Systems and methods of processing samples comprising immature granulocytes

Abstract

Samples comprising immature granulocytes may be processed via a method which comprises obtaining a plurality of representations based on, for each of a plurality of cells, obtaining a representation of that cell. Such a method may also comprise, for each cell in a set of cells from the plurality of cells, determining an immature granulocyte subtype corresponding to that cell. In this case, for each cell from the set of cells, the immature granulocyte subtype determined as corresponding to that cell may be selected from a plurality of immature granulocyte subtypes. Such a method may also include calculating an immature granulocyte index. Such an index may be calculated based on, for each subtype from the plurality of immature granulocyte subtypes, a subtype factor based on a number of cells identified as corresponding to that immature granulocyte subtype, and a weight for that immature granulocyte subtype.

Description

[0001] SYSTEMS AND METHODS OF PROCESSING SAMPLES COMPRISING IMMATURE

[0002] GRANULOCYTES

[0003] PRIORITY

[0004] This claims the benefit of U.S. provisional patent application 63 / 615,165, entitled “Systems and Methods of Processing Samples Comprising Immature Granulocytes,” filed December 27, 2023, the disclosure of which is hereby incorporated by reference in its entirety.

[0005] BACKGROUND

[0006] Blood cell analysis is one of the most commonly performed medical tests for providing an overview of a patient's health status. A sample (e.g., a blood sample) can be drawn from a patient's body and stored in a test tube containing an anticoagulant to prevent clotting. The sample can then be processed to determine information such as the number or percent of cells of various different categories that it includes. This information, in turn, can be applied in treatment and / or diagnosis of a patient. For example, high immature granulocyte levels can be diagnostic for conditions such as infections or inflammation.

[0007] While traditional cell processing technology can be effective, it does have drawbacks, including that it has traditionally been difficult to identify immature granulocytes and to provide concrete information based on subtypes of immature granulocytes present in a sample. Accordingly, there is a need for improved sample processing systems, such as systems which can classify immature granulocytes and provide concrete information based on the subtypes of those immature granulocytes which are present in a sample.

[0008] SUMMARY

[0009] Described herein are devices, systems and methods which can be used for the classification of immature granulocytes in a sample, as well as for application of that classification once made.

[0010] An illustrative implementation of such technology relates to a method which comprises obtaining a plurality of representations based on, for each of a plurality of cells, obtaining a representation of that cell. Such a method may also comprise, for each cell in a set of cells from the plurality of cells, determining an immature granulocyte subtype corresponding to that cell. In this case, for each cell from the set of cells, the immature granulocyte subtype determined as corresponding to that cell may be selected from a plurality of immature granulocyte subtypes. Such a method may also include calculating an immature granulocyte index. Such an index may be calculated based on, for each subtype from the plurality of immature granulocyte subtypes, a subtype factor based on a number of cells identified as corresponding to that immature granulocyte subtype, and a weight for that immature granulocyte subtype. Corresponding systems and computer readable media may also be implemented based on this disclosure.

[0011] While multiple examples are described herein, still other examples of the described subject matter will become apparent to those skilled in the art from the following detailed description and drawings, which show and describe illustrative examples of disclosed subject matter. As will be realized, the disclosed subject matter is capable of modifications in various aspects, all without departing from the spirit and scope of the described subject matter. Accordingly, the drawings and detailed description are to be regarded as illustrative in nature and not restrictive.

[0012] BRIEF DESCRIPTION OF THE DRAWINGS

[0013] 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:

[0014] FIG. 1 is a schematic illustration, partly in section and not to scale, showing operational aspects of an exemplary flow cell and high optical resolution imaging device for sample image analysis using digital image processing.

[0015] FIG. 2 illustrates a slide-based vision inspection system in which aspects of the disclosed technology may be used.

[0016] FIG. 3 illustrates a process which may be used to classify, and provide information based on the classification of, immature granulocytes.

[0017] FIG. 4 illustrates an example machine learning model. FIG. 5 illustrates an example of a layer such as may be included in a machine learning model as shown in FIG. 4.

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

[0019] DETAILED DESCRIPTION

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

[0021] According to some aspects of this disclosure, a system comprising a visual analyzer may be provided for obtaining images of a sample comprising particles suspended in a liquid. Such a system may be useful, for example, in characterizing particles in biological fluids, such as detecting and quantifying erythrocytes, reticulocytes, nucleated red blood cells, platelets, and white blood cells, including white blood cell differential counting, categorization and subcategorization and analysis. Other similar uses such as characterizing blood cells from other fluids are also contemplated.

[0022] The classification of blood cells in a blood sample is an exemplary application for which the subject matter is particularly well suited, though other types of body fluid samples may be used. For example, aspects of the disclosed technology may be used in analysis of a non-blood body fluid sample comprising blood cells (e.g., white blood cells and / or red blood cells), such as serum, bone marrow, lavage fluid, effusions, exudates, cerebrospinal fluid, pleural fluid, peritoneal fluid, and amniotic fluid. It is also possible that the sample can be a solid tissue sample, e.g., a biopsy sample that has been treated to produce a cell suspension. The sample may also he a suspension obtained from treating a fecal sample. A sample may also be a laboratory or production line sample comprising particles, such as a cell culture sample. The term sample may be used to refer to a sample obtained from a patient or laboratory or any fraction, portion or aliquot thereof. The sample can be diluted, divided into portions, or stained in some processes.

