Population-based cell classification

Abstract

Cell classification may be performed using a system that receives a set of images containing representations of a plurality of cells and performs various operations on each of the cells, which may include determining imaging parameters for each of the cells, generating a cluster assignment for each of the cells, and providing a type for each of the cells based on the cluster assignment.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to, but is not a provisional application for, Provisional Patent Application No. 63 / 434,658, entitled "Population Based Cell Classification," filed with the U.S. Patent and Trademark Office on December 22, 2022, which is incorporated herein by reference in its entirety. [Background technology]

[0002] Blood cell analysis is one of the most commonly performed medical tests to provide an overview of a patient's health. A blood sample is collected from a patient's body and stored in a test tube containing an anticoagulant to prevent clotting. A whole blood sample typically contains three major classes of blood cells: red blood cells, white blood cells, and platelets. Each class may be further divided into subclasses of members. For example, the 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 red blood cell types. The appearance of particles in a sample may vary depending on the pathological state, maturity of the cells, and other factors. Subclasses of red blood cells may include reticulocytes and nucleated red blood cells.

[0003] Traditionally, particle sorting systems have utilized non-imaging techniques, such as scattering light from laser illumination or measuring the change in impedance as particles pass through an aperture. While these techniques can be effective, they also have drawbacks. Thus, there is a need for improved sorting systems, such as systems that can classify particles based on information extracted from images of the particles. Summary of the Invention

[0004] Described herein are devices, systems and methods for classifying objects, such as cells, in images taken by an analyzer, such as a bioassay system that takes images of blood cells from a blood sample.

[0005] An illustrative example of such a technique relates to a system including a processor and a non-transitory computer-readable medium. The medium may store instructions operable, when executed by the processor, to perform a set of operations. The operations may include receiving a set of images, the set of images including a representation of a plurality of cells. The operations may also include a set of operations performed for each cell of the plurality of cells. The set of operations may include determining one or more imaging parameters for the cell based on application of an image analysis algorithm. The set of operations may also include generating a cluster assignment for the cell by assigning the cell to a cluster of a plurality of clusters based on at least one of the one or more imaging parameters for both the cell and a population including the plurality of cells. In other words, the set of operations may include generating a cluster assignment for the cell by assigning the cell to a cluster of a plurality of clusters based on at least one of the one or more imaging parameters for the cell and the at least one imaging parameter for each cell of a cell population including the plurality of cells. The set of operations may also include providing a type for the cell based on the cluster assignment for the cell.

[0006] 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 the disclosed subject matter.

[0007] While the specification concludes with claims that particularly point out and distinctly claim the invention, it is believed the present invention will be better understood from the following description of specific examples when read in conjunction with the accompanying drawings, in which like reference numerals identify identical elements and in which: [Brief explanation of the drawings]

[0008] [Figure 1]FIG. 1 is a schematic diagram, partially in cross section and not to scale, illustrating the operation of an exemplary flow cell and high optical resolution imaging device for sample image analysis using digital image processing. [Figure 2] FIG. 2 illustrates a sliding vision inspection system in which aspects of the disclosed technology may be used. [Figure 3] FIG. 3 illustrates a process that can be used to classify cells. [Figure 4] FIG. 4 illustrates a process that can be used to assign cells to clusters using a gating algorithm. [Figure 5] FIG. 5 illustrates a process that can be used to assign cells to clusters using a gating algorithm. [Figure 6] FIG. 6 shows an exemplary nuclear mask corresponding to the cell image of FIG. [Figure 7] FIG. 7 shows a slide image of a cell containing a nucleus. [Figure 8] FIG. 8 shows the cell mask for the image of the cell in FIG. [Figure 9] FIG. 9 shows a histogram of each pixel value of the cell image of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0009] The drawings are not intended to be limiting in any manner, and it is understood that various embodiments of the invention may be embodied in a variety of other forms, including forms not necessarily depicted in the drawings. The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate several aspects of the invention and, together with the detailed description, serve to explain the principles of the invention. It is understood, however, that the invention is not limited to the precise configurations shown.

[0010] The present disclosure relates to devices, systems, compositions, and methods for analyzing samples containing particles. In one embodiment, the present invention relates to an automated particle imaging system including an analyzer, which may be, for example, a visual analyzer. In some embodiments, the visual analyzer may further include a processor that facilitates automated analysis of the image.

[0011] According to some aspects of the present disclosure, a system including a visual analyzer may be provided for acquiring images of a sample containing particles suspended in a liquid. This system may be useful in characterizing particles in biological fluids, such as detecting and quantifying red blood cells, reticulocytes, nucleated red blood cells, platelets, and white blood cells (including differential count, categorization and subcategorization, and analysis). Other similar uses are also contemplated, such as characterizing blood cells in other fluids.

[0012] While classification of blood cells in a blood sample is an exemplary application for which the subject matter is particularly well suited, other types of bodily fluid samples may be used. For example, aspects of the disclosed technology may be used to analyze non-blood bodily fluid samples containing blood cells (e.g., white blood cells and / or red blood cells), such as serum, bone marrow, lavage fluid, exudate, effusion, cerebrospinal fluid, pleural fluid, peritoneal fluid, and amniotic fluid. The sample may also be a solid tissue sample, e.g., a biopsy sample processed to produce a cell suspension. The sample may also be a suspension obtained by processing a stool sample. The sample may also be a laboratory or manufacturing line sample containing 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 may also be diluted, divided into portions, or stained in some processing.

