructions to generate a flag for that type of particle based on the confidence for the first concentration and the confidence for the second concentration both being below a confidence threshold.

[0114] Example 25

[0115] The system of any of examples 16-24, wherein for the at least one of the one or more types of particles, generating the output corresponding to that type of particle comprises generating a flag for that type of particle based on a discrepancy between a first value based on the first count for that type of particle and a second value based on the second count for that type of particle.

[0116] Example 26

[0117] The system of any of examples 16-25, wherein the system comprises: a flow cell; a camera configured to capture the first plurality of images via flow imaging of the first portion of the patient sample as it passes through a viewing area of the flow cell; an alignment fluid reservoir in fluid communication with the viewing area of the flow cell; a channel adapted to inject the first portion of the patient sample into a flow of the alignment fluid, thereby forming a sample stream comprising the first portion of the patient sample and a sheath of alignment fluid surrounding the sample fluid.

[0118] Example 27

[0119] The system of example 26, wherein: the acts comprise, after capturing the plurality of images of the first portion of the patient sample and capturing the plurality of images of the second portion of the patient sample, transferring the plurality of images of the first portion of the patient sample and the plurality of images of the second portion of the patient sample to a remote location over a network connection; and for each of the one or more types of particles, determining the first count for that type of particle, and determining the second count for that type of particle are both performed at the remote location.

[0120] Example 28

[0121] A method of computer implemented biological analysis comprising performing the acts the instructions stored on the one or more non-transitory computer readable mediums of the system of any of examples 16-27 are to perform when executed.

[0122] Example 29

[0123] A non-transitory computer readable medium storage medium comprising instructions to perform the acts which the instructions stored on the one or more non-transitory computer readable mediums of the system of any of examples 16-27 are to perform when executed. Example 30

[0124] A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the acts which the instructions stored on the one or more non-transitory computer readable mediums of the system of any of examples 16-27 are to perform when executed.

[0125] IV. Interpretation

[0126] Each of the calculations or operations described herein may be performed using a computer or other processor having hardware, software, and / or firmware. The various method steps may be performed by modules, and the modules may comprise any of a wide variety of digital and / or analog data processing hardware and / or software arranged to perform the method steps described herein. The modules optionally comprising data processing hardware adapted to perform one or more of these steps by having appropriate machine programming code associated therewith, the modules for two or more steps (or portions of two or more steps) being integrated into a single processor board or separated into different processor boards in any of a wide variety of integrated and / or distributed processing architectures. These methods and systems will often employ a tangible media embodying machine-readable code with instructions for performing the method steps described above. Suitable tangible media may comprise a memory (including a volatile memory and / or a non-volatile memory), a storage media (such as a magnetic recording on a floppy disk, a hard disk, a tape, or the like; on an optical memory such as a CD, a CD-R / W, a CD-ROM, a DVD, or the like; or any other digital or analog storage media), or the like.

[0127] All patents, patent publications, patent applications, journal articles, books, technical references, and the like discussed in the instant disclosure are incorporated herein by reference in their entirety for all purposes.

[0128] Different arrangements of the components depicted in the drawings or described above, as well as components and steps not shown or described are possible. Similarly, some features and sub-combinations are useful and may be employed without reference to other features and sub-combinations. Embodiments of the invention have been described for illustrative and not restrictive purposes, and alternative embodiments will become apparent to readers of this patent. In certain cases, method steps or operations may be performed or executed in differing order, or operations may be added, deleted or modified. It can be appreciated that, in certain aspects of the invention, a single component may be replaced by multiple components, and multiple components may be replaced by a single component, to provide an element or structure or to perform a given function or functions. Except where such substitution would not be operative to practice certain embodiments of the invention, such substitution is considered within the scope of the invention. Accordingly, the claims should not be treated as limited to the examples, drawings, embodiments and illustrations provided above, but instead should be understood as having the scope provided when their terms are given their broadest reasonable interpretation as provided by a general purpose dictionary, except that when a term or phrase is indicated as having a particular meaning under the heading Explicit Definitions, it should be understood as having that meaning when used in the claims.

