Detecting sizes of blood sample particles in images

Abstract

Sizes of particles depicted in images captured of a blood sample by a blood analysis instrument may be calculated by processing those images. For example, a method for calculating a size of a particle in a blood sample imaged by a blood analysis instrument may include receiving an image depicting the particle in the blood sample, and identifying a boundary for the particle depicted in the image. A major and a minor axis may then be defined based on the boundary, and the size of the particle may be determined based on the major and minor axes.

Description

DETECTING SIZES OF BLOOD SAMPLE PARTICLES IN IMAGESCROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority from U.S. provisional application 63 / 650,502, filed May 22, 2024 for “Detecting Sizes of Blood Sample Particles in Images,” the disclosure of which is hereby incorporated by reference in its entirety.BACKGROUND

[0002] Blood cell analysis is a commonly performed medical test for providing an overview of a patient's health status. A blood sample can be drawn from a patient's body and stored in a test tube containing an anticoagulant to prevent clotting. A whole blood sample normally comprises three major classes of blood cells including red blood cells (erythrocytes), white blood cells (leukocytes) and platelets (thrombocytes). Each class can be further divided into subclasses of members. For example, five major types or subclasses of white blood cells (WBCs) have different shapes and functions. White blood cells may include neutrophils, lymphocytes, monocytes, eosinophils, and basophils. There are also subclasses of the red blood cell types. The appearances of particles in a sample may differ according to pathological conditions, cell maturity and other causes. Red blood cell subclasses may include reticulocytes and nucleated red blood cells.

[0003] When performing blood cell analysis using images of particles from a blood sample, it may be difficult to determine the size of an imaged particle. This may pose an obstacle to identification of abnormalities such as giant platelets (i.e., platelets with a diameter greater than 7pm, usually from 10pm-20pm). Accordingly, there is a need for technology which allows for the size of particles in a blood sample to be directly determined from captured images.BRIEF SUMMARY

[0004] The present disclosure relates to systems and methods for calculating a size of a particle in a blood sample imaged by a blood analysis imaging. Such a method may include receiving an image depicting the particle in the blood sample, and identifying a boundary for the particledepicted in the image. A major and a minor axis may then be defined based on the boundary, and the size of the particle may be determined based on the major and minor axes.

[0005] The present disclosure further relates to system and methods for identifying subpopulations of one or more cell types, such as by utilizing size related measurements that are obtained by blood analysis imaging.

[0006] The disclosed technology may also be implemented in other manners, such as in the form of systems or computer readable media programmed to performed methods such as described above. Accordingly, the above description of a method which may be implemented based on this disclosure should be understood as being illustrative only, and should not be treated as limiting.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] 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:

[0008] FIG. l is a schematic illustration, partly in section and not to scale, showing operational aspects of an exemplary flowcell which may be used in an analyzer configured to capture and analyze images.

[0009] FIG. 2 illustrates a method which may be used to calculate the size of a particle from a blood sample.

[0010] FIG. 3 illustrates a method which for identifying cell subpopulations using size information.

[0011] FIG. 4 illustrates a method which may be used to identify red blood cell subtypes.

[0012] FIG. 5 illustrates a potential population distribution of red blood cell sizes.

[0013] 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.DETAILED DESCRIPTION

[0014] The present disclosure relates to calculating the sizes of particles in blood samples imaged using a hematology analysis instrument or hematology analyzer. In one example, the hematology analyzer utilizes static or slide-based imaging. In one example, the hematology analyzer utilizes flow imaging principles (that is flowing a blood sample past an imaging device). An example of the type of instrument which may be used with this technology is shown in FIG. 1, which shows an exemplary flowcell 22 which may be used in an analyzer for conveying a sample fluid through a viewing zone 23 of a high optical resolution imaging device 24 (e.g., a camera) in a configuration for imaging microscopic particles in a sample flow stream 32 using digital image processing. Flowcell 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. Flowcell 22 is also coupled to one or more sources 27 of a particle and / or intracellular organelle alignment liquid (PIOAL) / sheath fluid, such as a clear glycerol solution having a viscosity that is greater than the viscosity of the sample fluid, an example of which is disclosed in U.S. Pat. Nos. 9,316,635 and 10,451,612, the disclosures of which are hereby incorporated by reference in their entirety.

[0015] 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 flowcell 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 besupplied 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 flow stream 32. The sample flow stream 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 charge couple device (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.

[0016] 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 flowcell.

[0017] The digital high optical resolution imaging device 24 with objective lens 46 is directed along an optical axis that intersects the ribbon-shaped sample flow stream 32. The relative distance between the objective 46 and the flowcell 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 flowcell such as shown in FIG. 1 is provided in U.S. Patent 9,322,752, entitled “Flowcell 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. Descriptions of approaches which may be used for focusing in an imaging system such as shown in FIG. 1 are provided in Published App. No. 2024 / 0357232 titled “Focus Quality Determination through Multi-Layer Processing,” filed onJune 11, 2024, 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 W02023 / 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.