[0013] In some embodiments, samples are presented, imaged, and analyzed in an automated manner. In the case of blood samples, the sample may be significantly diluted with an appropriate diluent or saline solution, thereby reducing the extent to which the appearance of some cells is obscured by other cells in undiluted or less diluted samples. Cells can be treated with agents that enhance the contrast of some cellular aspects, e.g., using permeabilizing agents to permeabilize cell membranes and using histological stains to attach to and reveal features such as granules and nuclei. In some cases, it may be desirable to stain an aliquot of the sample to count and characterize particles including reticulocytes, nucleated red blood cells, and platelets, as well as for the differentiation, characterization, and analysis of white blood cells. In other cases, samples containing red blood cells may be diluted prior to introduction into the flow cell and / or imaging in the flow cell or otherwise.

[0014] Details of sample preparation devices and methods for sample dilution, permeabilization, and histological staining can generally be achieved using precision pumps and valves operated by one or more programmable controllers, as exemplified in patents such as U.S. Patent No. 7,319,907. Similarly, techniques for differentiation of specific cell categories and / or subcategories according to their attributes, such as relative size and color, are known from U.S. Patent No. 5,436,978 in the context of white blood cells, the disclosures of which are incorporated herein by reference in their entireties.

[0015] I. Imaging System 1 schematically illustrates an exemplary flow cell 22 for conveying a sample fluid through a viewing region 23 of a high optical resolution imaging device 24 in a configuration for imaging microparticles in a sample flow stream 32 using digital image processing. The flow cell 22 is coupled to a source 25 of sample fluid, which may have been subjected to treatment such as contact with a particle contrast agent composition and heating. The flow cell 22 is also coupled to one or more sources 27 of particle and / or organelle alignment liquid (PIOAL), such as a clear glycerol solution having a viscosity higher than that of the sample fluid.

[0016] Sample fluid is injected into the flow cell 22 through a flat opening at the distal end 28 of the sample supply tube 29 at a point where PIOAL flow is substantially established, resulting in a steady, symmetric, laminar flow of PIOAL around / around the ribbon-shaped sample stream (e.g., circumferentially in a circular cross-sectional configuration, or around multiple sides in a non-circular (e.g., rectangular) cross-sectional configuration). The sample and PIOAL streams may be supplied by a precision metering pump that moves the PIOAL with the injected sample fluid along a significantly narrowing flow path. The PIOAL contains and compresses the sample fluid within the flow path narrowing region 21. The reduced flow path thickness in region 21 may therefore contribute to the geometric focusing of the sample stream 32. The sample fluid ribbon 32 is contained and transported along with the PIOAL downstream of the narrowing region 21, e.g., in front of or through the viewing region 23 of the high-optical-resolution imager 24, where images are collected using a CCD 48. In this manner, flow imaging is performed in which images are collected from the flowing sample stream and the cellular material contained therein. The processor 18 can receive as input pixel data from the CCD 48. The sample fluid ribbon flows to the outlet 33 along with the PIOAL.

[0017] As shown, narrowed region 21 can have a proximal flow path portion 21a having a proximal thickness PT and a distal flow path portion 21b having a distal thickness DT, such that distal thickness DT is less than proximal thickness PT. Thus, sample fluid can be injected through distal end 28 of sample tube 29 at a location distal to proximal portion 21a and proximal to distal portion 21b. Thus, as the PIOAL stream is compressed by region 21, the sample fluid will enter the PIOAL envelope. The sample fluid injection tube has a distal exit port through which sample fluid is injected into the flowing sheath liquid, the distal exit port being restricted by the reduced flow path size of the flow cell.

[0018] A digital high optical resolution imager 24 having an objective lens 46 is oriented along an optical axis that intersects the ribbon-shaped sample stream 32. The relative distance between the objective lens 46 and the flow cell 22 is varied by operation of a motor drive 54 to resolve and collect a focused digital image on a photosensor array. Further information regarding the construction and operation of an exemplary flow cell such as that shown in FIG. 1 is provided in U.S. Patent No. 9,322,752, filed March 17, 2014, entitled "Flow Cell Systems and Methods for Particle Analysis in Blood Samples," the disclosure of which is incorporated herein by reference in its entirety.

[0019] Aspects of the disclosed technology may be applied in contexts other than flow cell systems such as that shown in Figure 1. For example, Figure 2 shows a slide-based vision inspection system 200 in which aspects of the disclosed technology may be used. In the system shown in Figure 2, a slide 202 containing a sample, such as a blood sample, is placed in a slide holder 204. Slide holder 204 may be adapted to hold multiple slides or only one slide, as shown in Figure 2. Image capture device 206, including optical system 208 and image sensor 210, is adapted to acquire image data depicting the sample within slide 202.

[0020] Image data acquired by the image capture device 206 can be transferred to an image processing device 212. The image processing device 212 can be an external device, such as a personal computer, connected to the image capture device 206. Alternatively, the image processing device 212 can be incorporated into the image capture device 206. The image processing device 212 can include a processor 214 associated with a memory 216 configured to determine a change required to determine the difference between the actual focus and the correct focus for the image capture device 206. Once the difference is determined, instructions can be transferred to a steering motor system 218. The steering motor system 218 can change the distance z between the slide 202 and the optical system 208 based on instructions from the image processing device 212. Descriptions of approaches that can be used for focusing using this type of setup are provided in U.S. Provisional Patent Application No. 63 / 291,044, filed December 17, 2021, entitled "Autofocusing Through Multi-Layer Processing," U.S. Patent No. 9,857,361, filed March 17, 2014, entitled "Flowcell, sheath fluid, and autofocus systems and methods for particle analysis in urine samples," U.S. Patent No. 10,705,008, filed March 17, 2014, entitled "Autofocus systems and methods for particle analysis in blood samples," U.S. Patent No. 10,705,011, filed October 5, 2017, entitled "Dynamic focus system and methods," and International Application No. WO2023 / 150064, filed January 27, 2023, entitled "Measure image quality of blood cell images," the disclosures of each of which are incorporated herein by reference in their entirety.

