Identifying immature cell types using imaging

Abstract

The maturity of the cells can be detected using a computer-implemented image analysis method that involves capturing images of the stained blood cells with a camera and then determining the maturity of the stained blood cells. This determination can include classifying the stained blood cells before generating the maturity of the stained blood cells. Corresponding systems can also be implemented, and the techniques used to determine the maturity of the cells can be used to detect other characteristics, such as infection by malaria or other parasites.

Description

[Technical Field]

[0001] Identifying immature cell types using imaging [Background technology]

[0002] Blood cell analysis is one of the most commonly performed medical tests to provide an overview of a patient's health status. A blood sample may be collected from a patient's body and stored in a test tube containing an anticoagulant to prevent clotting. This blood sample may contain various particles, the identification of which may be clinically useful. For example, immature platelets (reticulated or immature platelets), which contain increased levels of mRNA and rRNA compared to mature cells, usually constitute 4.5% or less of the total platelets in a sample. However, an increased proportion of immature platelets may be a sign of platelet production and an early indicator of bone marrow recovery in patients undergoing chemotherapy and stem cell transplantation. As another example, as red blood cells develop, they pass through an intermediate stage called reticulocytes. These reticulocytes can be classified into immature and mature reticulocytes, and the ratio of immature to total reticulocytes (referred to as the immature reticulocyte fraction, or IRF) has been shown to have clinical utility, as described in Mitrani et al., The Immature Reticulocyte Fraction As an Aid in the Diagnosis and Prognosis of Parvovirus B19 Infection in Sickle Cell Disease, BLOOD (2018) 132 (Supplement 1); 3678.

[0003] Distinguishing particles such as platelets and reticulocytes can be difficult due to the relatively small size of the particles. Quantifying the mature vs. immature state of cells can be even more challenging due to factors such as cell size and the relatively small differences associated with specific particle types (e.g., immature vs. mature platelets, or immature vs. mature reticulocytes). Such discrimination can be difficult in many sample analysis systems, including image-based systems. Therefore, there is a need for a technology that can distinguish particles such as immature platelets and reticulocytes based on data collected by an image-based sample processing system. Summary of the Invention [Problem to be solved by the invention]

[0004] Described herein are devices, systems, and methods for identifying objects such as immature reticulocytes and platelets in data acquired by an image-based sample processing system. [Means for solving the problem]

[0005] An exemplary implementation of such technology relates to a computer-implemented image analysis method for detecting the maturity of blood cells. As described herein, such an image analysis method may include acquiring images of stained blood cells with a camera, classifying the stained blood cells, and determining the maturity of the stained blood cells after they are classified.

[0006] A first aspect of the present invention relates to a computer-implemented image analysis method for detecting maturity of blood cells, the method comprising: acquiring images of stained blood cells with a camera; classifying the stained blood cells, e.g., by using the images of the stained blood cells; and determining the maturity of the stained blood cells after they have been classified, e.g., by using the classification of the stained blood cells.

[0007] In particular, according to the present invention, classifying the stained blood cells includes determining a blood cell type of the stained blood cells. For example, the blood cell type of the stained blood cells can be at least one of white blood cells (WBCs), platelets, and reticulocytes. Alternatively or additionally, according to the present invention, classifying the stained blood cells includes selecting a blood cell type of the stained blood cells from a blood cell type set, the blood cell type set including at least WBCs, platelets, and reticulocytes.

[0008] Illustratively, the determination of the maturity of the stained blood cells is based on the blood cell type of the stained blood cells.

[0009] The method according to the first aspect of the present invention may further include determining whether the stained blood cells are blood cells of interest based on the blood cell type of the stained blood cells. In this case, determining the maturity of the stained blood cells is performed if the stained blood cells are blood cells of interest. If the stained blood cells are not blood cells of interest, the method may include discarding and / or removing the image of the stained blood cells. For example, the stained blood cells are blood cells of interest if their blood cell type is platelets or reticulocytes. In particular, the stained blood cells are not blood cells of interest if their blood cell type is neither platelets nor reticulocytes, for example, if their blood cell type is WBCs.