[0023] In some aspects, samples are presented, imaged and analyzed in an automated manner. In the case of blood samples, the sample may be substantially diluted with a suitable diluent or saline solution, which reduces the extent to which the view of some cells might be hidden by other cells in an undiluted or less-diluted sample. The cells can be treated with agents that enhance the contrast of some cell aspects, for example using permeabilizing agents to render cell membranes permeable, and histological stains to adhere in and to reveal features, such as granules and the nucleus. In some cases, it may be desirable to stain an aliquot of the sample for counting and characterizing particles which include reticulocytes, nucleated red blood cells, and platelets, and for white blood cell differential, characterization and analysis. In other cases, samples containing red blood cells may be diluted before introduction to the flow cell and / or imaging in the flow cell or otherwise.

[0024] The particulars of sample preparation apparatus and methods for sample dilution, permeabilizing and histological staining, generally may be accomplished using precision pumps and valves operated by one or more programmable controllers. Examples can be found in patents such as U.S. Pat. No. 7,319,907. Likewise, techniques for distinguishing among certain cell categories and / or subcategories by their attributes such as relative size and color can be found in U.S. Pat. No. 5,436,978 in connection with white blood cells. The disclosures of these patents are hereby incorporated by reference in their entirety.

[0025] I. IMAGING SYSTEMS

[0026] Turning now to the drawings, FIG. 1 schematically shows an exemplary flow cell 22 for conveying a sample fluid through a viewing zone 23 of a high optical resolution imaging device 24 in a configuration for imaging microscopic particles in a sample flow stream 32 using digital image processing. Flow cell 22 is coupled to a source 25 of sample fluid which may have been subjected to processing, such as contact with a particle contrast agent composition and heating. Flow cell 22 is also coupled to one or more sources 27 of a particle and / or intracellular organelle alignment liquid (PTOAL), such as a clear glycerol solution having a viscosity that is greater than the viscosity of the sample fluid.

[0027] The sample fluid is injected through a flattened opening at a distal end 28 of a sample feed tube 29, and into the interior of the flow cell 22 at a point where the PIOAL flow has been substantially established resulting in a stable and symmetric laminar flow of the PIOAL around / surrounding (e.g., circumferentially in a circular cross-sectional arrangement, or surrounding a plurality of sides of in a non-circular (e.g., rectangular) cross-sectional arrangement) the ribbon-shaped sample stream. The sample and PIOAL streams may be supplied by precision metering pumps that move the PIOAL with the injected sample fluid along a flowpath that narrows substantially. The PIOAL envelopes and compresses the sample fluid in the zone 21 where the flowpath narrows. Hence, the decrease in flowpath thickness at zone 21 can contribute to a geometric focusing of the sample stream 32. The sample fluid ribbon 32 is enveloped and carried along with the PIOAL downstream of the narrowing zone 21, passing in front of, or otherwise through the viewing zone 23 of, the high optical resolution imaging device 24 where images are collected, for example, using a CCD 48. In this way, flow imaging is performed where images from the flowing sample stream and the cellular material contained therein are collected. Processor 18 can receive, as input, pixel data from CCD 48. The sample fluid ribbon flows together with the PIOAL to a discharge 33.

[0028] As shown here, the narrowing zone 21 can have a proximal flowpath portion 21a having a proximal thickness PT and a distal flowpath portion 21b having a distal thickness DT, such that distal thickness DT is less than proximal thickness PT. The sample fluid can therefore be injected through the distal end 28 of sample tube 29 at a location that is distal to the proximal portion 21a and proximal to the distal portion 21b. Hence, the sample fluid can enter the PIOAL envelope as the PIOAL stream is compressed by the zone 21. wherein the sample fluid injection tube has a distal exit port through which sample fluid is injected into flowing sheath fluid, the distal exit port bounded by the decrease in flowpath size of the flow cell.

[0029] The digital high optical resolution imaging device 24 with objective lens 46 is directed along an optical axis that intersects the ribbon-shaped sample stream 32. The relative distance between the objective 46 and the flow cell 33 is variable by operation of a motor drive 54, for resolving and collecting a focused digitized image on a photosensor array. Additional information regarding the construction and operation of an exemplary flow cell such as shown in FIG. 1 is provided in U.S. Patent 9,322,752, entitled “Flow cell Systems and Methods for Particle Analysis in Blood Samples,” filed on March 17, 2014, the disclosure of which is hereby incorporated by reference in its entirety.

[0030] Aspects of the disclosed technology may also be applied in contexts other than flow cell systems such as shown in FIG. 1. For example, FIG. 2 illustrates a slide-based vision inspection system 200 in which aspects of the disclosed technology may be used. In the system shown in FIG. 2, a slide 202 comprising a sample, such as a blood sample, is placed in a slide holder 204. The slide holder 204 may be adapted to hold a number of slides or only one, as illustrated in FIG. 2. An image capturing device 206, comprising an optical system 208 and an image sensor 210, is adapted to capture image data depicting the sample in the slide 202.

[0031] The image data captured by the image capturing device 206 can be transferred to an image processing device 212. The image processing device 112 may be an external apparatus, such as a personal computer, connected to the image capturing device 206. Alternatively, the image processing device 212 may be incorporated in the image capturing device 206. The image processing device 212 can comprise a processor 214, associated with a memory 216, configured to determine changes needed to determine differences between the actual focus and a correct focus for the image capturing device 206. When the difference is determined an instruction can be transferred to a steering motor system 218. The steering motor system 218 can, based upon the instruction from the image processing device 212, alter the distance z between the slide 202 and the optical system 208. Descriptions of approaches which may be used for focusing using this type of setup are provided in U.S. provisional patent application 63 / 291,044 titled “Autofocusing Through Multi-Layer Processing,” filed on December 17, 2021, U.S. patent 9,857,361 titled “Flowcell, sheath fluid, and autofocus systems and methods for particle analysis in urine samples”, filed on March 17, 2014, U.S. patent 10,705,008 titled “autofocus systems and methods for particle analysis in blood samples”, filed on March 17, 2014, U.S. patent 10,705,011, titled “Dynamic focus system and methods”, filed October 5, 2017, and international application 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. II. DATA PROCESSING

[0032] Data captured by systems such as shown in FIGS. 1 and 2 may be subjected to various types of processing. A high level method which may be performed in such processing is shown in FIG. 3, discussed below.