[0021] II. Data Processing Data acquired by a system such as that shown in Figures 1 and 2 may be subjected to various processes, the high level methods which may be performed in this process being shown in Figure 3 and described below.

[0022] A. Image Analysis 3, a representation of a plurality of cells may be received (301). This may include, for example, the processor receiving one or more images, each including a representation of a plurality of cells (e.g., as may be imaged in a slide-based system as shown in FIG. 2). Alternatively, receiving a representation of a plurality of cells (301) may include the processor receiving multiple images, each including a representation of only a single cell (e.g., as may be imaged by a flow cell-based flow imaging system as shown in FIG. 1). Once the representation is received (301), the method continues with performing image analysis (302) to obtain data that can be used in subsequent data processing. Exemplary data that may be obtained as a result of performing image analysis (302) is provided below in Table 1.

[0023] [Table 1]

[0024] Other types of image analysis may be included in step 302 of performing image analysis, such as isolating cellular representations using a cell isolation algorithm (e.g., an algorithm that thresholds an image captured by a flow cell system to identify portions of the image that do not represent cells) and / or boundary identification using approaches such as those described in U.S. Pat. No. 4,538,299, issued August 1985, entitled "Method and Apparatus for Locating the Boundary of an Object," the disclosure of which is incorporated herein by reference in its entirety.

[0025] Additionally, in some embodiments, performing image analysis 302 may include generating a mask 303. For example, the following masks may potentially be generated 303:

[0026] [Table 2]

[0027] To illustrate what may be involved in generating a mask 303, FIG. 7 shows an image 700 of a cell, such as may be captured using an apparatus such as that shown in FIG. 1 or 2. In some embodiments, the image may comprise a background portion 710 and a foreground portion 720. The foreground portion 720 may represent a blood cell, which may be further segmented into cellular portions (e.g., cytoplasm 722 and nucleus 724). These components of the blood cell image 700 (e.g., cytoplasm 722 and nucleus 724) may be described or defined using a corresponding mask. For example, referring briefly to FIG. 8, an illustrative example of a cell mask 800 (corresponding to cell_mask in Table 2) is shown. In some embodiments, the mask may be binary. For example, and as shown, the cell mask 800 may be approximately the same size as the original image and may represent each pixel using a series of 0s and / or 1s. In some embodiments, a value of "1" may represent that the corresponding pixel belongs to a cell 810, while a value of "0" may represent that the corresponding pixel does not belong to a cell (e.g., background mask 820). This cell mask can be generated, for example, by normalizing the pixel values ​​in an RGB image, using the normalized values ​​to generate a histogram, and using the histogram to define a threshold that separates cells from non-cellular pixels. An example of this histogram is shown in Figure 9, which shows a graphical representation 900 that plots a pixel's normalized value 910 (e.g., the minimum red, green, and blue values ​​smoothed by averaging the values ​​of neighboring pixels within a smoothing window and projected to a 0:1 range) against the total number of pixels with the corresponding value 920 in the image.

[0028] Other masks can be generated similar to those described above for the cell mask, although the details of a particular mask may vary depending on the nature of the mask itself. For example, the nucleus mask 600 shown in FIG. 6 (corresponding to nucleus_mask in Table 2) may be defined using the left threshold 930 in the histogram of FIG. 9, reflecting that pixels depicting the nucleus tend to be darker than pixels depicting other parts of the cell. As another example, in some cases, a mask may be generated using other masks and / or parameters of other masks as inputs. For example, a dark mask may be a mask of pixels in the cell mask whose values ​​are equal to or less than a first darkness threshold. Meanwhile, a black mask may be a mask of pixels in the cell mask whose values ​​are equal to or less than a second darkness threshold that is equal to or less than the first darkness threshold. In some cases, one or more other sets of pixels may be generated in addition to or instead of the masks described above. These may include, for example, boundary pixels and / or pixels corresponding to one or more of the enumerated masks (e.g., cytoplasmic pixels, black pixels). Furthermore, in some cases, the mask generating step 303 may involve processing beyond that based on pixel values. For example, in some cases, once a mask has been generated for structures (e.g., cells) that are expected to be continuous, an anomaly removal step may be performed in which small (e.g., less than a certain number of pixels) holes in the mask are removed (i.e., processed to be included regardless of pixel value) so that the mask generation is not adversely affected by imaging or other artifacts. Thus, the above description of step 303 of generating a mask should be understood as illustrative only and should not be treated as limiting.

[0029] B. Determining parameters In the method of Figure 3, after performing image analysis step 302 (potentially including generating a mask step 303) is completed, the data obtained from the image analysis may be used in determining imaging parameters step 304. Examples of these types of parameters and how their values ​​may be determined 304 are provided below in Table 3.

[0030] [Table 3-1] [Table 3-2]

[0031] C. Cluster Allocation With the parameters determined (304), processing as shown in Figure 3 continues with step 305 of assigning each of the cells to a cluster based on the imaging parameters. This may be done, for example, by applying a gating algorithm to the display of cells, where the previously determined parameters are sequentially evaluated to assign the cells to various clusters. For illustration, consider Figure 4, which shows how this gating approach can be applied to clustering cells in a blood sample.

[0032] In the method of FIG. 4, first, a check 401 may be applied to determine whether a cell is a white blood cell. This may be done using parameters such as the cell's darkness, its blue-to-red ratio, and the absorbance due to its presence. For example, histograms may be generated of the darkness, blue-to-red ratio, and / or absorbance values ​​of the cell, and the lowest point in each of these histograms may be defined as a threshold for determining whether a cell is a white blood cell. With these thresholds, any cells that do not have darkness values, blue-to-red ratios, or absorbance values ​​above the cutoff for being treated as white blood cells will be assigned to the non-white blood cell cluster (402). (For example, cells whose blue channel divided by the red channel in their cell mask is less than 1, and whose average L channel values ​​in their cell mask in L*a*b color space divided by the average L values ​​of their boundary pixels in L*a*b color space is less than 1, may be classified as non-white blood cells.) Alternatively, the cells may be subjected to further analysis to determine what type of white blood cell they were.