[0129] Explicit Definitions

[0130] It should be understood that, in the above examples and the claims, a statement that something is “based on” something else should be understood to mean that it is determined at least in part by the thing that it is indicated as being based on. To indicate that something must be completely determined based on something else, it is described as being “based EXCLUSIVELY on” whatever it must be completely determined by.

[0131] It should be understood that, in the above examples and claims, the term “set” should be understood as one or more things which are grouped together.

Claims

What is claimed is:

1. A computer-enabled method of biological analysis comprising: preparing first and second portions of a patient sample, wherein preparing the first and second portions comprises staining a plurality of particles in the first portion of the patient sample; capturing a first plurality of images and a second plurality of images, wherein: the first plurality of images is a plurality of images of the first portion of the patient sample captured after staining the plurality of particles in the first portion of the patient sample; the second plurality of images is a plurality of images of the second portion of the patient sample, wherein no particles comprised by the second portion of the patient sample are stained when the plurality of images of the second portion of the patient sample are captured; for each of one or more types of particles, determining a first count for that type of particle and a second count for that type of particle, wherein the first count for that type of particles is determined based on the plurality of images of the first portion of the patient sample and the second count for that type of particles is determined based on the plurality of images of the second portion of the patient sample; and for at least one of the one or more types of particles, generating an output corresponding to that type of particle based on the first count for that type of particle and the second count for that type of particle.

2. The method of claim 1 , wherein the one or more types of particles are platelets and white blood cells.

3. The method of any of claims 1-2, wherein, for each of the one or more types of particles: determining the first count for that type of particle is performed using a stained particle machine learning model corresponding to that type of particle, wherein the stained particle machine learning model corresponding to that type of particle is trained to identify images depicting stained particles of that type of particle; determining the second count for that type of particle is performed using an unstained particle machine learning model corresponding to that type of particle,wherein the unstained particle machine learning model for that type of particle is trained to identify images depicting unstained particles of that type of particle; and neither the first machine learning model corresponding to that type of particle nor the second machine learning model corresponding to that type of particle is used in determining any count for any other type of particle.

4. The method of any of claims 1-2, wherein, for each of the one or more types of particles: determining the first count for that type of particle is performed using a stained particle machine learning model, wherein the stained particle machine learning model is trained to classify images of stained particles into classes corresponding to the one or more types of particles; determining the second count for that type of particle is performed using an unstained particle machine learning model, wherein the unstained particle machine learning model is trained to classify images of unstained particles into classes corresponding to the one or more types of particles; and the stained particle machine learning model and the unstained particle machine learning model used in determining the first and second counts for that type of particle are the same machine learning models used for determining counts for each other type of particle from the one or more types of particles.

5. The method of any of claims 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; and executing computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to average the first concentration for that type of particle and the second concentration for that type of particle.

6. The method of any of claims 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle ; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle; comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is greater than a concentration threshold for that type of particle; and executing computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to: in the event that the first concentration for that type of particle is greater than the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle; and in the event that the first concentration for that type of particle is less than or equal to the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle.

7. The method of any of claims 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle;comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is less than a first concentration threshold for that type of particle; and executing computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to: in the event that the first concentration for that type of particle is less than the first concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle; in the event that the first concentration for that type of particle is greater than or equal to the first concentration threshold for that type of particle and is also less than a second concentration threshold for that type of particle, define the reportable concentration for that type of particle as being an average of the first concentration for that type of particle and a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle; and in the event that the first concentration for that type of particle is greater than or equal to the second concentration threshold for that type of particle, define the reportable concentration for that type of particle as equal to the second concentration for that type of particle.

8. The method of any of claims 1-4, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle ; generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; andexecuting computer executable instructions stored on a non-transitory computer readable medium, wherein the computer executable instructions comprise instructions to determine the output corresponding to that type of particle based on a confidence for the first concentration for that type of particle and a confidence for the second concentration for that type of particle.