[0033] A. Obtaining Representations

[0034] Initially, in the process of FIG. 3, representations of a plurality of cells would be obtained 301. This may comprise, for example, in a system such as that illustrated in FIG. 1, establishing 302 a flow of alignment fluid from an alignment fluid reservoir into a flow cell. It may also include creating 303 a sample stream comprising sample fluid and a sheath of alignment fluid surrounding the sample based on injecting the sample fluid from a channel into the flow of alignment fluid. With the sample stream established 303, a camera focused on a viewing area of the flow cell may be used to capture 304 a plurality of images as the sample stream is flowing through the viewing area of the flow cell.

[0035] Once the images have been captured 304 they may be subjected to some level of image analysis and / or manipulation to provide representations which may be used in later processing. For example, captured 304 images may be filtered or subdivided so that each image which would subsequently be processed would only depict a single cell. Additionally, or alternatively, portions of images which do not represent a cell (e.g., background) may be removed through processes such as detecting a cell boundary and removing portions of images outside of that boundary (and / or replacing portions of images outside of that boundary with uniform values which had previously been determined to be used for background portions of images). Additionally, in some cases, images (either before or after further processing such as described above) may be transmitted 305 to a remote location (e.g., a cloud processing platform in communication with the location where the images were captured 304 via a wide area network) for further processing, though it should be understood that this transmission 305 may not be present in all cases, and that in some embodiments cell representations may be processed (e.g., through determination 306 of immature granulocyte subtypes, described in more detail below) at the same location where the images were captured 304. It is also possible that representations may be obtained 301 in a different manner entirely. For example, in some cases obtaining representations may be performed using a slide based system such as that shown in FIG. 2, rather than a flow cell based system such as that shown in FIG. 1. Accordingly, the above description of acts which may be involved in obtaining a plurality of representations should be understood as being illustrative only, and should not be treated as liming on the scope of protection provided by this document or any related document.

[0036] B. Determining Immature Granulocyte Subtypes

[0037] After representations of a plurality of cells (e.g., images of those cells, either as captured or following some degree of additional processing) had been obtained 301, immature granulocyte subtypes may be determined 306 for a set of cells comprised by the plurality of cells whose representations had been obtained 301. This may be done in a variety of manners. For example, in some cases, the immature granulocyte subtypes may be determined 306 by providing 307 each representation of a cell from the plurality of cells to a machine learning model trained to classify inputs into a plurality of classes which includes a plurality of subtypes of immature granulocytes (e.g., metamyelocytes, myelocytes and promyelocytes). An example architecture of a machine learning model which may be used for this purpose is illustrated and described below in the context of FIGS. 4 and 5.

[0038] Turning now to FIG. 4, that figure illustrates a machine learning model which can be used in some embodiments in determining 306 immature granulocyte subtypes. In the architecture of FIG. 4, an input image 401 would be analyzed in a series of stages 402a-402n, each of which may be referred to as a “layer,” and which are illustrated in more detail in FIG. 5. As shown in FIG. 5, an input 501 (which, in the initial layer 502a of FIG. 5 would be the input image 401, and otherwise would be the output of the preceding layer) is provided to a layer 502 where it would be processed to generate one or more transformed images 503a-503n. This processing may include convolving the input 501 with a set of filters 504a-504n, each of which would identify a type of feature from the underlying image that would then be captured in that filter’s corresponding transformed image. For instance, as a simple example, convolving an image with the filter shown in table 1 could generate a transformed image capturing the edges from the input image 501.

[0039] [ -1 -1 -1 ]

[0040] Table 1

[0041] As shown in FIG. 5, in addition to generating transformed images 503a-503n a layer may also generate a pooled image 505a-505n for each of the transformed images 503a-503n. This may be done, for example, by organizing the appropriate transformed image into a set of regions, and then replacing the values in that region with a single value, such as the maximum value for the region or the average of the values for the region. The result would be a pooled image whose resolution would be reduced relative to its corresponding transformed image based on the size of the regions it was split into (e.g., if the transformed image had NxN dimensions, and it was split into 2x2 regions, then the pooled image would have size (N / 2)x(N / 2)). These pooled images 505a-505n could then be combined into a single output image 506, in which each of the pooled images 505a- 505n is treated as a separate channel in the output image 506. This output image 506 can then be provided as input to the next layer as shown in FIG. 4.

[0042] Returning to the discussion of FIG. 4, after a final output image 403 has been created through the various stages 402a-402n of processing, the final output image 403 could be provided as input to a neural network 404. This may be done, for example, by providing the value of each channel of each pixel in the output image 403 to an input node of a densely connected single layer network. The output of the neural network 404 could then be treated a classification of the original input image 401. For example, in the case such as shown in FIG. 4, where a neural network 404 has multiple output nodes each of those output nodes may be treated as corresponding to a cell classification, with separate nodes for each subtype of immature granulocytes that would be distinguished as part of the determination (e.g., a neural network 404 as shown in FIG. 4 may have output nodes for metamyelocytes, myelocytes, promyelocytes, non-white blood cells, neutrophils (excluding immature granulocytes), lymphocyte, monocytes, eosinophile, basophile, and blast). The corresponding classification for the output node with the highest value could be treated as the classification for the cell depicted in the input image that resulted in that value being reached.