[0033] In the method of FIG. 4, if a cell is determined to be a white blood cell (401), a further determination of whether the cell is an eosinophil is made (403). This may be done using parameters such as the darkness of the cell's granules and the blueness of the cell's granules and / or cytoplasm. For example, Gaussian mixture model clustering may be used to cluster the cells in a two-dimensional space defined by the blueness of the cell's granules. Cells with the fewest blue granules are then processed as eosinophils and assigned to the eosinophil cluster (404). A similar process may be applied to identify neutrophils. That is, after appropriate cells have been assigned to the eosinophil cluster (404), a further determination of whether the remaining cells are neutrophils (405) may be made by applying Gaussian mixture model clustering to cluster the remaining cells in a three-dimensional space defined by the cell size and the darkness and blueness of their cytoplasm. Then, relatively large cells with fewer blue granules or cytoplasm at the same darkness level (e.g., the difference between the V value in the HSV color space and 1 for the applicable cells) will be treated as neutrophils and assigned to the neutrophil cluster (406).

[0034] In the method of FIG. 4 , after cells have been appropriately assigned to the neutrophil cluster (406), the remaining cells are further determined 407 to be basophils or not. This may be done, for example, by identifying the number of dark blue granules around the nucleus and using OPTICS clustering (described in Kriegel, Hans-Peter; Kroger, Peer; Sander, Jorg; and Zimek, Arthur, Density-Based Clustering, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 1(3):231-240, the disclosure of which is incorporated herein by reference in its entirety) or a thresholding algorithm to identify cells whose representation contains a relatively large number of such granules. These cells are then assigned 408 to the basophil cluster, and further determination 409 of whether the remaining cells are monocytes or lymphocytes may be made. This may be done using k-means clustering to separate cells based on their size and / or the size of their nuclei. The smaller cells (e.g., cells with a normalized y-value of 0.42 or less) will be assigned 410 to the lymphocyte cluster, and the remaining cells will be assigned 411 to the monocyte cluster. Thus, the cells in the sample will be classified as non-WBC, eosinophil, neutrophil, basophil, lymphocyte, and monocyte using a series of binary classifications based on the relationship of a parameter for a particular cell to the relevant parameter for the entire population of cells under consideration.

[0035] D.Classification Referring now to the description of FIG. 3 , after cells are assigned to clusters (305), the cluster assignments can be used to provide classifications for the cells (306). This can be done, for example, by displaying the cells on a scatter plot in which different colors are used to distinguish cell types from one another and providing output to a user (e.g., on a display). Similarly, in some cases, the cell classifications can be provided to an evaluation algorithm that can use the classifications to determine whether there may be any anomalies in the image evaluation. For example, the evaluation algorithm can be configured with data representing expected characteristics and relative positions for different clusters based on images captured under ideal conditions. In this case, the cell classifications can be provided to an evaluation algorithm that can compare the relative positions and characteristics of clusters generated from the images with the expected relative positions and characteristics (306). Based on this comparison, the evaluation algorithm may indicate whether the cellular representations were imaged with less than ideal illumination (e.g., because cells within a cluster appear darker than expected), whether the imaged sample was not properly stained (e.g., because clusters appear pale, which may cause the clusters to be shifted on an axis representing the blueness or darkness of the cells), or whether the images were imaged with improper focus (e.g., because cell size within various clusters appears larger than expected). The evaluation algorithm may then quantify the difference between the actual and ideal conditions, such as by measuring shifts along various parameters across the population of cells represented by the clusters. This may then be used to provide various outputs, such as flagging samples that may need to be re-imaged due to anomalies above some threshold magnitude, or informing an operator that they should adjust the imaging components they are using to improve image quality in the future. Other uses of this type of information are possible, such as providing an assessment of the effectiveness of an analysis system as it is developed, and other uses should be readily apparent to those skilled in the art in light of the present disclosure. Therefore, the examples provided should be understood as illustrative only and not limiting.

[0036] Relative distribution profiles implemented in accordance with the present disclosure may provide advantages over cell-by-cell classification systems (e.g., those that identify and classify each cell one at a time). Because the classification system can identify relative population distributions and look for population clusters within the overall population distribution to classify cells, there is less opportunity for misclassification due to, for example, poor imaging conditions (e.g., camera out of focus, poor lighting, or staining problems). In addition to the examples above, a classification system may seek to pool or group data instead of comparing observed population distributions to expected population distributions, and then learn to segment cell populations in this way (e.g., without the step of comparison to expected distribution profiles).

[0037] III. Variations Other variations and embodiments of the disclosed techniques are possible. For example, in some cases, cell isolation techniques such as those described in the flow imaging background may be applied to images from a slide-based imaging system, and individual cells may be grouped into clusters (potentially with other cells in different images of the same sample) as part of receiving cell representations 301. Also, in some embodiments, other types of classification may be performed. For example, in some cases, a determination of whether cells are large platelets (not shown in FIG. 4 ) may be made based on whether the cells have a relatively low granularity and / or blue-to-green ratio before determining whether the cells remaining for classification are eosinophils 403. Similarly, in some cases, a determination may be made as to whether one or more groups of cells should be identified as immature granulocytes. This may be done, for example, using a process such as that shown in FIG. 5 . In that process, rather than simply determining whether the cells should be treated as neutrophils 405 as shown in FIG. 4 , a determination 505 of whether the cells should potentially be treated as neutrophils or immature granulocytes is made. The determination 505 may be made, for example, using the same Gaussian Mixture Module clustering described in the background of FIG. 4 , followed by an additional determination 506 of whether the clustered cells are neutrophils by separating the cluster into two subclusters based on darkness and blueness. In this type of approach, relatively less bright and / or bluer cells would be assigned to the cluster for neutrophils (507), while the remaining cells in the cluster identified in the previous determination 505 would be assigned to the immature granulocyte (IG) cluster (508). Additional steps may be included. For example, in some cases, the assignment 302 of cells to clusters may be made after eliminating certain pixels from consideration, such as black pixels (which may be defined as pixels with a low difference between the red and blue channels and the red and green channels (e.g., less than 35) and a low value in the blue channel of an RGB representation (e.g., less than 170)).