[0018] When an image depicting a blood sample particle (e.g., a blood cell) is captured using a blood analysis instrument including a flowcell such as shown in FIG. 1, a size for that particle may be calculated using a method such as shown in FIG. 2. As shown in that figure, calculation of a size of a blood sample particle may include providing a blood sample to the analysis instrument, and receiving 201 an image depicting the particle whose size is to be calculated. This may be done, for example, by continuously capturing non-overlapping images of a sample fluid flow as it flows through a viewing area of a flowcell such as that shown in FIG. 1. After the image has been received 201, it may be processed to identify 202 a boundary for the particle. This may be done in a variety of manners. For example, in some case identifying 202 a boundary for the particle may be performed using a two-step process in which foreground and background portions of the image are separated from one another (e.g., by applying an Otsu filter to the image, or by applying a threshold where pixels in the image are treated as foreground or background based on whether their brightness is above or below a threshold value), and the boundary of the particle is then identified using a contour finding algorithm such as the Chan-Vese algorithm. As another example, in some cases, a boundary may be identified by classifying pixels as foreground, or background, or boundary pixels, based on comparing their neighbors to a brightness threshold, and then classifying the pixels based on whether their neighbors were above or below the threshold (e.g., a pixel may be treated as a foreground or background pixel if all of its neighbors were above or below a brightness threshold, and may be treated as a border pixel if some of its neighbors were above the threshold and some were below the threshold). Other approaches, such as training a machine learning model to classify pixels in an image as either foreground, background or border pixels, are also possible, and could be implemented by those of skill in the art in light of this disclosure.Accordingly, the exemplary approaches described above to identifying 202 a boundary for a particle should be understood as being illustrative only, and should not be treated as limiting.

[0019] However it is identified 202, once the boundary of a blood sample particle has been identified, that boundary may be used to determine 203 a major axis and a minor axis for the particle. This may include selecting a first point on the particle boundary to use for defining the major axis. For example, the distances of opposing points around the boundary of the particle may be measured, and an endpoint of a longest line between a pair of opposing points may be treated as the selected first point. Other ways of selecting the first point (e.g., randomly) are also possible, and may be used in some implementations. Once the first point has been selected, the straight line distance between that point and every other point on the boundary of the particle may be measured, and the line between the selected first point and the point on the boundary of the particle which has the largest straight line distance from the selected first point can be identified as the major axis. A line which is perpendicular to the major axis and which has the farthest distance between the points where it intersects with the particle boundary can then be identified as the minor axis. These axes can then be used to determine 204 a size for the particle. For example, the major and minor axes can be used to define an ellipse corresponding to the particle (e.g., an ellipse having a major axis with length in pixels equal to the length of the major axis for the particle, and a minor axis with a length in pixels equal to the length of the minor axis for the particle), and the area in pixels of the corresponding ellipse could be multiplied by a pixel to pm2conversion factor, which conversion factor may have a value between 0.05 pm2 / pixel and 2.0 pm2 / pixel, with the actual factor being used in an particular situation potentially having been determined by the manufacturer of the blood sample analysis instrument used to capture the particle image, based on factors such as the level of magnification, the field of view, and the distance between the analyzer’s camera and the viewing area of the flowcell. In this way, can be used to convert between blood sample particle images captured using a flowcell as shown in FIG. 1, and size measurements such as may be used for various diagnostic and / or analytic purposes.

[0020] Once a particle size has been determined (e.g., using a method such as illustrated in FIG. 2), it may be applied in a variety of manners. For instance, particular cell classifiers can utilize sizeas an element in classifying a particular cell type. In some examples, a classifier can utilize a set of mathematical rules to assign particular cell types based on a plurality of variables (one being size), where a cell determination or label is made based on set of rules - in other words, a deterministic based classification based on a series of measurement-based rules including a size parameter. One example of this is provided in international application WO 2024 / 138139 for “Population Based Cell Classification,” the disclosure of which is hereby incorporated by reference in its entirety). Cell size information can be used in additional ways - for instance, displayed in a user interface, for instance in conjunction with cell images to provide additional information about cells.

[0021] The aforementioned FIG. 2 provides one exemplary process for obtaining size information. In some examples, size information can be used to subclassify particles among a plurality of particle subtypes. In some examples further disclosed herein, fixed size values (e g., pre- established size values) can be used to establish the plurality of particle subtypes, or alternatively dynamic or not fixed size values (e.g., established during the analytical process) can be used.

[0022] A method which may be performed to provide such subclassifications is illustrated in FIG. 3. In such a method, initially, a population of imaged blood cells may be identified 301. This may be done using a cell classifier - such as a neural network based classifier as described in international application PCT / US24 / 61792 for “Systems and Methods for Integrating Stained and Unstained Sample Processing” or a population based classifier such as described in international application WO 2024 / 138139 for “Population Based Cell Classification,” the disclosures of each of which are hereby incorporated by reference in their entirety. Sizes may also be obtained 302 for the imaged blood cells, such as using techniques as described previously in the context of FIG. 2. Those sizes may then be used to identify 303 a plurality of subpopulations. To illustrate, consider the example of platelets, which can be further classified into subtypes of platelets (e.g., regular or typical platelets), large platelets, and giant platelets. Given that these subclassifications differ from each other principally based on size, size information such as could be derived using the disclosed technology could be used to provide these further platelet subclassifications, for example, by comparing the sizes of particlesidentified as platelets with various predefined thresholds. For instance, to identify normal (i.e., not large and not giant) platelet cells, a diameter threshold of about 4 pm may be applied to a major diameter identified when sizing the platelets, and platelets with a diameter below that threshold may be identified as normal platelets. Platelets with a diameter threshold above about 7 pm are then classified as giant platelets. The remaining platelets (i.e., platelets whose sizes fall between the threshold for normal and giant platelets) may then be treated as large platelets. This example would utilize a fixed threshold type concept where fixed or pre-programmed ranges or measurements are used to demarcate the subpopulations.