[0010] Illustratively, the method according to the first aspect of the present invention further comprises treating a blood sample with a lysing agent, a staining agent, or a staining and lysing agent, and flowing the blood sample through a flow cell past a camera, wherein acquiring images of the stained blood cells with the camera is performed while the blood sample flows through the flow cell and past the camera. Notably, in this example, the stained blood cells are contained in the blood sample.

[0011] In some examples, classifying the stained blood cells includes classifying the stained blood cells as at least one of reticulocytes or platelets.

[0012] The method according to the first aspect of the invention further comprises determining at least one of the immature reticulocyte fraction and the immature platelet fraction for the blood sample.

[0013] In particular, determining at least one of the immature reticulocyte fraction and the immature platelet fraction for the blood sample may be performed by using an image of stained blood cells and a plurality of images, each image of the plurality of images depicting a respective stained blood cell of the blood sample. For example, determining at least one of the immature reticulocyte fraction and the immature platelet fraction for the blood sample may include, for each image of the plurality of images, classifying each stained blood cell depicted in the each image, and determining the maturity of the each stained blood cell after the each stained blood cell is classified, e.g., by using the classification of the each stained blood cell.

[0014] For example, determining the immature reticulocyte fraction may include determining some of the images of the plurality of images that depict immature reticulocyte cells. Alternatively or additionally, determining the immature reticulocyte fraction may include determining some of the images of the plurality of images that depict immature platelet cells.

[0015] For example, classifying the stained blood cells may include utilizing an artificial intelligence or machine learning model. In particular, classifying the stained blood cells may include determining the blood cell type of the stained blood cells by using a convolutional neural network and at least a portion of the image of the stained blood cells. For example, the convolutional neural network is configured, e.g., trained, to process at least a portion of the image of the stained blood cells to thereby determine the blood cell type. In particular, the convolutional neural network is a classifier configured, e.g., trained, to assign one blood cell type from a set of blood cell types to the stained blood cells by using at least a portion of the image of the stained blood cells as input. In particular, the portion of the image includes a set of pixels of the image. The set of pixels may be a proper subset of the pixels of the image or may include all pixels of the image.

[0016] Additionally or alternatively, classifying the stained blood cells includes pixel analysis, for example, involving HSV space. In particular, according to the present invention, the foreground of an image is a set of pixels of the image, in particular the portion of the image described above. In some examples, classifying the stained blood cells includes determining a set of image intensities and identifying the foreground in the image based on the set of image intensities.

[0017] Illustratively, the method according to the first aspect of the present invention further comprises calculating an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image, and classifying the stained blood cells based on the average red intensity and the average blue intensity, wherein the average blue intensity and the average red intensity are included in the set of image intensities mentioned above.

[0018] Illustratively, determining the maturity of the stained blood cells includes utilizing pixel foreground analysis. Specifically, according to the present invention, the foreground count is the number of pixels in the image of the stained blood cells that are contained in the foreground.

[0019] For example, determining the maturity of stained blood cells includes determining whether the foreground number satisfies certain conditions of a set of maturity conditions (e.g., each condition of the set of maturity conditions, or a majority of the conditions in the set of maturity conditions). If the foreground number satisfies certain conditions of the set of maturity conditions, the stained blood cells are considered mature. Alternatively, if the foreground number does not satisfy the maturity conditions (e.g., fails to satisfy each condition, or fails to satisfy a majority of the conditions), the stained blood cells are considered immature.

[0020] Alternatively, determining the maturity of the stained blood cells includes determining whether the foreground number satisfies each condition of a set of immaturity conditions. If the foreground number satisfies all conditions of the set of immaturity conditions, the stained blood cells are considered immature. Alternatively, if the foreground number does not satisfy at least one condition of the set of immaturity conditions, the stained blood cells are considered mature.

[0021] For example, determining the maturity of stained blood cells includes determining whether the pixel foreground count exceeds a threshold amount, in which case the set of immaturity conditions specifically includes the condition that the pixel foreground count exceeds a threshold amount.

[0022] Illustratively, the method includes determining that the stained blood cells are immature based on determining that the pixel foreground count exceeds a threshold amount.