[0038] As another example of one type of variation, although various types of clustering are described above in the context of Figures 4 and 5, other approaches, such as agglomerative clustering or distributional clustering, may additionally (or alternatively) be used. Similarly, in some cases, rather than using a gating approach to assign cells to clusters associated with particular types of cells as described in the context of Figure 4, cells may be clustered using parameters such as those set forth in Table 3, and after all cells have been assigned to clusters, the clusters may be associated with different cell types based on their relative positions in feature space. Other variations, such as using sequential clustering and only identifying features for cells (e.g., a mask such as those shown in Table 2 or features such as those shown in Table 3), since these features are used to determine which cells should be assigned to clusters, will be readily apparent to those of skill in the art and can be implemented without undue experimentation based on the present disclosure.

[0039] Another example of one type of variation lies in the parameters that are determined (304) and / or used in assigning cells to clusters (305). For example, in some systems implemented according to the present disclosure, standards for various color values ​​or combinations of color values ​​in an RGB image or other types of values ​​in other images (e.g., L values ​​in an L*a*b image) may also be determined (304). These parameters (and possibly other parameters) may be used in clustering and classification, which may differ from those described above. For example, in some embodiments, cells may be clustered into white blood cell (WBC) or non-WBC clusters according to the BR median (i.e., the blue channel divided by the red channel) and the NV median (i.e., the average of the L channel values ​​in the cell mask divided by the average of the L channel values ​​in the boundary mask). For another example, the system may cluster cells into an eosinophil cluster by utilizing a Gaussian mixture model (GMM) in a two-dimensional feature space, where the first dimension is the average blue channel value of pixels in the dark mask divided by the average blue channel value in the background mask, and the second dimension is the average blue channel minus the red channel of any pixel in the dark mask that has a blue channel below a threshold (e.g., a value defined based on a percentage quantile for the mask). As another example, a system implemented according to the present disclosure may cluster cells into a basophil cluster by using a GMM in a two-dimensional feature space where the first dimension is nucleus_contrast1 and the second dimension is nucleus_contrast2. In some cases, cells may be classified into a lymphocyte-monocyte cluster by applying K-means clustering to the two-dimensional feature space where the features are normalized_x and normalized_y for the two target clusters. The cluster with the smaller normalized_x can be treated as the lymphocyte-monocyte cluster. This cluster can then be further subdivided into lymphocytes and monocytes by treating cells with normalized_y values ​​of 0.42 or less as lymphocytes and cells with normalized_y values ​​greater than 0.42 as monocytes.Clustering may also be performed to separate neutrophils from immature granulocytes, with neutrophils and immature granulocytes clustered using a GMM in a two-dimensional feature space where the first dimension is nonblack_mask_Nv and the second dimension is nonblack_mask_blueness2 (e.g., nonblack_mask is used to help identify specific cell types such as immature granulocytes). As yet another example, in some cases, clusters may be generated in an n-dimensional space defined by the determined (304) features, and cells may be classified based on the relative location of the clusters in that space.

[0040] Variations are possible in the various hardware used to implement the disclosed techniques. For example, in some cases, the image analysis tools and other operations described in the context of Figures 3-9 may be applied using hardware integrated into or local to an analyzer that includes imaging components such as those shown in Figures 1-2. For example, features may be extracted from images captured by the analyzer using a computer connected to the analyzer using a USB cable or over a local area network and used to classify cells depicted therein. Alternatively, in some cases, images captured by the analyzer (or information extracted from the images) may be communicated over a wide area network to a remote processing device, such as a cloud server, that processes the images (or information extracted from those images before transmission) and can be used to classify cells depicted in the images.

[0041] IV. Working Examples As further illustrations of potential implementations and applications of the disclosed technology, the following examples are provided in a non-exclusive manner in which the teachings herein may be combined or applied. It should be understood that the following examples are not intended to limit the scope of protection of any claims that may be presented at any time in this application or a subsequent application related to this application. No disclaimer is intended. The following examples are provided for illustrative purposes only. It is contemplated that the various teachings herein may be configured and applied in numerous other ways. It is also contemplated that some variations may omit specific features mentioned in the following examples. Therefore, none of the aspects or features mentioned below should be considered essential unless expressly stated otherwise, such as at a later date, by the inventor or the inventor's successor in interest. If any claims are presented in this application or in a subsequent application related to this application that include additional features other than those mentioned below, those additional features should not be presumed to have been added for any reason regarding patentability.

[0042] Example 1 1. A method of cell classification, comprising: receiving a set of images comprising representations of a plurality of cells; for each cell of the plurality of cells, determining one or more imaging parameters for the cell based on application of an image analysis algorithm; generating a cluster assignment for the cell by assigning the cell to a cluster of a plurality of clusters; and providing a type for the cell based on the cluster assignment for the cell.

[0043] Example 2 The method of Example 1, wherein for each cell of the plurality of cells, the step of generating a cluster assignment for the cell is performed using a gating algorithm configured to assign the cell to a cluster based on at least one of one or more imaging parameters for both the cell and a population including the plurality of cells.