[0023] Other approaches may also be used to identify 303 subpopulations, for example a dynamic threshold type concept where the ranges or measurements used to demarcate the subpopulations are not a preset value and are instead determined during the analytical process.. For example, the distribution of cell sizes within a population may be analyzed (e.g., as a graphical population distribution like a histogram or chart), and if multiple peaks are identified in the distribution, then those peaks may be treated as representing distinct subpopulations - given each peak would correspond with a relatively larger subpopulation associated with a particular cell size, which would point to a distinct subpopulation within the broader population. Note, the histogram or population distribution can either be a real or virtual process. In a virtual process, the system would analyze size data and look for population spikes associated with a subpopulation, which would in essence be analogous to analyzing a population-type graphical distribution but would not necessarily require creating or analyzing an actual graph. In a real process, the system would present and analyze the data as a physical population distribution (e.g., a population chart such as a histogram) and analyze the distribution for distinct subpopulations.

[0024] To illustrate, consider FIG. 4, which illustrates a process which may apply this approach to identifying if there are multiple subpopulations of red blood cells in a sample - a condition often known as dimorphism (referring to two distinct red blood cell subpopulations), trimorphism (referring to three distinct red blood cell subpopulations), or multimorphism is more subpopulations are involved. In a healthy patient, red blood cell size should resemble a standard bell curve when size is plotted against population, with a lower number of outlier cellsizes (very low and very large sizes) and a peak around the middle reflecting the majority or plurality of cells. This is differentiated from, for example, dimorphism where the population distribution would have multiple peaks each representing a different subpopulation (e.g., shown in FIG. 5, which will be explained in more detail further herein).

[0025] Considering FIG. 4, in that process, initially, images of red blood cells (RBCs) would be identified 401 (e.g., using cell classification approaches similar to those described above for the identification of platelets). Once the red blood cell images had been identified, those images may be filtered 402 such that only those images depicting front facing RBCs would subsequently be used. This may be done, for example, by taking the ratio of the major to the minor axes of an ellipse determined using the method of FIG. 2, and comparing that ratio to a threshold, with cells having a ratio below the threshold being treated as front facing, though other approaches (e.g., as described in WO 2025 / 059453, published March 30, 2025 for “Using Trained Machine Learning Models to Determine Alignment Characteristics,”) may also be used. Once only the front facing RBC images remained, the sizes of those images may be used to generate 403 population distribution (e.g., a histogram), such as that illustrated in FIG. 5, and the histogram may be checked 404 for multiple peaks. If there were multiple peaks, then this may be treated as indicating that there were multiple circulating subpopulations of red blood cells (e.g., dimorphism if there are two such subpopulations), which, in turn, may be indicative of an underlying condition that might require medical attention. Further variations are also possible, such as treating multiple peaks in a population distribution as indicating multiple subpopulations only if the multiple peaks were at least a minimum distance apart (e.g., if they were separated from each other by at least 1-2 standard deviations). Similarly, it is possible that a population distribution such as the histogram in FIG. 5 may be used to identify the existence of multiple subpopulations, and also to identify a threshold (e.g., a midpoint between peaks in the population distribution) which may be used to separate cells into the various subpopulations. These same approaches may also be used to identify subpopulations of other types of cells, such as identifying multiple peaks in a histogram of platelet sizes to identify large, small and giant platelets - by utilizing dynamic or non-fixed size ranges where the population distribution is analyzed to determine where population spikes are and the sizes associated with those heightened subpopulations types.

[0026] Cell size may also be used for purposes other than subtyping already identified cells. For example, particle size may be provided as an input to a machine learning model which was trained to identify various types of cells, thereby potentially allowing the model to more accurately distinguish between types of particles with similar appearance but different dimensions. It is also possible that this type of size identification may be used to more effectively flag analysis results that may warrant clinician review, such as when a blood sample is identified as including anomalous particles (e.g., giant platelets, multiple subtypes of circulating RBCs). As another example, in some cases a particle size may be used to enhance an interface used to present the results of blood cell analysis, such as by allowing a user to select a particle identified in the analysis and automatically displaying both a picture of that particle and a size determined for that particle using a method such as shown in FIG. 2. Size information may also be used for diagnosing conditions or identifying anomalies in cells, such as by identifying if there were particular types of cells which were of unusual size (e.g., neutrophils or monocytes 2-3+ standard deviations larger than average), or identifying if the distributions of sizes were indicative of an underlying condition (e.g., identifying if the standard deviation of sizes of monocytes indicated that a patient from whom a sample was taken had, or was at risk for, sepsis). Other uses of cell size determination technology such as described herein are also possible, and will be immediately apparent to those of skill in the art. Accordingly, the examples provided above should be understood as being illustrative only, and should not be treated as limiting.