[0023] A second aspect of the present invention relates to an image analysis system for detecting maturity of blood cells, the system comprising: a camera configured to acquire images of stained blood cells; and a processor configured to classify the stained blood cells (e.g., by using the images of the stained blood cells); and determine the maturity of the stained blood cells after they have been classified, e.g., by using the classification of the stained blood cells. Alternatively, the maturity determination step may be part of the classification step (e.g., immature cell types are part of an initial classification step - e.g., a primary classifier trained to distinguish immature cell types).

[0024] The image analysis system may further include a flow cell, and the camera may be configured to acquire images of the stained blood cells as the blood sample flows through the flow cell and past the camera. In particular, the flow cell and the camera are positioned relative to one another such that the flow cell is configured to carry at least a portion of the sample fluid through a field of view of the camera.

[0025] Illustratively, the processor is configured to classify the stained blood cells as at least one of reticulocytes or platelets. Alternatively or additionally, the processor is further configured to determine at least one of an immature reticulocyte fraction and an immature platelet fraction for the blood sample.

[0026] Additionally or alternatively, the processor may be configured to utilize a convolutional neural network to classify the stained blood cells.

[0027] Additionally or alternatively, the processor may be configured to classify the stained blood cells based on identifying foreground within the image based on the intensity of each pixel within the image.

[0028] For example, the processor may be further configured to calculate an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image. Further, the processor may be configured to classify the stained blood cells based on the average red intensity and the average blue intensity.

[0029] Illustratively, the processor is configured to determine the maturity of the stained blood cells based on the pixel foreground count.

[0030] In particular, the processor is configured to determine that the stained blood cells are immature based on a pixel foreground number exceeding a threshold amount.

[0031] For example, an image analysis system according to the first aspect of the invention is configured to carry out a method according to the second aspect of the invention.

[0032] A third aspect of the invention relates to a machine comprising a camera and means for classifying and determining the maturity of cells in images acquired by the camera.

[0033] A fourth aspect of the invention relates to a computer program product comprising instructions which, when the program is run by a computer, cause the computer to carry out a method according to the first aspect of the invention.

[0034] A fifth aspect of the invention relates to a computer-readable medium, for example a transitory computer-readable medium, comprising instructions which, when executed by a computer, cause the computer to carry out a method according to the first aspect of the invention.

[0035] Additional aspects of the present invention include modules used to assist in imaging of biological samples. An illumination module is used to illuminate the sample to provide favorable lighting conditions for an image acquisition device (e.g., a camera) to capture images of the cells of the sample. A staining module is used to stain biological cells (e.g., the interior or nuclear regions of blood cells) to visualize the interior regions of the cells to assist in cell classification and / or maturity determination.

[0036] It should be noted that any of the various features of the embodiments disclosed herein may be included in each of the embodiments or may be combined.

[0037] 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. As will be understood, the disclosed subject matter is capable of modification in various aspects, all without departing from the spirit and scope of the described subject matter. Accordingly, the drawings and detailed description should be regarded as illustrative in nature and not restrictive.

[0038] While the specification concludes with claims particularly pointing out and distinctly claiming the invention, it is believed the invention will be better understood from the following description of specific examples taken in conjunction with the accompanying drawings, in which like numerals identify the same elements and in which: [Brief explanation of the drawings]