[0044] Example 3 The method of Example 2, wherein the gating algorithm is configured to assign cells to clusters corresponding to cell types by first determining cells assigned to a non-leukocyte cluster, then determining cells assigned to an eosinophil cluster, then determining cells assigned to a neutrophil cluster, then determining cells assigned to a basophil cluster, then determining cells assigned to a lymphocyte cluster, and then determining cells assigned to a monocyte cluster.

[0045] Example 4 The method of any of Examples 2 or 3, wherein for each cell of the plurality of cells, determining one or more imaging parameters for the cell based on application of an image analysis algorithm includes generating a plurality of masks for the cell; and for each of the plurality of masks, for each of a plurality of features, determining a value for the feature for the mask.

[0046] Example 5 The method of Example 4, wherein for each cell of the plurality of cells, the plurality of clusters comprises a first cluster, and the gating algorithm is configured to determine whether to assign the cell to the first cluster based on a first imaging parameter based on a pixel value in an RGB color space of a cell mask for the cell, and a second imaging parameter based on a pixel value in an L*a*b color space of a cell mask for the cell.

[0047] Example 6 6. The method of any of Examples 4 or 5, wherein, for each cell of the plurality of cells, the plurality of masks for the cell include a cell mask, a nucleus mask, a cytoplasm mask, a dark mask, a black mask, and an IG mask.

[0048] Example 7 7. The method of any of Examples 1 to 6, wherein the one or more imaging parameters include at least two of size, shape, darkness, color, and internal structure.

[0049] Example 8 8. The method of any of Examples 1 to 7, wherein the set of operations includes extracting representations of a plurality of cells from the set of images based on application of a cell isolation algorithm.

[0050] Example 9 The method of any of Examples 1 to 8, comprising a step of capturing a set of images by performing operations including a step of establishing a flow of alignment fluid from an alignment fluid reservoir into a flow cell, a step of generating a sample stream containing the sample fluid and a sheath of alignment fluid on opposite sides of the sample fluid based on injecting sample fluid from a channel into the flow of alignment fluid, and a step of capturing a set of images using a camera focused on the viewing area of ​​the flow cell as the sample stream flows through the viewing area of ​​the flow cell.

[0051] Example 10 10. The method of any of Examples 1 to 9, wherein the plurality of cells comprises blood cells.

[0052] Example 11 11. The method of example 10, wherein the plurality of cells comprises a first white blood cell and a second white blood cell, the first white blood cell type being different from the second white blood cell type.

[0053] Example 12 1. A system for cell classification, comprising: one or more processors; and a non-transitory computer-readable medium storing instructions operable, when executed by the one or more processors, to perform a set of operations, the set of operations comprising: receiving a set of images comprising representations of a plurality of cells; for each cell of the plurality of cells, determining one or more imaging parameters for the cell based on application of an image analysis algorithm; generating a cluster assignment for the cell by assigning the cell to a cluster of a plurality of clusters based on at least one of the one or more imaging parameters for both the cell and a population comprising the plurality of cells; and providing a type for the cell based on the cluster assignment for the cell.

[0054] Example 13 The system of Example 12, wherein, for each cell of the plurality of cells, the instructions, when executed by one or more processors, are operable to generate a cluster assignment for the cell using a gating algorithm configured to assign the cell to a cluster based on at least one of one or more imaging parameters for both the cell and a population including the plurality of cells.

[0055] Example 14 The system of Example 13, wherein the gating algorithm is configured to assign cells to clusters corresponding to cell types by first determining cells assigned to a non-leukocyte cluster, then determining cells assigned to an eosinophil cluster, then determining cells assigned to a neutrophil cluster, then determining cells assigned to a basophil cluster, then determining cells assigned to a lymphocyte cluster, and then determining cells assigned to a monocyte cluster.

[0056] Example 15 The system of any of Examples 13 or 14, wherein for each cell of the plurality of cells, determining one or more imaging parameters for the cell based on application of an image analysis algorithm includes generating a plurality of masks for the cell, and for each of the plurality of masks, determining, for each of a plurality of features, a value for the feature for the mask.

[0057] Example 16 The system of Example 15, wherein for each cell of the plurality of cells, the plurality of clusters comprises a first cluster, and the gating algorithm is configured to determine whether to assign the cell to the first cluster based on a first imaging parameter based on a pixel value in an RGB color space of a cell mask for the cell, and a second imaging parameter based on a pixel value in an L*a*b color space of a cell mask for the cell.

[0058] Example 17 The system of any of Examples 15 or 16, wherein for each cell of the plurality of cells, the plurality of masks for the cell include a cell mask, a nucleus mask, a cytoplasm mask, a dark mask, a black mask, and an IG mask.

[0059] Example 18 18. The system of any of Examples 12 to 17, wherein the one or more imaging parameters include at least two of size, shape, darkness, color, and internal structure.

[0060] Example 19 19. The system of any of Examples 12 to 18, wherein the set of operations includes extracting representations of a plurality of cells from the set of images based on application of a cell isolation algorithm.

[0061] Example 20 20. The system of any of Examples 12 to 19, comprising a flow cell and a camera configured to capture a set of images by flow imaging of the sample stream as it passes through a viewing region of the flow cell, each image of the set of images including a representation of a single cell among the plurality of cells.

[0062] Example 21 The system of Example 20, comprising an alignment fluid reservoir in fluid communication with the viewing region of the flow cell, and a channel adapted to inject a sample fluid into the flow of alignment fluid, thereby forming a sample stream comprising the sample fluid and a sheath of alignment fluid surrounding the sample fluid.

[0063] Example 22 22. The system of any of Examples 12 to 21, wherein the plurality of cells comprises blood cells.

[0064] Example 23 23. The system of example 22, wherein the plurality of cells comprises a first white blood cell and a second white blood cell, the first white blood cell type being different from the second white blood cell type.

[0065] Example 24 A machine comprising a camera and means for classifying cells in an image captured by the camera.