[0027] In implementations of the disclosed technology which include a method such as shown in FIG. 2, the method may be performed using a variety of different hardware. For example, in some cases, a method such as shown in FIG. 2 may be performed using a processor which is integrated into a blood analysis instrument along with the flowcell and other components used to capture particle images (e.g., a controller which could also perform tasks such as controlling a camera to capture images and controlling hydraulics to flow a sample through the flowcell). As another example, in some cases, a method such as shown in FIG. 2 may be performed by a processor which is separate from, but in communication with, a blood analysis instrument, such as a processor of a computer which is in a single room with the blood analysis instrument, or of a computer which is connected to the blood analysis instrument over a local area networkconnection. It is also possible that, in some cases, components may be used which are located remotely from each other. For example, in some cases, images may be captured by a blood analysis instrument in a first location, but sizes for particles in those images may be determined using a remote server (e.g., a cloud server) in communication with the blood analysis instrument over a wide area network. Other types of configurations are also possible and will be immediately apparent to those of skill in the art in light of this disclosure. Accordingly, the example configurations given above should be understood as being illustrative only, and should not be treated as limiting.

[0028] 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.

[0029] Example 1

[0030] A computer-implemented method of identifying blood cell subpopulations, the method comprising: identifying a population of imaged blood cells using a classifier; obtaining sizes of the imaged blood cells; and using the sizes to identify a plurality of subpopulations of the population of imaged blood cells.

[0031] Example 2

[0032] The computer-implemented method of example 1 , wherein obtaining sizes of the imaged blood cells comprises, for each of the imaged blood cells: obtaining an image depicting that imaged blood cell; identifying a boundary for that imaged blood cell; defining a major and a minor axis for that imaged blood cell based on the boundary; and determining the size of that imaged blood cell based on the major axis and the minor axis.

[0033] Example 3

[0034] The computer-implemented method of example 2, wherein, for each of the imaged blood cells, identifying the boundary for that imaged blood cells comprises: separating a foreground of the image depicting that imaged blood cell from a background of the image depicting that imaged blood cell; and identifying contours of the foreground of the image depicting that imaged blood cell as the boundary for that imaged blood cell.

[0035] Example 4

[0036] The computer-implemented method of example 3, wherein, for each of the imaged blood cells: separating the foreground of the image depicting that imaged blood cell from the background of the image depicting that imaged blood cell comprises separating the foreground from the background using an otsu filter; identifying the contours of the foreground of the image depicting that imaged blood cell comprises identifying the contours using a chan-vese algorithm.

[0037] Example 5

[0038] The computer-implemented method of any of examples 2-4, wherein, for each of the imaged blood cells, defining the major and minor axis for that imaged blood cell comprises: selecting a first point on the boundary; identifying a line connecting the first point on the boundary to a second point on the boundary as the major axis, wherein there is no point on the boundary which has a greater straight line distance in pixels from the first point on the boundary than the second point on the boundary; and identifying a line which: is perpendicular to the major axis, and connects a third point on the boundary to a fourth point on the boundary, wherein no line which is perpendicular to the major axis has a straight line distance connecting points on theboundary has a greater straight line distance than the straight line distance between the third point and the fourth point; as the minor axis.

[0039] Example 6

[0040] The computer-implemented method of any of examples 2-5, wherein, for each of the imaged blood cells, determining a size of that imaged blood cell based on the major axis and the minor axis comprises: defining an ellipse having a major axis which is the major axis for that imaged blood cell, and a minor axis which is the minor axis for that imaged blood cell; calculating an area of the ellipse in pixels; and multiplying the area of the ellipse in pixels by a pixel conversion value.

[0041] Example 7

[0042] The computer-implemented method of any of examples 2-6, wherein, the method comprises receiving images of the imaged blood cells by performing acts comprising: establishing a flow of alignment fluid from an alignment fluid reservoir into a flowcell; creating a sample stream comprising sample fluid 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 flowcell to capture a plurality of images as the sample stream is flowing through the viewing area of the flowcell.

[0043] Example 8

[0044] The computer-implemented method of any of examples 1-7, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises comparing the sizes of the population of imaged blood cells with one or more thresholds which are specific to the population of imaged blood cells.

[0045] Example 9

[0046] The computer-implemented method of any of examples 1-8, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises identifying peaks in a distribution of the sizes of imaged blood cells in the population of imaged blood cells.

[0047] Example 10

[0048] The computer-implemented method of any of examples 1-9, wherein: the population of imaged blood cells is platelets; and the plurality of subpopulations of the population of imaged blood cells comprises giant platelets, large platelets and normal platelets.

[0049] Example 11

[0050] The computer-implemented method of any of examples 1-9 further comprising identifying a blood sample as containing dimorphic red blood cells when the plurality of subpopulations comprise two subpopulations and when the population of imaged blood cells comprises red blood cells.

[0051] Example 12

[0052] The computer-implemented method of any of examples 1-11, wherein identifying a population of imaged blood cells using the classifier comprises providing the sizes of the imaged blood cells to the classifier as input.

[0053] Example 13

[0054] The computer-implemented method of any of examples 1-12, wherein the method comprises identifying a disease state based on the sizes of the imaged blood cells.

[0055] Example 14

[0056] A system comprising: one or more processors; and a non-transitory readable medium having stored thereon instructions for performing the computer-implemented method of any of examples 1-13 when executed using the one or more processors.

[0057] Example 15

[0058] A non-transitory computer readable medium having stored thereon instructions for performing the computer implemented method of any of examples 1-13.