[0039] [Figure 1] 1 is a schematic diagram, partially in cross section and not to scale, illustrating operational aspects of an exemplary flow cell and high optical resolution imaging device for sample image analysis using digital image processing. FIG. [Figure 2] FIG. 1 illustrates a slide-based vision inspection system in which aspects of the disclosed technology may be used. [Figure 3]FIG. 12 is a perspective view of an exemplary illumination module in conjunction with another exemplary flow cell and a high optical resolution imaging device for sample image analysis using digital image processing. [Figure 4] 4 is a perspective view of the lighting module of FIG. 3 with a portion of the housing removed to show the light emitter, focusing lens, dichroic element, and collimating lens of the lighting module. [Figure 5] 4 is a top plan view of the lighting module of FIG. 3 showing light traveling from each of the light emitters to a collimating lens. [Figure 6A] FIG. 1 is a perspective view of an exemplary staining module for mixing a stain with a sample to form a sample mixture and incubating the sample mixture, showing lamination of a ferromagnetic sheet to a housing of the staining module. [Figure 6B] FIG. 6B is a perspective view of the dye module of FIG. 6A showing the wrapping of the ferromagnetic sheet to the housing using adhesive tape. [Figure 6C] 6B is a perspective view of the dyeing module of FIG. 6A showing the wrapping of the dyeing module's heating coil around the housing. FIG. [Figure 7A] FIG. 1 is a side view of an exemplary multi-chamber staining module for mixing a stain with a sample to form a sample mixture and incubating the sample mixture. [Figure 7B] FIG. 7B is a top plan view of the multi-chamber staining module of FIG. 7A. [Figure 8] FIG. 1 illustrates a process that can be used to stain a sample. [Figure 9] FIG. 1 illustrates a process that can be used to determine blood cell maturity and to determine the maturity of particles in a sample. [Figure 10] FIG. 1 illustrates a process that can be used to classify particles based on the morphological features of the imaged cells. [Figure 11] FIG. 1 illustrates an example machine learning model. [Figure 12] FIG. 12 illustrates an example of layers that may be included in a machine learning model such as that shown in FIG. [Figure 13]FIG. 1 illustrates a method that can be used to generate a maturity index for imaged cells. [Figure 14] FIG. 1 illustrates how maturity information is used to generate overall information about a biological sample. [Figure 15] FIG. 1 depicts a method in which cell maturity is generated as part of classifying cells. DETAILED DESCRIPTION OF THE INVENTION

[0040] The drawings are not intended to be limiting in any way, and it is contemplated that various embodiments of the invention may be embodied in a variety of other ways, including those not necessarily depicted in the drawings. The accompanying drawings, which are incorporated in and form a part of this specification, illustrate several aspects of the invention and, together with the description, serve to explain the principles of the invention, although it should be understood that the invention is not limited to the precise arrangements shown.

[0041] The present disclosure relates to, among other things, devices, systems, compositions, and methods for analyzing samples containing particles. In one embodiment, the present invention relates to an automated particle imaging system comprising an analysis device, which may be, for example, a visual analysis device. In some embodiments, the visual analysis device may further comprise a processor to facilitate automated analysis of the image.

[0042] 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. Such a system may be useful in characterizing particles in biological fluids, such as detecting and quantifying red blood cells, immature reticulocytes, mature reticulocytes, nucleated red blood cells, immature platelets, and / or white blood cells, including, for example, white blood cell differential counting, categorization and subcategorization, and analysis. Other similar applications, such as characterizing blood cells from other fluids and / or distinguishing parasites such as malaria, are also contemplated.

[0043] While identifying various types of particles in a blood sample is an exemplary application for which the subject matter is particularly well suited, other types of bodily fluid samples may also be used. For example, embodiments 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, serous fluid, exudate, cerebrospinal fluid, pleural fluid, peritoneal fluid, and amniotic fluid. It is also possible that the sample may be a solid tissue sample, e.g., a biopsy sample that has been processed to produce a cell suspension. The sample may also be a suspension obtained from processing a stool sample. The sample may also be a laboratory or production 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 be diluted, divided into portions, or stained in some processes.

[0044] In some embodiments, the sample is automatically presented, imaged, or analyzed. In the case of a blood sample, the sample can be substantially diluted with a suitable diluent or saline solution to reduce the extent to which some cells may be obscured by other cells in an undiluted or less diluted sample. Cells can be treated with agents that enhance the contrast of some cellular aspects, for example, using permeabilizing agents to permeabilize cell membranes and tissue stains to adhere 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 white blood cell differentiation, characterization, and analysis. In other cases, a sample containing red blood cells can be diluted before being introduced into a flow cell and / or imaged or otherwise processed in the flow cell.

[0045] The subject matter of sample preparation devices and methods for sample dilution, permeabilization, and tissue staining can generally 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. Similarly, techniques for distinguishing between specific 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, relating to white blood cells. The disclosures of these patents are incorporated herein by reference in their entireties.