[0066] Example 25 1. A system for cell classification, comprising: a flow cell configured to pass a sample stream through it; a camera configured to capture one or more images of a plurality of cells from the sample stream; a processor; and a non-transitory computer-readable medium having stored thereon instructions operable, when executed by the processor, to perform a set of operations, the set of operations including: determining one or more imaging parameters of the plurality of cells using an image analysis algorithm; identifying a plurality of data clusters within a population distribution for at least one of the one or more imaging parameters; and assigning a cell type to each cell of the plurality of cells based on a data cluster of the plurality of data clusters consisting of the cells.

[0067] Example 26 A system for cell classification, comprising: a processor; and a non-transitory computer-readable medium storing computer-executable code including instructions that, when executed by the processor, perform a set of operations, the set of operations including: receiving one or more images depicting a plurality of cells; determining one or more imaging parameters of the plurality of cells; identifying a plurality of data clusters within a population distribution established from at least one of the one or more imaging parameters; and assigning a corresponding cell type for the data cluster to each data cluster of the plurality of data clusters.

[0068] Example 27 1. A system for cell classification, the system comprising: a flow cell configured to flow a sample stream; a camera configured to capture one or more images of a plurality of cells in the sample stream; a processor; and a non-transitory computer-readable medium having stored thereon computer-executable code including instructions that, when executed by the processor, perform a set of operations, the set of operations including: determining one or more imaging parameters of the plurality of cells; identifying a plurality of data clusters within a population distribution established from at least one of the one or more imaging parameters; and assigning a corresponding cell type to each data cluster of the plurality of data clusters.

[0069] Example 28 1. A method for cell classification, comprising: passing a sample stream through a flow cell; capturing one or more images of a plurality of cells in the sample stream using a camera as the sample stream flows through a viewing area of ​​the flow cell; determining one or more imaging parameters of the plurality of cells using an image analysis algorithm; identifying a plurality of data clusters within a population distribution for at least one of the one or more imaging parameters; and assigning a cell type to each cell of the plurality of cells based on a data cluster of the plurality of data clusters consisting of the cells.

[0070] Example 29 1. A method of cell classification, comprising: capturing one or more images of a plurality of cells using a camera; determining one or more imaging parameters of the plurality of cells; identifying a plurality of data clusters within a population distribution established from at least one of the one or more imaging parameters; and assigning a corresponding cell type to each data cluster of the plurality of data clusters.

[0071] Example 30 1. A method of cell classification, comprising: passing a sample stream through a flow cell; capturing one or more images of a plurality of cells in the sample stream using a camera as the sample stream passes through a viewing area of ​​the flow cell; determining one or more imaging parameters of the plurality of cells; identifying a plurality of data clusters within a population distribution established from at least one of the one or more imaging parameters; and assigning a corresponding cell type to each data cluster of the plurality of data clusters.

[0072] V. Interpretation Each of the calculations or operations / operations described herein may be performed using a computer or other processor having hardware, software, and / or firmware. Various method steps may be performed by modules, which may comprise any of a variety of digital and / or analog data processing hardware and / or software configured to perform the method steps described herein. A module optionally comprises data processing hardware adapted to perform one or more of these steps by having appropriate machine programming code associated therewith, where modules for two or more steps (or portions of two or more steps) are integrated on a single processor board or separated onto different processor boards in any of a variety of integrated and / or distributed processing architectures. These methods and systems often employ tangible media embodying machine-readable code of instructions for performing the method steps described above. Suitable tangible media may comprise memory (including volatile and / or nonvolatile memory), storage media (magnetic recording on floppy disks, hard disks, tapes, etc., optical memory such as CDs, CD-R / Ws, CD-ROMs, DVDs, or any other digital or analog storage medium), etc.

[0073] All patents, patent publications, patent applications, journal articles, books, technical literature, and the like mentioned in this disclosure are hereby incorporated by reference in their entirety for all purposes.

[0074] Different configurations 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 subcombinations are useful and may be employed without reference to other features and subcombinations. The embodiments of the invention have been described for purposes of illustration and not limitation, and alternative embodiments will become apparent to readers of this patent. In certain cases, method steps or actions may be performed in a different order, or actions may be added, deleted, or modified. It will be appreciated that in certain aspects of the invention, multiple components may be substituted for a single component, or multiple components may be substituted for a single component, to provide an element or structure or to perform a given function or functions. Except to the extent that such a substitution would render the particular embodiment of the invention inoperable, it is deemed to be within the scope of the invention. Accordingly, the claims should not be treated as limited to the examples, drawings, embodiments, and descriptions provided above, but should be understood as having the scope to be given when those terms are given their broadest reasonable interpretation as afforded by a commonly used dictionary. except that where a term or phrase is set forth in the subheading "Expressly Provided" as having a particular meaning, it is to be understood to have that meaning when used in the claims.

[0075] Explicit provision It should be understood that in the above examples and claims, a statement that something is "based on" something, etc., should be understood to mean that it is at least partially specified by the thing that is indicated as being based on. To indicate that something must be completely specified based on something else, whatever that thing must be completely specified by, it is described as "based exclusively on."

[0076] In the above examples and claims, it should be understood that the "means for classifying cells in an image captured by a camera" is a means-plus-function invention feature as defined in 35 U.S.C. §112(f), the function being "classifying cells in an image captured by a camera," and the corresponding structure being a computer configured to use the algorithms shown in Figures 3, 4, and 5 and described in the accompanying description.

[0077] It should be understood that in the above examples and claims, the term "a set" should be understood as one or more grouped together.