[0059] Example 16

[0060] A system comprising: one or more processors; a non-transitory computer readable medium having stored thereon instructions which, when executed using the one or more processors, perform a set of acts comprising: identifying a population of imaged blood cells using a classifier; obtaining sizes of the imaged blood cells; and using the sizes to identify a plurality of subpopulations of the population of imaged blood cells.

[0061] Example 17

[0062] The system of example 16, wherein obtaining sizes of the imaged blood cells comprises, for each of the imaged blood cells: obtaining an image depicting that imaged blood cell; identifying a boundary for that imaged blood cell; defining a major and a minor axis for that imaged blood cell based on the boundary; and determining the size of that imaged blood cell based on the major axis and the minor axis.

[0063] Example 18

[0064] The system of example 17, wherein, for each of the imaged blood cells, identifying the boundary forthat imaged blood cells comprises: separating a foreground of the image depicting that imaged blood cell from a background of the image depicting that imaged blood cell; and identifying contours of the foreground of the image depicting that imaged blood cell as the boundary for that imaged blood cell.

[0065] Example 19

[0066] The system of example 18, wherein, for each of the imaged blood cells: separating the foreground of the image depicting that imaged blood cell from the background of the image depicting that imaged blood cell comprises separating the foreground from the background using an otsu filter; identifying the contours of the foreground of the image depicting that imaged blood cell comprises identifying the contours using a chan-vese algorithm.

[0067] Example 20

[0068] The system of any of examples 17-19, wherein, for each of the imaged blood cells, defining the major and minor axis for that imaged blood cell comprises: selecting a first point on the boundary; identifying a line connecting the first point on the boundary to a second point on the boundary as the major axis, wherein there is no point on the boundary which has a greater straight line distance in pixels from the first point on the boundary than the second point on the boundary; and identifying a line which: is perpendicular to the major axis, and connects a third point on the boundary to a fourth point on the boundary, wherein no line which is perpendicular to the major axis has a straight line distance connecting points on the boundary has a greater straight line distance than the straight line distance between the third point and the fourth point; as the minor axis.

[0069] Example 21

[0070] The system of any of examples 17-20, wherein, for each of the imaged blood cells, determining a size of that imaged blood cell based on the major axis and the minor axis comprises: defining an ellipse having a major axis which is the major axis for that imaged blood cell, and a minor axis which is the minor axis for that imaged blood cell; calculating an area of the ellipse in pixels; and multiplying the area of the ellipse in pixels by a pixel conversion value.

[0071] Example 22

[0072] The system of any of examples 17-21, wherein, the set of acts comprises receiving images of the imaged blood cells by performing acts comprising: establishing a flow of alignment fluid from an alignment fluid reservoir into a flowcell; creating a sample stream comprising sample fluid 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 flowcell to capture a plurality of images as the sample stream is flowing through the viewing area of the flowcell.

[0073] Example 23

[0074] The system of any of examples 16-22, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises comparing the sizes of the population ofimaged blood cells with one or more thresholds which are specific to the population of imaged blood cells.

[0075] Example 24

[0076] The system of any of examples 16-23, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises identifying peaks in a distribution of the sizes of imaged blood cells in the population of imaged blood cells.

[0077] Example 25

[0078] The system of any of examples 16-24, wherein: the population of imaged blood cells is platelets; and the plurality of subpopulations of the population of imaged blood cells comprises giant platelets, large platelets and normal platelets.

[0079] Example 26

[0080] The system of any of examples 16-24 further comprising identifying a blood sample as containing dimorphic red blood cells when the plurality of subpopulations comprise two subpopulations and when the population of imaged blood cells comprises red blood cells.

[0081] Example 27

[0082] The system of any of examples 16-26, wherein identifying a population of imaged blood cells using the classifier comprises providing the sizes of the imaged blood cells to the classifier as input.

[0083] Example 28

[0084] The system of any of examples 16-27, wherein the set of acts comprises identifying a disease state based on the sizes of the imaged blood cells.

[0085] Example 29

[0086] A method comprising performing the set of acts the instructions stored on the non-transitory computer readable medium of the system of any of examples 16-28 are to perform when executed.

[0087] Example 30

[0088] A non-transitory computer readable medium having stored thereon instructions for performing the set of acts the instructions stored on the non-transitory computer readable medium of the system of any of examples 16-28 are to perform when executed.

[0089] Example 31

[0090] An analyzer comprising: a camera; a flowcell; one or more processors; and a non-transitory computer readable medium having stored thereon instructions which, when executed using the one or more processors, perform a set of acts comprising: identifying a population of imaged blood cells using a classifier; obtaining sizes of the imaged blood cells; and using the sizes to identify a plurality of subpopulations of the population of imaged blood cells.

[0091] Example 32

[0092] The analyzer of example 31, wherein obtaining sizes of the imaged blood cells comprises, for each of the imaged blood cells: obtaining an image depicting that imaged blood cell; identifying a boundary for that imaged blood cell; defining a major and a minor axis for that imaged blood cell based on the boundary; and determining the size of that imaged blood cell based on the major axis and the minor axis.

[0093] Example 33

[0094] The analyzer of example 32, wherein, for each of the imaged blood cells, identifying the boundary for that imaged blood cells comprises: separating a foreground of the image depicting that imaged blood cell from a background of the image depicting that imaged blood cell; and identifying contours of the foreground of the image depicting that imaged blood cell as the boundary for that imaged blood cell.