[0046] I. System Overview Turning now to the drawings, Figure 1 schematically illustrates an exemplary flow cell 22 for conveying a sample fluid through a viewing area 23 of a high optical resolution imaging device 24 configured for imaging microscopic particles in a sample flow stream 32 using digital image processing. The flow cell 22 is coupled to a source 25 of sample fluid that may have undergone processing 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 intracellular organelle orientation liquid (PIOAL), such as a clear glycerol solution having a viscosity greater than that of the sample fluid.

[0047] Sample fluid is injected into the flow cell 22 through a flat opening at the distal end 28 of the sample feed tube 29 at a point where PIOAL flow is substantially established, resulting in a steady and symmetric laminar flow of PIOAL above and below (or on either side of) the ribbon-shaped sample stream. The sample and PIOAL streams may be supplied by precision metering pumps that move the PIOAL, along with the injected sample fluid, along a substantially narrowing flow path. The PIOAL covers and compresses the sample fluid in the narrowing region 21. Thus, the reduction in flow path thickness in region 21 may contribute to the geometric focusing of the sample stream 32. The sample fluid ribbon 32 is then conveyed, covered together with the PIOAL, downstream of the narrowing region 21, past or separately through the viewing region 23 of the high-optical-resolution imaging device 24, where images are collected using, for example, a charge-coupled device (CCD) 48. In this manner, flow imaging is performed to collect images from the flowing sample stream and the cellular material contained therein. Processor 18 may receive as input pixel data from CCD 48. The sample fluid ribbon flows along with the PIOAL to outlet 33.

[0048] As shown here, narrowed region 21 can have proximal flow path portion 21a having a proximal thickness Pt and distal flow path portion 21b having a distal thickness Dt, such that distal thickness Dt is less than proximal thickness Pt. Sample fluid can therefore 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, sample fluid can enter the PIOAL envelope when the PIOAL stream is constrained by region 21, and the sample fluid injection tube has a distal exit port through which the sample fluid is injected into the flowing sheath fluid, the distal exit port being restricted by the reduced flow path size of the flow cell.

[0049] A digital high optical resolution imaging device 24 having an 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 to resolve and collect a focused digitized image on a photosensor array. Additional information regarding the construction and operation of an exemplary flow cell such as that shown in FIG. 1 is provided in U.S. Pat. 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.

[0050] Aspects of the disclosed technology may be applied in contexts other than flow cell systems such as that 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 containing a sample, such as a blood sample, is placed in a slide holder 204. The slide holder 204 may be adapted to hold several slides, or, as illustrated in FIG. 2, only one slide. An image acquisition device 206, comprising an optical system 208 and an image sensor 210, is adapted to acquire image data depicting the sample in the slide 202.

[0051] Image data acquired by image capturing device 206 may be transferred to image processing device 212. Image processing device 212 may be an external device, such as a personal computer, connected to image capturing device 206. Alternatively, image processing device 212 may be incorporated into image capturing device 206. Image processing device 212 may include a processor 214 associated with memory 216 configured to determine the change needed to determine the difference between the actual focus and the correct focus of image capturing device 206. When the difference is determined, instructions may be transferred to steering motor system 218. Steering motor system 218 may change the distance z between slide 202 and optical system 208 based on instructions from image processing device 212. Descriptions of techniques that may be used for focusing using this type of setup are provided in U.S. Pat. No. 9,857,361, entitled "Flowcell, sheath fluid, and autofocus systems and methods for particle analysis in urine samples," issued on January 2, 2018, and U.S. Pat. No. 10,705,008, entitled "Autofocus systems and methods for particle analysis in blood samples," issued on July 7, 2020, the disclosures of which are incorporated herein by reference in their entireties.

[0052] II. Lighting module example In the context of imaging, including the flow imaging concepts discussed for biological imaging, proper illumination is important to enable proper visualization of biological material (e.g., blood cells). Illumination is an important criterion for image acquisition devices (e.g., cameras) to acquire clear and bright images of the sample, for example, for algorithms to properly identify cell types.