[0043] Machine learning models such as illustrated in FIGS. 4 and 5 can be trained to determine classes for cells, including classes for immature granulocyte subtypes, using blood cell images having known classes to minimize cross entropy loss among the output nodes of the neural network 404. Such blood cell images can be acquired through human annotation of images produced during normal operation of an analyzer (e.g., a human inspecting images and then labeling them with cell classes), and those classified images can then be used to train a machine learning model such as illustrated in FIGS. 4 and 5. This training may include splitting the classified images up multiple subsets, or folds, and then training and evaluating the model multiple times, with a different fold of training images being held back as a validation set each time (i.e., K-fold cross validation). In this way, performance metrics from each training instance can be averaged to verify the model’s generalization performance and, assuming the performance is acceptable, a final trained version of the model (e.g., whichever trained model had the best individual performance) can be used to make inferences (i.e., classify cell images) in production.

[0044] It is also possible that the determination 306 of immature granulocyte subtypes may be performed using a phased approach. For instance, as shown in FIG. 3, in some cases after representations are provided 307 to a model, at least some of those representations may also be provided 308 to a second model. This may be done, for example, by initially providing the representations to a first model which had been trained to determine whether a representation was an immature granulocyte without determining the immature granulocyte subtype (e.g., a model with an immature granulocyte class, rather than separate classes for metamyelocytes, myelocytes, promyelocytes), and then providing 308 the set of representations of cells classified as immature granulocytes to a machine learning model which had been trained to distinguish between subtypes of immature granulocytes (e.g., a model which had been trained only images of immature granulocytes which had been annotated with the appropriate subclasses, and which had output nodes corresponding to metamyelocytes, myelocytes, promyelocytes).

[0045] Other variations on how the determination 306 of immature granulocyte subtypes may be performed are also possible. For example, in some cases, rather than using machine learning models having architectures such as described above in the context of FIGS. 4 and 5, other types of machine learning models, such as decision trees or support vector machines may be used. It is also possible that additional layers of classification may be performed, such as initially classifying cells as either white blood cells or non-white blood cells, then classifying cells which had been identified as white blood cells into classes which included a class for immature granulocytes, then classifying cells which had been identified as immature granulocytes into immature granulocyte subtypes. Further variations are also possible, and will be immediately apparent to those of skill in the art in light of this disclosure. Accordingly, the above examples of how the determination 306 of immature granulocyte subtypes may take place should be understood as being illustrative only, and should not be treated as limiting.

[0046] C. Calculating Immature Granulocyte Index

[0047] Continuing with the discussion of FIG. 3, after immature granulocyte subtypes had been determined 306, in immature granulocyte index may be calculated 309. As shown in FIG. 3, this may include calculating 310 a subtype factor for each of the immature granulocyte subtypes. For example, for each of the immature granulocyte subtypes, the subtype factor for that subtype may be calculated 310 as the raw count of the number of cells corresponding to that subtype. Alternatively, the subtype factor can be represented as a percentage, being calculated 310 as the number of cells corresponding to that subtype divided by the total number of cells whose representations were obtained (e.g., a percentage for each immature granulocyte subtype).

[0048] Once subtype factor is calculated 310, weighted factors can be obtained 311. For instance, calculating 309 an immature granulocyte index may also include obtaining 311 weighted factors by multiplying each subtype factor by a weight for that immature granulocyte subtype. For example, the subtype factor for metamyelocytes may be multiplied by a first number (e.g., 3), the myelocyte factor may be multiplied by a second number (e.g., 2), and the promyelocyte factor may be multiplied by a third number (e.g., 1). These numbers are just provided by way of example and any numbers can be used whereby each subtype has its own, unique weighting factor.

[0049] Once weighting factors are obtained 311, these values can then be normalized through a division or normalization process 312.For example the weighted factors may then be divided 312 by the sum of the unweighted factors to provide a final immature granulocyte index. For instance, if the subtype factors were counts with weights of 3, 2 and 1 for metamyelocytes, myelocytes and promyelocytes, then the immature granulocyte index may be calculated 309 as (metamyelocyte count * 3 + myelocyte count * 2 + promyelocyte count * 1 ( / (metamyelocyte count + myelocyte count + promyelocyte absolute count). Alternatively, if the subtype factors were percents, then, using those weights, the immature granulocyte index may be calculated 309 as (metamyelocyte percent * 3 + myelocyte percent * 2 + promyelocyte percent * 1 ( / (metamyelocyte percent + myelocyte percent + promyelocyte percent). In some examples, the metamyelocyte, myelocyte, and promyelocyte percentage reflects the relative percentage of each in proportion to immature granulocyte subtypes (such subtypes being metamyelocytes, myelocytes, and promyelocytes), meaning the sum of this percentage is 100% (or 1). In other examples, the metamyelocyte, myelocyte, and promyelocyte percentage reflects the relative percentage of each in proportion to white blood cell types, meaning the sum of this percentage reflects immature granulocyte percentage among white blood cells. In all cases, the immature granulocyte index may function essentially as a maturity index, with the weights providing higher values when the overall mix of immature granulocytes is more mature (e.g., having relatively more metamyelocytes), thereby potentially allowing for more precise and targeted diagnosis and / or treatment of the patient whose cell representations were processed using the disclosed technology. Note, the weighting factor examples (e.g., 1, 2, 3 as the weighting factors) are exemplary and any weights can be used where the more mature cell types (e.g., myelocytes) are weighted more than more immature cell types (e.g., promyelocytes) by assigning a higher weighting factor number to the more mature cell types (in other words, any numbers can be used for the different weighting factors).