9. The method of claim 8, wherein the computer executable instructions stored on the non-transitory computer readable medium comprise instructions to generate a flag for that type of particle based on the confidence for the first concentration and the confidence for the second concentration both being below a confidence threshold.

10. The method of any of claims 1-9, wherein for the at least one of the one or more types of particles, generating the output corresponding to that type of particle comprises generating a flag for that type of particle based on a discrepancy between a first value based on the first count for that type of particle and a second value based on the second count for that type of particle.

11. The method of any of claims 1-10, wherein, for each portion of the patient sample, capturing the plurality of images of that portion of the patient sample comprises: establishing a flow of alignment fluid from an alignment fluid reservoir into a flow cell; creating a sample stream comprising sample fluid from that portion of the patient sample and a sheath of alignment fluid surrounding the sample fluid based on injecting the sample fluid from a channel into the flow of alignment fluid; and using a camera focused on a viewing area of the flow cell to capture the plurality of images of that portion of the patient sample as the sample stream is flowing through the viewing area of the flow cell.

12. The method of claim 11 , wherein: the method comprises, after capturing the plurality of images of the first portion of the patient sample and capturing the plurality of images of the second portion of the patient sample, transferring the plurality of images of the first portion of the patientsample and the plurality of images of the second portion of the patient sample to a remote location over a network connection; and for each of the one or more types of particles, determining the first count for that type of particle, and determining the second count for that type of particle are both performed at the remote location.

13. A biological analysis system, comprising: one or more processors; and a non-transitory computer readable medium having stored thereon instructions operable to, when executed by the one or more processors, perform the method of any preceding claim.

14. A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of any one of the methods of claims 1 to 12.

15. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of any one of the methods of claims 1 to 12.

16. A biological analysis system, comprising: one or more processors; and one or more non-transitory computer readable mediums storing instructions operable to, when executed by the one or more processors, perform acts comprising: preparing first and second portions of a patient sample, wherein preparing the first and second portions comprises staining a plurality of particles in the first portion of the patient sample; capturing a first plurality of images and a second plurality of images, wherein: the first plurality of images is a plurality of images of the first portion of the patient sample captured after staining the plurality of particles in the first portion of the patient sample;the second plurality of images is a plurality of images of the second portion of the patient sample, wherein no particles comprised by the second portion of the patient sample are stained when the plurality of images of the second portion of the patient sample are captured; for each of one or more types of particles determining a first count for that type of particle and a second count for that type of particle, wherein the first count for that type of particles is determined based on the plurality of images of the first portion of the patient sample and the second count for that type of particles is determined based on the plurality of images of the second portion of the patient sample; and for at least one of the one or more types of particles, generating an output corresponding to that type of particle based on the first count for that type of particle and the second count for that type of particle.

17. The system of claim 16, wherein the one or more types of particles are platelets and white blood cells.

18. The system of any of claims 16-17, wherein, for each of the one or more types of particles: determining the first count for that type of particle is performed using a stained particle machine learning model corresponding to that type of particle, wherein the stained particle machine learning model corresponding to that type of particle is trained to identify images depicting stained particles of that type of particle; determining the second count for that type of particle is performed using an unstained particle machine learning model corresponding to that type of particle, wherein the unstained particle machine learning model for that type of particle is trained to identify images depicting unstained particles of that type of particle; and neither the first machine learning model corresponding to that type of particle nor the second machine learning model corresponding to that type of particle is used in determining any count for any other type of particle.

19. The system of any of claims 16-17, wherein, for each of the one or more types of particles:determining the first count for that type of particle is performed using a stained particle machine learning model, wherein the stained particle machine learning model is trained to classify images of stained particles into classes corresponding to the one or more types of particles; determining the second count for that type of particle is performed using an unstained particle machine learning model, wherein the unstained particle machine learning model is trained to classify images of unstained particles into classes corresponding to the one or more types of particles; and the stained particle machine learning model and the unstained particle machine learning model used in determining the first and second counts for that type of particle are the same machine learning models used for determining counts for each other type of particle from the one or more types of particles.