[0095] Example 34

[0096] The analyzer of example 33, wherein, for each of the imaged blood cells: separating the foreground of the image depicting that imaged blood cell from the background of the image depicting that imaged blood cell comprises separating the foreground from the background using an otsu filter; identifying the contours of the foreground of the image depicting that imaged blood cell comprises identifying the contours using a chan-vese algorithm.

[0097] Example 35

[0098] The analyzer of any of examples 32-34, wherein, for each of the imaged blood cells, defining the major and minor axis for that imaged blood cell comprises: selecting a first point on the boundary; identifying a line connecting the first point on the boundary to a second point on the boundary as the major axis, wherein there is no point on the boundary which has a greater straight line distance in pixels from the first point on the boundary than the second point on the boundary; and identifying a line which: is perpendicular to the major axis, and connects a third point on the boundary to a fourth point on the boundary, wherein no line which is perpendicular to the major axis has a straight line distance connecting points on the boundary has a greater straight line distance than the straight line distance between the third point and the fourth point; as the minor axis.

[0099] Example 36

[0100] The analyzer of any of examples 32-35, wherein, for each of the imaged blood cells, determining a size of that imaged blood cell based on the major axis and the minor axis comprises: defining an ellipse having a major axis which is the major axis for that imaged blood cell, and a minor axis which is the minor axis for that imaged blood cell; calculating an area of the ellipse in pixels; and multiplying the area of the ellipse in pixels by a pixel conversion value.

[0101] Example 37

[0102] The analyzer of any of examples 32-35, wherein, the set of acts comprises receiving images of the imaged blood cells by performing acts comprising: establishing a flow of alignment fluid from an alignment fluid reservoir into the flowcell; creating a sample stream comprising sample fluid 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 the camera focused on a viewing area of the flowcell to capture a plurality of images as the sample stream is flowing through the viewing area of the flowcell.

[0103] Example 38

[0104] The analyzer of any of examples 31-37, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises comparing the sizes of the population of imaged blood cells with one or more thresholds which are specific to the population of imaged blood cells.

[0105] Example 39

[0106] The analyzer of any of examples 31-38, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises identifying peaks in a distribution of the sizes of imaged blood cells in the population of imaged blood cells.

[0107] Example 40

[0108] The analyzer of any of examples 31-39, wherein: the population of imaged blood cells is platelets; and the plurality of subpopulations of the population of imaged blood cells comprises giant platelets, large platelets and normal platelets.

[0109] Example 41

[0110] The analyzer of any of examples 31-39 further comprising identifying a blood sample as containing dimorphic red blood cells when the plurality of subpopulations comprise two subpopulations and when the population of imaged blood cells comprises red blood cells.

[0111] Example 42

[0112] The analyzer of any of examples 31 -41, wherein identifying a population of imaged blood cells using the classifier comprises providing the sizes of the imaged blood cells to the classifier as input.

[0113] Example 43

[0114] The analyzer of any of examples 31-42, wherein the set of acts comprises identifying a disease state based on the sizes of the imaged blood cells.

[0115] Example 44

[0116] A method comprising performing the set of acts the instructions stored on the non- transitory computer readable medium of the analyzer of any of examples 31-43 are to perform when executed.

[0117] Example 45

[0118] A non-transitory computer readable medium having stored thereon instructions for performing the set of acts the instructions stored on the non-transitory computer readable medium of the analyzer of any of examples 31-43 are to perform when executed.

[0119] 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.

[0120] 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 orstructure 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.

[0121] Explicit Definitions

[0122] 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.

[0123] 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

CLAIMSWhat is claimed is:

1. A computer-implemented method of identifying blood cell subpopulations, the method comprising:• identifying a population of imaged blood cells using a classifier;• obtaining sizes of the imaged blood cells; and• using the sizes to identify a plurality of subpopulations of the population of imaged blood cells.

2. The computer-implemented method of claim 1, wherein obtaining sizes of the imaged blood cells comprises, for each of the imaged blood cells:• obtaining an image depicting that imaged blood cell;• identifying a boundary for that imaged blood cell;• defining a major and a minor axis for that imaged blood cell based on the boundary; and• determining the size of that imaged blood cell based on the major axis and the minor axis.

3. The computer-implemented method of claim 2, wherein, for each of the imaged blood cells, identifying the boundary for that imaged blood cells comprises:• separating a foreground of the image depicting that imaged blood cell from a background of the image depicting that imaged blood cell; and• identifying contours of the foreground of the image depicting that imaged blood cell as the boundary for that imaged blood cell.

4. The computer-implemented method of claim 3, wherein, for each of the imaged blood cells:• separating the foreground of the image depicting that imaged blood cell from the background of the image depicting that imaged blood cell comprises separating the foreground from the background using an otsu filter;identifying the contours of the foreground of the image depicting that imaged blood cell comprises identifying the contours using a chan-vese algorithm.

5. The computer-implemented method of any of claims 2-4, wherein, for each of the imaged blood cells, defining the major and minor axis for that imaged blood cell comprises:• selecting a first point on the boundary;• identifying a line connecting the first point on the boundary to a second point on the boundary as the major axis, wherein there is no point on the boundary which has a greater straight line distance in pixels from the first point on the boundary than the second point on the boundary; and• identifying a line which:° is perpendicular to the major axis, and° connects a third point on the boundary to a fourth point on the boundary, wherein no line which is perpendicular to the major axis has a straight line distance connecting points on the boundary has a greater straight line distance than the straight line distance between the third point and the fourth point; as the minor axis.