Claims

1. 1. A method of cell classification comprising: receiving a set of images including a representation of a plurality of cells; For each cell of the plurality of cells, determining one or more imaging parameters for the cells based on application of an image analysis algorithm; generating a cluster assignment for the cell by assigning the cell to a cluster of a plurality of clusters; providing a type for the cell based on the cluster assignment for the cell; A method comprising:

2. 2. The method of claim 1, wherein, for each cell of the plurality of cells, generating a cluster assignment for the cell is performed using a gating algorithm configured to assign the cell to a cluster based on at least one of one or more imaging parameters for both the cell and a population comprising the plurality of cells.

3. The gating algorithm comprises: determining cells initially assigned to non-leukocyte clusters; determining which cells are then assigned to the eosinophil cluster; determining which cells are then assigned to the neutrophil cluster; determining which cells are then assigned to the basophil cluster; determining which cells are then assigned to the lymphocyte cluster; determining which cells are then assigned to the monocyte cluster; The method of claim 2 , further comprising: assigning cells to clusters corresponding to their cell types by:

4. For each cell of the plurality of cells, determining one or more imaging parameters for the cell based on application of the image analysis algorithm comprises: generating a plurality of masks for the cells; for each of the plurality of masks, for each of a plurality of features, determining a value for the feature relative to the mask; The method of claim 2 , comprising:

5. For each cell of the plurality of cells, the plurality of clusters comprises a first cluster, and the gating algorithm comprises: a first imaging parameter based on a value of a pixel in an RGB color space of a cell mask for the cell; and a second imaging parameter based on a pixel value in the L*a*b color space of the cell mask for the cell; 5. The method of claim 4, configured to determine whether to assign the cell to the first cluster based on:

6. For each cell of the plurality of cells, the plurality of masks for the cell include: Cell masks and Nuclear mask and Cytoplasmic mask and The method of claim 4, comprising:

7. The method of claim 1 , wherein the one or more imaging parameters include at least two of size, shape, darkness, color, and internal structure.

8. The method of claim 1 , wherein the set of operations comprises extracting representations of the plurality of cells from the set of images based on application of a cell isolation algorithm.

9. establishing a flow of alignment fluid from an alignment fluid reservoir into the flow cell; generating a sample stream including the sample fluid and a sheath of alignment fluid surrounding the sample fluid based on injecting a sample fluid from a channel into the flow of alignment fluid; capturing the set of images with a camera focused on a viewing region of the flow cell as the sample stream flows through the viewing region of the flow cell; 10. The method of claim 1, comprising capturing the set of images by performing an operation comprising:

10. The method of claim 1 , wherein the plurality of cells comprises blood cells.

11. 11. The method of claim 10, wherein the plurality of cells comprises first white blood cells and second white blood cells, the first white blood cell type being different from the second white blood cell type.

12. 1. A system for cell classification, comprising: one or more processors; A non-transitory computer-readable medium having stored thereon instructions operable to perform a set of operations when executed by the one or more processors, the set of operations comprising: receiving a set of images including a representation of a plurality of cells; For each cell of the plurality of cells, determining one or more imaging parameters for the cells based on application of an image analysis algorithm; generating a cluster assignment for the cell by assigning the cell to a cluster of a plurality of clusters based on at least one of the one or more imaging parameters for both the cell and a population including the plurality of cells; providing a type for the cell based on the cluster assignment for the cell; a non-transitory computer-readable medium, A system including:

13. 13. The system of claim 12, wherein, for each cell of the plurality of cells, the instructions, when executed by the one or more processors, are operable to generate a cluster assignment for the cell using a gating algorithm configured to assign the cell to a cluster based on at least one of the one or more imaging parameters for both the cell and a population including the plurality of cells.

14. The gating algorithm comprises: determining cells initially assigned to non-leukocyte clusters; determining which cells are then assigned to the eosinophil cluster; determining which cells are then assigned to the neutrophil cluster; determining which cells are then assigned to the basophil cluster; determining which cells are then assigned to the lymphocyte cluster; determining which cells are then assigned to the monocyte cluster; The system of claim 13 , configured to assign cells to clusters corresponding to their cell types by:

15. For each cell of the plurality of cells, determining one or more imaging parameters for the cell based on application of the image analysis algorithm comprises: generating a plurality of masks for the cells; for each of the plurality of masks, for each of a plurality of features, determining a value for the feature relative to the mask; The system of claim 13 , comprising:

16. For each cell of the plurality of cells, the plurality of clusters comprises a first cluster, and the gating algorithm comprises: a first imaging parameter based on a value of a pixel in an RGB color space of a cell mask for the cell; and a second imaging parameter based on a pixel value in the L*a*b color space of the cell mask for the cell; 16. The system of claim 15, configured to determine whether to assign the cell to the first cluster based on:

17. For each cell of the plurality of cells, the plurality of masks for the cell include: Cell masks and Nuclear mask and Cytoplasmic mask and The system of claim 15, comprising:

18. The system of claim 12 , wherein the one or more imaging parameters include at least two of size, shape, darkness, color, and internal structure.

19. The system of claim 12 , wherein the set of operations comprises extracting representations of the plurality of cells from the set of images based on application of a cell isolation algorithm.

20. a flow cell and a camera configured to capture the set of images by flow imaging of the sample stream as it passes through a viewing region of the flow cell; The system of claim 12 , wherein each image in the set of images comprises a representation of a single cell in the plurality of cells.

21. 21. The system of claim 20, comprising: an alignment fluid reservoir in fluid communication with the viewing region of the flow cell; and a channel adapted to inject a sample fluid into the flow of alignment fluid, thereby forming a sample stream comprising the sample fluid and a sheath of alignment fluid surrounding the sample fluid.

22. The system of claim 12 , wherein the plurality of cells comprises blood cells.

23. 23. The system of claim 22, wherein the plurality of cells comprises a first white blood cell and a second white blood cell, the first white blood cell type being different from the second white blood cell type.

24. A camera and means for classifying cells in an image captured by the camera; Machinery including.

Images