20. The system of any of claims 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; and executing computer executable instructions comprising instructions to average the first concentration for that type of particle and the second concentration for that type of particle.

21. The system of any of claims 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle;comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is greater than a concentration threshold for that type of particle; and executing computer executable instructions comprising instructions to: in the event that the first concentration for that type of particle is greater than the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle; and in the event that the first concentration for that type of particle is less than or equal to the concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle.

22. The system of any of claims 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle; and generating the output corresponding to that type of particle comprises: determining a first concentration for that type of particle based on the first count for that type of particle; comparing the first concentration for that type of particle with a set of thresholds by performing acts comprising determining if the first concentration for that type of particle is less than a first concentration threshold for that type of particle ; and executing computer executable instructions comprising instructions to: in the event that the first concentration for that type of particle is less than the first concentration threshold for that type of particle, define the reportable concentration for that type of particle as being equal to the first concentration for that type of particle;in the event that the first concentration for that type of particle is greater than or equal to the first concentration threshold for that type of particle and is also less than a second concentration threshold for that type of particle, define the reportable concentration for that type of particle as being an average of the first concentration for that type of particle and a second concentration for that type of particle, wherein the second concentration for that type of particle is based on the second count for that type of particle; and in the event that the first concentration for that type of particle is greater than or equal to the second concentration threshold for that type of particle, define the reportable concentration for that type of particle as equal to the second concentration for that type of particle.

23. The system of any of claims 16-19, wherein, for each of the at least one of the one or more types of particles: the output corresponding to that type of particle is a reportable concentration for that type of particle ; generating the output corresponding to that type of particle comprises: generating a first concentration for that type of particle based on the first count for that type of particle, and a second concentration for that type of particle based on the second count for that type of particle; and executing computer executable instructions comprising instructions to determine the output corresponding to that type of particle based on a confidence for the first concentration for that type of particle and a confidence for the second concentration for that type of particle.

24. The system of claim 23, wherein, for each of the at least one of the one or more types of particles, the computer executable instructions stored on the one or more non- transitory computer readable mediums comprise instructions to generate a flag for that type of particle based on the confidence for the first concentration and the confidence for the second concentration both being below a confidence threshold.

25. The system of any of claims 16-24, wherein for the at least one of the one or more types of particles, generating the output corresponding to that type of particle comprises generating a flag for that type of particle based on a discrepancy between a first value based on the first count for that type of particle and a second value based on the second count for that type of particle.

26. The system of any of claims 16-25, wherein the system comprises: a flow cell; a camera configured to capture the first plurality of images via flow imaging of the first portion of the patient sample as it passes through a viewing area of the flow cell; an alignment fluid reservoir in fluid communication with the viewing area of the flow cell; a channel adapted to inject the first portion of the patient sample into a flow of the alignment fluid, thereby forming a sample stream comprising the first portion of the patient sample and a sheath of alignment fluid surrounding the sample fluid.

27. The system of claim 26, wherein: the acts comprises, after capturing the plurality of images of the first portion of the patient sample and capturing the plurality of images of the second portion of the patient sample, transferring the plurality of images of the first portion of the patient sample and the plurality of images of the second portion of the patient sample to a remote location over a network connection; and for each of the one or more types of particles, determining the first count for that type of particle, and determining the second count for that type of particle are both performed at the remote location.

28. A method of computer implemented biological analysis comprising performing the acts the instructions stored on the one or more non-transitory computer readable mediums of the system of any of claims 16-27 are to perform when executed.

29. A non-transitory computer readable medium storage medium comprising instructions to perform the acts which the instructions stored on the one or more non-transitorycomputer readable mediums of the system of any of claims 16-27 are to perform when executed.

30. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the acts which the instructions stored on the one or more non-transitory computer readable mediums of the system of any of claims 16-27 are to perform when executed.

Images