6. The computer-implemented method of any of claims 2-5, wherein, for each of the imaged blood cells, determining a size of that imaged blood cell based on the major axis and the minor axis comprises:• defining an ellipse having a major axis which is the major axis for that imaged blood cell, and a minor axis which is the minor axis for that imaged blood cell;• calculating an area of the ellipse in pixels; and• multiplying the area of the ellipse in pixels by a pixel conversion value.

7. The computer-implemented method of any of claims 2-6, wherein, the method comprises receiving images of the imaged blood cells by performing acts comprising:• establishing a flow of alignment fluid from an alignment fluid reservoir into a flowcell;• creating a sample stream comprising sample fluid 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 flowcell to capture a plurality of images as the sample stream is flowing through the viewing area of the flowcell.

8. The computer-implemented method of any of claims 1-7, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises comparing the sizes of the population of imaged blood cells with one or more thresholds which are specific to the population of imaged blood cells.

9. The computer-implemented method of any of claims 1-8, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises identifying peaks in a distribution of the sizes of imaged blood cells in the population of imaged blood cells.

10. The computer-implemented method of any of claims 1-9, wherein:• the population of imaged blood cells is platelets; and• the plurality of subpopulations of the population of imaged blood cells comprises giant platelets, large platelets and normal platelets.

11. The computer-implemented method of any of claims 1-9 further comprising identifying a blood sample as containing dimorphic red blood cells when the plurality of subpopulations comprise two subpopulations and when the population of imaged blood cells comprises red blood cells.

12. The computer-implemented method of any of claims 1-11, wherein identifying a population of imaged blood cells using the classifier comprises providing the sizes of the imaged blood cells to the classifier as input.

13. The computer-implemented method of any of claims 1-12, wherein the method comprises identifying a disease state based on the sizes of the imaged blood cells.

14. A system comprising: one or more processors; and a non-transitory readable medium having stored thereon instructions for performing a computer-implemented method as claimed in any of claims 1-13 when executed using the one or more processors.

15. A non-transitory computer readable medium having stored thereon instructions for performing a computer-implemented method as claimed in any of claims 1-13.

16. A system comprising:• one or more processors;• a non-transitory computer readable medium having stored thereon instructions which, when executed using the one or more processors, perform a set of acts comprising:° identifying a population of imaged blood cells using a classifier;° obtaining sizes of the imaged blood cells; and° using the sizes to identify a plurality of subpopulations of the population of imaged blood cells.

17. The system of claim 16, wherein obtaining sizes of the imaged blood cells comprises, for each of the imaged blood cells:• obtaining an image depicting that imaged blood cell;• identifying a boundary for that imaged blood cell;• defining a major and a minor axis for that imaged blood cell based on the boundary; anddetermining the size of that imaged blood cell based on the major axis and the minor axis.

18. The system of claim 17, wherein, for each of the imaged blood cells, identifying the boundary for that imaged blood cells comprises:• separating a foreground of the image depicting that imaged blood cell from a background of the image depicting that imaged blood cell; and• identifying contours of the foreground of the image depicting that imaged blood cell as the boundary for that imaged blood cell.

19. The system of claim 18, wherein, for each of the imaged blood cells:• separating the foreground of the image depicting that imaged blood cell from the background of the image depicting that imaged blood cell comprises separating the foreground from the background using an otsu filter;• identifying the contours of the foreground of the image depicting that imaged blood cell comprises identifying the contours using a chan-vese algorithm.

20. The system of any of claims 17-19, wherein, for each of the imaged blood cells, defining the major and minor axis for that imaged blood cell comprises:• selecting a first point on the boundary;• identifying a line connecting the first point on the boundary to a second point on the boundary as the major axis, wherein there is no point on the boundary which has a greater straight line distance in pixels from the first point on the boundary than the second point on the boundary; and• identifying a line which:° is perpendicular to the major axis, and° connects a third point on the boundary to a fourth point on the boundary, wherein no line which is perpendicular to the major axis has a straight line distance connecting points on the boundary has a greater straight linedistance than the straight line distance between the third point and the fourth point; as the minor axis.

21. The system of any of claims 17-20, wherein, for each of the imaged blood cells, determining a size of that imaged blood cell based on the major axis and the minor axis comprises:• defining an ellipse having a major axis which is the major axis for that imaged blood cell, and a minor axis which is the minor axis for that imaged blood cell;• calculating an area of the ellipse in pixels; and• multiplying the area of the ellipse in pixels by a pixel conversion value.

22. The system of any of claims 17-21, wherein, the set of acts comprises receiving images of the imaged blood cells by performing acts comprising:• establishing a flow of alignment fluid from an alignment fluid reservoir into a flowcell;• creating a sample stream comprising sample fluid 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 flowcell to capture a plurality of images as the sample stream is flowing through the viewing area of the flowcell.

23. The system of any of claims 16-22, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises comparing the sizes of the population of imaged blood cells with one or more thresholds which are specific to the population of imaged blood cells.