[0050] Variations are also possible on how an immature granulocyte index may be calculated 309. For example, in some cases, rather than dividing 312 weighted factors by unweighted factors (e.g., in a normalization process) to obtain the immature granulocyte index, the sum of the weighted factors may simply be treated as the immature granulocyte index without requiring an additional division 312 step (e.g., step 310 is the calculation 309). Thus, if the subtype factors were counts with weights of 3, 1 and 1 (by way of example, though any numerical weights may be used) for metamyelocytes, myelocytes and promyelocytes, then, in some embodiments, the immature granulocyte index may be calculated 309 as (metamyelocyte count * 3 + myelocyte count * 2 + promyelocyte count * 1). Similarly, if the subtype factors were percents, then, using those weights, the immature granulocyte index may be calculated 309 as (metamyelocyte percent * 3 + myelocyte percent * 2 + promyelocyte percent * 1) (e.g., step 311 is the calculation 309). As another type of variation, in some cases different weight values may be used for the different subtypes of immature granulocytes. While, these weights will generally be related to each other by the inequality metamyelocyte weight > myelocyte weight > promyelocyte weight, it is also possible that other relationships may be used. For example, in some cases weights may follow the inequality metamyelocyte weight > myelocyte weight > promyelocyte weight, thereby providing an immature granulocyte index which functions as an immaturity index, rather than a maturity index as described above. Other variations arc also possible and will be immediately apparent to those skilled in the art in light of the above disclosure. Accordingly, the examples provided of how calculation 309 of an immature granulocyte index may take place should be understood as being illustrative only, and should not be treated as limiting on the protection provided by this document or any related document.

[0051] In the examples above, the index was calculated such that a higher index score corresponds to relatively more mature types of immature granulocytes being present in the sample since, for example, metamyelocytes receive a higher weighting factor. Other embodiments can reverse this configuration so that a higher number corresponds to more immature cell types by assigning a higher weighting factor to promyelocytes, for instance in the examples above the promyelocyte count or percentage can receive a relatively higher weighting factor (e.g., 3) compared to myelocytes (e.g., 2) and promyelocytes (e.g., 1). These numbers / values are exemplary and any weighting factors can be used whereby promyelocyte weight > myelocyte weight > metamyelocyte weight.

[0052] Though the examples have primarily been discussed in the context of image analysis of cells (e.g., through flow imaging or static imaging) and an associated immature granulocyte score or index, other embodiments can utilize this score or index in the context of non-image based data. In such examples, hematological techniques such as fluorescence, impedance, or volume-scatter- conductivity approaches can be used to subclassify immature granulocytes among promyelocytes, myelocytes, and metamyelocytes whereby a weight can be assigned to each to come up with a score or index value. The various ways this can be performed are encompassing of the examples expressed herein (e.g., utilizing a raw count or percentage to establish a subtype factor, along with various weighting characteristics to establish different weights for each of promyelocytes, myelocytes, and metamyelocytes).

[0053] III. Variations

[0054] Other variations on, and implementation of, the disclosed technology are also possible. For example, in some cases, rather than determining 306 immature granulocyte subtypes and then calculating 309 an immature granulocyte index based on subtype factors, in some cases the technology disclosed herein may be applied without considering subtypes for immature granulocytes. For instance, in some cases cells may simply be identified as granulocytes, and a granulocyte index may be calculated based on information for the cells identified as granulocytes, rather than considering particular immature granulocyte subtypes (e.g., the immature granulocyte index may be defined as simply the count of immature granulocytes, or as the count of immature granulocytes divided by the sum of the count of immature granulocytes and the count of white blood cells other than immature granulocytes). Additionally, on some cases, the disclosed technology may be used in classifying cells other than immature granulocytes. For example, in some cases a first machine learning model may be used to classify cells as immature granulocytes, non-immature granulocyte white blood cells, and non-white blood cells, and then only the cells classified as non-immature granulocyte white blood cells may be provided to a second classifier which would classify them more precisely into classes such as neutrophil (excluding immature granulocytes), lymphocyte, monocytes, eosinophile, basophile, and blast). Other variations, such as considering only white blood cells when calculating percentages for immature granulocyte subtypes (e.g., treating the plurality of cells whose representations were obtained as only including the white blood cells and dividing the number of cells corresponding to an immature granulocyte subtype by the number of white blood cells to obtain the factor for that subtype) are also possible and will be immediately apparent to those of skill in the art in light of this disclosure. Accordingly, the variations set forth in this section, like the other examples provided in this document, should be understood as being illustrative only, and should not be treated as limiting.

[0055] IV. Examples

[0056] 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 arc 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.

[0057] Example 1

[0058] A method comprising: obtaining a plurality of representations based on, for each of a plurality of cells, obtaining a representation of that cell; for each cell in a set of cells from the plurality of cells, determining an immature granulocyte subtype corresponding to that cell, wherein, for each cell from the set of cells, the immature granulocyte subtype determined as corresponding to that cell is selected from a plurality of immature granulocyte subtypes; and calculating an immature granulocyte index based on for each subtype from the plurality of immature granulocyte subtypes: a subtype factor, wherein the subtype factor is based on a number of cells identified as corresponding to that immature granulocyte subtype; and a weight for that immature granulocyte subtype.

[0059] Example 2

[0060] The method of example 1 , wherein the plurality of immature granulocyte subtypes comprises metamyelocytes, myelocytes and promyelocytes.