[0053] In a system such as that shown in FIG. 1 or FIG. 2, an illumination module (also referred to as an illumination system or lighting device) 300 as shown in FIG. 3 may be used to illuminate cells to be imaged by a camera, such as the high-optical resolution imaging device 24 of FIG. 1 or the image sensor 210 of FIG. 2. For example, the illumination module 300 may be incorporated in place of the light source 42 shown in FIG. 1. FIG. 3 shows the illumination module 300 in conjunction with an exemplary flow cell 302, which may be configured and operative like the flow cell 22 shown in FIG. 1, and a high-optical resolution imaging device 304, which may be configured and operative like the high-optical resolution imaging device 24 shown in FIG. 1. As shown, the illumination module 300 is positioned on the side of the flow cell 302 opposite the high-optical resolution imaging device 304 to illuminate an analysis region (also referred to as an image acquisition region or imaging region), such as a viewing area of the flow cell 302, as the sample moves through the analysis region to facilitate acquisition of an image of the sample by the high-optical resolution imaging device 304. The cells of the sample may be stained prior to moving through the flow cell 302 via a staining module, such as, for example, any of the staining modules 400, 500 described below.

[0054] In the example shown, lighting module 300 includes a housing 310, a plurality of light emitters 312 a, 312 b, and 312 c, a plurality of focusing lenses 314 a, 314 b, and 314 c, a plurality of dichroic elements 316 a, 316 b, and 316 c, and a collimating lens 318. Light emitters 312 a, 312 b, and 312 c may each be any suitable light source, including, for example, an arc lamp, a light emitting diode (LED), or any other suitable light emitter for providing either pulsed or continuous illumination. In some embodiments, light emitters 312 a, 312 b, and 312 c may each be configured to emit light of a different color than the other light emitters 312 a, 312 b, and 312 c. For example, the first light emitter 312a may include a red LED configured to emit red light having a wavelength of about 600 nanometers to about 650 nanometers, such as about 620 nanometers, the second light emitter 312b may include a green LED configured to emit green light having a wavelength of about 470 nanometers to about 600 nanometers, such as about 525 nanometers, and / or the third light emitter 312c may include a blue LED configured to emit blue light having a wavelength of about 400 nanometers to about 470 nanometers, such as about 450 nanometers.

[0055] The light emitters 312a, 312b, 312c are each mounted on a side of the housing 310 in a row extending generally parallel to the optical axis of the high optical resolution imaging device 304 so that light emitted by each light emitter 312a, 312b, 312c may initially be projected into the interior of the housing 310 in a direction generally perpendicular to the optical axis of the high optical resolution imaging device 304. As shown, each focusing lens 314a, 314b, 314c is mounted within the housing 310 and is axially aligned with a corresponding one of the light emitters 312a, 312b, 312c to focus the light emitted by the corresponding light emitter 312a, 312b, 312c.

[0056] Each dichroic element 316a, 316b, 316c is mounted within the housing 310 in line with a corresponding one of the light emitters 312a, 312b, 312c to reflect and / or filter light emitted by one or more of the light emitters 312a, 312b, 312c (and focused by the corresponding focusing lens 314a, 314b, 314c). In this regard, each dichroic element 316a, 316b, 316c in this example includes a corresponding reflecting side 320a, 320b, 320c and a corresponding filtering side 322a, 322b, 322c. Each dichroic element 316a, 316b, 316c is oriented obliquely with respect to the optical axis of the high optical resolution imaging device 304 and with respect to light received from the corresponding focusing lens 314a, 314b, 314c. For example, each dichroic element 316a, 316b, 316c may be oriented at an angle of approximately 45 degrees with respect to the optical axis of the high optical resolution imaging device 304. More specifically, each dichroic element 316a, 316b, 316c is oriented such that the corresponding reflective side 320a, 320b, 320c faces generally toward both the corresponding focusing lens 314a, 314b, 314c and the high optical resolution imaging device 304, while the corresponding filtering side 322a, 322b, 322c faces generally away from both the corresponding focusing lens 314a, 314b, 314c and the high optical resolution imaging device 304.