24. The system of any of claims 16-23, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises identifying peaks in a distribution of the sizes of imaged blood cells in the population of imaged blood cells.

25. The system of any of claims 16-24, wherein:• the population of imaged blood cells is platelets; and• the plurality of subpopulations of the population of imaged blood cells comprises giant platelets, large platelets and normal platelets.

26. The system of any of claims 16-24 further comprising identifying a blood sample as containing dimorphic red blood cells when the plurality of subpopulations comprise two subpopulations and when the population of imaged blood cells comprises red blood cells.

27. The system of any of claims 16-26, wherein identifying a population of imaged blood cells using the classifier comprises providing the sizes of the imaged blood cells to the classifier as input.

28. The system of any of claims 16-27, wherein the set of acts comprises identifying a disease state based on the sizes of the imaged blood cells.

29. A method comprising performing the set of acts the instructions stored on the non- transitory computer readable medium of the system of any of claims 16-28 are to perform when executed.

30. A non-transitory computer readable medium having stored thereon instructions for performing the set of acts the instructions stored on the non-transitory computer readable medium of the system of any of claims 16-28 are to perform when executed.

31. An analyzer comprising: a camera; a flowcell; one or more processors; and• a non-transitory computer readable medium having stored thereon instructions which, when executed using the one or more processors, perform a set of acts comprising:° identifying a population of imaged blood cells using a classifier;° obtaining sizes of the imaged blood cells; and° using the sizes to identify a plurality of subpopulations of the population of imaged blood cells.

32. The analyzer of claim 31, wherein obtaining sizes of the imaged blood cells comprises, for each of the imaged blood cells:• obtaining an image depicting that imaged blood cell;• identifying a boundary for that imaged blood cell;• defining a major and a minor axis for that imaged blood cell based on the boundary; and• determining the size of that imaged blood cell based on the major axis and the minor axis.

33. The analyzer of claim 32, wherein, for each of the imaged blood cells, identifying the boundary for that imaged blood cells comprises:• separating a foreground of the image depicting that imaged blood cell from a background of the image depicting that imaged blood cell; and• identifying contours of the foreground of the image depicting that imaged blood cell as the boundary for that imaged blood cell.

34. The analyzer of claim 33, wherein, for each of the imaged blood cells:• separating the foreground of the image depicting that imaged blood cell from the background of the image depicting that imaged blood cell comprises separating the foreground from the background using an otsu filter;• identifying the contours of the foreground of the image depicting that imaged blood cell comprises identifying the contours using a chan-vese algorithm.

35. The analyzer of any of claims 32-34, wherein, for each of the imaged blood cells, defining the major and minor axis for that imaged blood cell comprises:• selecting a first point on the boundary;• identifying a line connecting the first point on the boundary to a second point on the boundary as the major axis, wherein there is no point on the boundary which has a greater straight line distance in pixels from the first point on the boundary than the second point on the boundary; and• identifying a line which:° is perpendicular to the major axis, and° connects a third point on the boundary to a fourth point on the boundary, wherein no line which is perpendicular to the major axis has a straight line distance connecting points on the boundary has a greater straight line distance than the straight line distance between the third point and the fourth point; as the minor axis.

36. The analyzer of any of claims 32-35, wherein, for each of the imaged blood cells, determining a size of that imaged blood cell based on the major axis and the minor axis comprises:• defining an ellipse having a major axis which is the major axis for that imaged blood cell, and a minor axis which is the minor axis for that imaged blood cell;• calculating an area of the ellipse in pixels; and• multiplying the area of the ellipse in pixels by a pixel conversion value.

37. The analyzer of any of claims 32-35, wherein, the set of acts comprises receiving images of the imaged blood cells by performing acts comprising:• establishing a flow of alignment fluid from an alignment fluid reservoir into the flowcell;• creating a sample stream comprising sample fluid 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 the camera focused on a viewing area of the flowcell to capture a plurality of images as the sample stream is flowing through the viewing area of the flowcell.

38. The analyzer of any of claims 31-37, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises comparing the sizes of the population of imaged blood cells with one or more thresholds which are specific to the population of imaged blood cells.

39. The analyzer of any of claims 31-38, wherein using the sizes to identify the plurality of subpopulations of imaged blood cells comprises identifying peaks in a distribution of the sizes of imaged blood cells in the population of imaged blood cells.

40. The analyzer of any of claims 31-39, wherein:• the population of imaged blood cells is platelets; and• the plurality of subpopulations of the population of imaged blood cells comprises giant platelets, large platelets and normal platelets.

41. The analyzer of any of claims 31-39 further comprising identifying a blood sample as containing dimorphic red blood cells when the plurality of subpopulations comprise two subpopulations and when the population of imaged blood cells comprises red blood cells.

42. The analyzer of any of claims 31-41, wherein identifying a population of imaged blood cells using the classifier comprises providing the sizes of the imaged blood cells to the classifier as input.

43. The analyzer of any of claims 31-42, wherein the set of acts comprises identifying a disease state based on the sizes of the imaged blood cells.

44. A method comprising performing the set of acts the instructions stored on the non- transitory computer readable medium of the analyzer of any of claims 31-43 are to perform when executed.

45. A non-transitory computer readable medium having stored thereon instructions for performing the set of acts the instructions stored on the non-transitory computer readable medium of the analyzer of any of claims 31-43 are to perform when executed.

Images