[0061] Example 3

[0062] The method of any of examples 1-2 wherein the method comprises, for each subtype from the plurality of immature granulocyte subtypes, calculating the subtype factor for that subtype by dividing the number of cells identified as corresponding to that immature granulocyte subtype by a total number of cells of the plurality of cells.

[0063] Example 4

[0064] The method of any of examples 1-2 wherein for each subtype from the plurality of immature granulocyte subtypes, the subtype factor for that subtype is equal to the number of cells identified as corresponding to that immature granulocyte subtype. Example 5

[0065] The method of any of examples 1-4, wherein calculating the immature granulocyte index comprises: obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; and dividing a sum of the set of weighted factors by a sum of the subtype factors for each subtype from the plurality of immature granulocyte subtypes.

[0066] Example 6

[0067] The method of claim 5, wherein calculating the immature granulocyte index further comprises: normalizing the weighted factors through a normalization or division process.

[0068] Example 7

[0069] The method of any of examples 1-4, wherein: calculating the immature granulocyte index comprises obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; and the immature granulocyte index is equal to a sum of the set of weighted factors.

[0070] Example 8

[0071] The method of any of examples 1-7, wherein: the method comprises, for each cell from the plurality of cells, providing the representation of that cell to a machine learning model trained to classify inputs into a plurality of classes, wherein the plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by providing the representation of that cell to the trained machine learning model.

[0072] Example 9

[0073] The method of any of examples 1-7, wherein the method comprises: for each cell from the plurality of cells, providing the representation of that cell to a first machine learning model, wherein the first machine learning model is trained to classify inputs a first plurality of classes, wherein the first plurality of classes comprises an immature granulocyte class; for each cell whose representation was classified into the immature granulocyte class by the first machine learning model, classifying that cell using a second machine learning model, wherein the second machine learning model is trained to classify inputs into a second plurality of classes, wherein the second plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; the set of cell is the cells whose representations were classified into the immature granulocyte class by the first machine learning model; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by classifying that cell using the second machine learning model.

[0074] Example 10

[0075] The method of any of examples 1-9, wherein the method comprises obtaining the plurality of representations based on: establishing a flow of alignment fluid from an alignment fluid reservoir into a flow cell; 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 flow cell to capture a plurality of images as the sample stream is flowing through the viewing area of the flow cell.

[0076] Example 11

[0077] The method of example 10, wherein the method comprises: after capturing the plurality of images, transferring the plurality of images to a remote location over a network connection; and for each for each cell in the set of cells from the plurality of cells, performing the act of determining the immature granulocyte subtype corresponding to that cell at the remote location.

[0078] Example 12

[0079] The method of any of examples 1-9, where in the method comprises obtaining the plurality of representations with a slide based system.

[0080] Example 13

[0081] A biological analysis system, comprising: one or more processors; and a non-transitory computer readable medium having stored thereon instructions operable to, when executed by the one or more processors, perform the method of any of examples 1-12. Example 14

[0082] A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of any one of the methods of examples 1 to 12.

[0083] Example 15

[0084] A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of any one of the methods of examples 1 to 12.

[0085] Example 16

[0086] A system, comprising: one or more processors; and a non-transitory computer readable medium having stored thereon instructions to, when executed by the one or more processors, perform a set of acts comprising: obtaining a plurality of representations based on, for each of a plurality of cells, obtaining a representation of that cell; for each cell in a set of cells from the plurality of cells, determining an immature granulocyte subtype corresponding to that cell, wherein, for each cell from the set of cells, the immature granulocyte subtype determined as corresponding to that cell is selected from a plurality of immature granulocyte subtypes; and calculating an immature granulocyte index based on for each subtype from the plurality of immature granulocyte subtypes: a subtype factor, wherein the subtype factor is based on a number of cells identified as corresponding to that immature granulocyte subtype; and a weight for that immature granulocyte subtype.

[0087] Example 17

[0088] The system of example 16, wherein the plurality of immature granulocyte subtypes comprises metamyelocytes, myelocytes and promyelocytes.

[0089] Example 18

[0090] The system of any of examples 16-17 wherein the set of acts comprises, for each subtype from the plurality of immature granulocyte subtypes, calculating the subtype factor for that subtype by dividing the number of cells identified as corresponding to that immature granulocyte subtype by a total number of cells of the plurality of cells.

[0091] Example 19

[0092] The system of any of examples 16-17 wherein for each subtype from the plurality of immature granulocyte subtypes, the subtype factor for that subtype is equal to the number of cells identified as corresponding to that immature granulocyte subtype.

[0093] Example 20

[0094] The system of any of examples 16-19, wherein calculating the immature granulocyte index comprises: obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; and dividing a sum of the set of weighted factors by a sum of the subtype factors for each subtype from the plurality of immature granulocyte subtypes.

[0095] Example 21

[0096] The system of example 20, wherein calculating the immature granulocyte index further comprises: normalizing the weighted factors through a normalization or division process.

[0097] Example 22

[0098] The system of any of examples 16-19, wherein: calculating the immature granulocyte index comprises obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; and the immature granulocyte index is equal to a sum of the set of weighted factors.

[0099] Example 23

[0100] The system of any of examples 16-22, wherein: the set of acts comprises, for each cell from the plurality of cells, providing the representation of that cell to a machine learning model trained to classify inputs into a plurality of classes, wherein the plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by providing the representation of that cell to the trained machine learning model.

[0101] Example 24

[0102] The system of any of examples 16-22, wherein the set of acts comprises: for each cell from the plurality of cells, providing the representation of that cell to a first machine learning model, wherein the first machine learning model is trained to classify inputs a first plurality of classes, wherein the first plurality of classes comprises an immature granulocyte class; for each cell whose representation was classified into the immature granulocyte class by the first machine learning model, classifying that cell using a second machine learning model, wherein the second machine learning model is trained to classify inputs into a second plurality of classes, wherein the second plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; the set of cell is the cells whose representations were classified into the immature granulocyte class by the first machine learning model; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by classifying that cell using the second machine learning model.

[0103] Example 25

[0104] The system of any of examples 16-24, wherein: the system comprises: a flow cell; a camera configured to capture the plurality of images via flow imaging of a sample stream as it passes through a viewing area of the flow cell; an alignment fluid reservoir in fluid communication with the viewing area of the flow cell; a channel adapted to inject sample fluid into a flow of the alignment fluid, thereby forming a sample stream comprising the sample fluid and a sheath of alignment fluid surrounding the sample fluid; and each image from the plurality of images comprises a representation of a single cell from the plurality of cells.

[0105] Example 26

[0106] The system of example 25, wherein the set of acts comprises: after capturing the plurality of images, transferring the plurality of images to a remote location over a network connection; and for each for each cell in the set of cells from the plurality of cells, performing the act of determining the immature granulocyte subtype corresponding to that cell at the remote location. Example 27

[0107] The example of any of claims 16-24, wherein the system is a slide based system.

[0108] Example 28

[0109] A method of computer implemented biological analysis comprising performing the set of acts the instructions stored on the non-transitory computer readable medium of the system of any of examples 16-27 are to perform when executed.

[0110] Example 29

[0111] A non-transitory computer readable medium storage medium comprising instructions to perform the set of acts which the instructions stored on the non-transitory computer readable medium of the system of any of examples 16-27 are to perform when executed.

[0112] Example 30

[0113] A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the set of acts which the instructions stored on the non- transitory computer readable medium of the system of any of examples 16-27 arc to perform when executed.

[0114] V. Interpretation

[0115] Each of the calculations or operations described herein may be performed using a computer or other processor having hardware, software, and / or firmware. The various method steps may be performed by modules, and the modules may comprise any of a wide variety of digital and / or analog data processing hardware and / or software arranged to perform the method steps described herein. The modules optionally comprising data processing hardware adapted to perform one or more of these steps by having appropriate machine programming code associated therewith, the modules for two or more steps (or portions of two or more steps) being integrated into a single processor board or separated into different processor boards in any of a wide variety of integrated and / or distributed processing architectures. These methods and systems will often employ a tangible media embodying machine-readable code with instructions for performing the method steps described above. Suitable tangible media may comprise a memory (including a volatile memory and / or a non-volatile memory), a storage media (such as a magnetic recording on a floppy disk, a hai’d disk, a tape, or the like; on an optical memory such as a CD, a CD-R / W, a CD-ROM, a DVD, or the like; or any other digital or analog storage media), or the like.

[0116] 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.

[0117] 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 subcombinations are useful and may be employed without reference to other features and subcombinations. Embodiments of the invention have been described for illustrative and not restrictive purposes, and alternative embodiments will become apparent to readers of this patent. In certain cases, method steps or operations may be performed or executed in differing order, or operations may be added, deleted or modified. It can be appreciated that, in certain aspects of the invention, a single component may be replaced by multiple components, and multiple components may be replaced by a single component, to provide an element or structure or to perform a given function or functions. Except where such substitution would not be operative to practice certain embodiments of the invention, such substitution is considered within the scope of the invention. Accordingly, the claims should not be treated as limited to the examples, drawings, embodiments and illustrations provided above, but instead should be understood as having the scope provided when their terms are given their broadest reasonable interpretation as provided by a general purpose dictionary, except that when a term or phrase is indicated as having a particular meaning under the heading Explicit Definitions, it should be understood as having that meaning when used in the claims.

[0118] Explicit Definitions

[0119] 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.

[0120] It should be understood that, in the above examples and claims, the term “set” should be understood as one or more things which are grouped together.

Claims

What is claimed is:

1. A computer implemented biological analysis method comprising: obtaining a plurality of representations based on, for each of a plurality of cells, obtaining a representation of that cell; for each cell in a set of cells from the plurality of cells, determining an immature granulocyte subtype corresponding to that cell, wherein, for each cell from the set of cells, the immature granulocyte subtype determined as corresponding to that cell is selected from a plurality of immature granulocyte subtypes; and calculating an immature granulocyte index based on, for each subtype from the plurality of immature granulocyte subtypes: a subtype factor, wherein the subtype factor is based on a number of cells identified as corresponding to that immature granulocyte subtype; and a weight for that immature granulocyte subtype.

2. The method of claim 1, wherein the plurality of immature granulocyte subtypes comprises metamyelocytes, myelocytes and promyelocytes.

3. The method of any preceding claim wherein the method comprises, for each subtype from the plurality of immature granulocyte subtypes, calculating the subtype factor for that subtype by dividing the number of cells identified as corresponding to that immature granulocyte subtype by a total number of cells of the plurality of cells.

4. The method of any of claims 1-2 wherein for each subtype from the plurality of immature granulocyte subtypes, the subtype factor for that subtype is equal to the number of cells identified as corresponding to that immature granulocyte subtype.

5. The method of any preceding claim, wherein calculating the immature granulocyte index comprises: obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; anddividing a sum of the set of weighted factors by a sum of the subtype factors for each subtype from the plurality of immature granulocyte subtypes.

6. The method of claim 5, wherein calculating the immature granulocyte index further comprises: normalizing the weighted factors through a normalization or division process.

7. The method of any of claims 1-4, wherein: calculating the immature granulocyte index comprises obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; and the immature granulocyte index is equal to a sum of the set of weighted factors.

8. The method of any preceding claim, wherein: the method comprises, for each cell from the plurality of cells, providing the representation of that cell to a machine learning model trained to classify inputs into a plurality of classes, wherein the plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by providing the representation of that cell to the trained machine learning model.

9. The method of any of claims 1-7, wherein the method comprises: for each cell from the plurality of cells, providing the representation of that cell to a first machine learning model, wherein the first machine learning model is trained to classify inputs a first plurality of classes, wherein the first plurality of classes comprises an immature granulocyte class; for each cell whose representation was classified into the immature granulocyte class by the first machine learning model, classifying that cell using a second machine learning model, wherein the second machine learning model is trained to classify inputsinto a second plurality of classes, wherein the second plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; the set of cell is the cells whose representations were classified into the immature granulocyte class by the first machine learning model; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by classifying that cell using the second machine learning model.

10. The method of any preceding claim, wherein the method comprises obtaining the plurality of representations based on: establishing a flow of alignment fluid from an alignment fluid reservoir into a flow cell; 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 flow cell to capture a plurality of images as the sample stream is flowing through the viewing area of the flow cell.

11. The method of claim 10, wherein the method comprises: after capturing the plurality of images, transferring the plurality of images to a remote location over a network connection; and for each for each cell in the set of cells from the plurality of cells, performing the act of determining the immature granulocyte subtype corresponding to that cell at the remote location.

12. The method of any of claims 1-9, wherein the method comprises obtaining the plurality of representations with a slide based system.

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

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

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

16. A biological analysis system, comprising: one or more processors; and a non-transitory computer readable medium having stored thereon instructions to, when executed by the one or more processors, perform a set of acts comprising: obtaining a plurality of representations based on, for each of a plurality of cells, obtaining a representation of that cell; for each cell in a set of cells from the plurality of cells, determining an immature granulocyte subtype corresponding to that cell, wherein, for each cell from the set of cells, the immature granulocyte subtype determined as corresponding to that cell is selected from a plurality of immature granulocyte subtypes; and calculating an immature granulocyte index based on for each subtype from the plurality of immature granulocyte subtypes: a subtype factor, wherein the subtype factor is based on a number of cells identified as corresponding to that immature granulocyte subtype; and a weight for that immature granulocyte subtype.

17. The system of claim 16, wherein the plurality of immature granulocyte subtypes comprises metamyelocytes, myelocytes and promyelocytes.

18. The system of any of claims 16-17 wherein the set of acts comprises, for each subtype from the plurality of immature granulocyte subtypes, calculating the subtype factor for that subtype by dividing the number of cells identified as corresponding to that immature granulocyte subtype by a total number of cells of the plurality of cells.

19. The system of any of claims 16-17 wherein for each subtype from the plurality of immature granulocyte subtypes, the subtype factor for that subtype is equal to the number of cells identified as corresponding to that immature granulocyte subtype.

20. The system of any of claims 16-19, wherein calculating the immature granulocyte index comprises: obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; and dividing a sum of the set of weighted factors by a sum of the subtype factors for each subtype from the plurality of immature granulocyte subtypes.

21. The system of claim 20, wherein calculating the immature granulocyte index further comprises: normalizing the weighted factors through a normalization or division process.

22. The system of any of claims 16-19, wherein: calculating the immature granulocyte index comprises obtaining a set of weighted factors based on, for each subtype from the plurality of immature granulocyte subtypes, multiplying the subtype factor for that subtype by the weight for that subtype; and the immature granulocyte index is equal to a sum of the set of weighted factors.

23. The system of any of claims 16-22, wherein:the set of acts comprises, for each cell from the plurality of cells, providing the representation of that cell to a machine learning model trained to classify inputs into a plurality of classes, wherein the plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by providing the representation of that cell to the trained machine learning model.

24. The system of any of claims 16-22, wherein the set of acts comprises: for each cell from the plurality of cells, providing the representation of that cell to a first machine learning model, wherein the first machine learning model is trained to classify inputs a first plurality of classes, wherein the first plurality of classes comprises an immature granulocyte class; for each cell whose representation was classified into the immature granulocyte class by the first machine learning model, classifying that cell using a second machine learning model, wherein the second machine learning model is trained to classify inputs into a second plurality of classes, wherein the second plurality of classes comprises each subtype from the plurality of immature granulocyte subtypes; the set of cell is the cells whose representations were classified into the immature granulocyte class by the first machine learning model; and for each cell from the set of cells, determining the immature granulocyte subtype for that cell is performed by classifying that cell using the second machine learning model.

25. The system of any of claims 16-24, wherein: the system comprises: a flow cell; a camera configured to capture the plurality of images via flow imaging of a sample stream as it passes through a viewing area of the flow cell; an alignment fluid reservoir in fluid communication with the viewing area of the flow cell;a channel adapted to inject sample fluid into a flow of the alignment fluid, thereby forming a sample stream comprising the sample fluid and a sheath of alignment fluid surrounding the sample fluid; and each image from the plurality of images comprises a representation of a single cell from the plurality of cells.

26. The system of claim 25, wherein the set of acts comprises: after capturing the plurality of images, transferring the plurality of images to a remote location over a network connection; and for each for each cell in the set of cells from the plurality of cells, performing the act of determining the immature granulocyte subtype corresponding to that cell at the remote location.

27. The system of any of claims 16-24, wherein the system is a slide based system.

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

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

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

Images