[0057] In this manner, the reflective side 320a, 320b, 320c of each dichroic element 316a, 316b, 316c may be configured to reflect light emitted from the corresponding light emitter 312a, 312b, 312c (and focused by the corresponding focusing lens 314a, 314b, 314c) and traveling approximately perpendicular to the optical axis of the high optical resolution imaging device 304, so that the reflected light travels approximately parallel to the optical axis of the high optical resolution imaging device 304. For example, the reflective side 320a of the first dichroic element 316a may be configured to reflect light emitted from the first light emitter 312a (and focused by the first focusing lens 314a) so that the reflected light travels approximately parallel to the optical axis of the high optical resolution imaging device 304, the reflective side 320b of the second dichroic element 316b may be configured to reflect light emitted from the second light emitter 312b (and focused by the second focusing lens 314b) so that the reflected light travels approximately parallel to the optical axis of the high optical resolution imaging device 304, and / or the reflective side 320c of the third dichroic element 316c may be configured to reflect light emitted from the third light emitter 312c (and focused by the third focusing lens 314c) so that the reflected light travels approximately parallel to the optical axis of the high optical resolution imaging device 304.

[0058] Additionally, the filtering sides 322a, 322b, 322c of at least some of the dichroic elements 316a, 316b, 316c may be configured to filter light received from one or more of the other dichroic elements 316a, 316b, 316c. For example, the filtering side 322b of the second dichroic element 316b may be configured to filter light reflected from the first dichroic element 316a, and / or the filtering side 322c of the third dichroic element 316c may be configured to filter light reflected from the second dichroic element 316b and / or to filter light reflected from the first dichroic element 316a (and filtered by the second dichroic element 316b). In this regard, the filtering side 322a, 322b, 322c of each dichroic element 316a, 316b, 316c can be configured to inhibit light having wavelengths below a corresponding predetermined threshold from passing therethrough. For example, the filtering side 322b of the second dichroic element 316b can be configured to inhibit light having wavelengths below a predetermined threshold of approximately 596 nanometers from passing therethrough, and / or the filtering side 322c of the third dichroic element 316c can be configured to inhibit light having wavelengths below a predetermined threshold of approximately 484 nanometers from passing therethrough. In some cases, the filtering sides 322b, 322c of the second and third dichroic elements 316b, 316c can be configured to allow approximately 95% of light having wavelengths above the corresponding predetermined threshold to pass therethrough and / or inhibit approximately 99% of light having wavelengths below the corresponding predetermined threshold from passing therethrough.

[0059] Thus, light emitted by the first light emitter 312a may be focused by the first focusing lens 314a, reflected by the reflective side 320a of the first dichroic element 316a, filtered by the filtering side 322b of the second dichroic element 316b, and filtered by the filtering side 322c of the third dichroic element 316c; light emitted by the second light emitter 312b may be focused by the second focusing lens 314b, reflected by the reflective side 320b of the second dichroic element 316b, and filtered by the filtering side 322c of the third dichroic element 316c; and / or light emitted by the third light emitter 312c may be focused by the third focusing lens 314c and reflected by the reflective side 320c of the third dichroic element 316c. In this manner, the light emitted by light emitters 312a, 312b, 312c can be conditioned via dichroic elements 316a, 316b, 316c to improve the whiteness of the light before being focused together by collimating lens 318 into a single parallel beam of white light, which can then be transmitted out of housing 310 towards flow cell 302.

[0060] It should be understood that when the first light emitter 312a includes a red LED, the red light emitted by the first light emitter 312a is substantially unaffected by the filtering sides 322b, 322c of the second and third dichroic elements 316b, 316c due to the relatively high wavelength of the red light, which may be greater than the threshold of either of the filtering sides 322b, 322c.

[0061] The collimated beam of white light formed by collimating lens 318 may be transmitted toward flow cell 302 through a light pipe (also referred to as an illumination column or light guide), such as a hexagonal light pipe. The light pipe may be configured to collect the collimated beam of white light, randomize the collimated beam of white light, and / or focus the collimated beam of white light onto flow cell 302 (e.g., at the viewing area of flow cell 302). The light pipe may be positioned relative to collimating lens 318 so that the collimated beam focuses to a point (e.g., phase) at the entrance of the light pipe. The light pipe may be attached to a flow cell holder (not shown), such as flow cell holder 700 described below, that holds flow cell 302 to securely fasten the exit of the light pipe relative to flow cell 302. In this manner, the distance between the light pipe and flow cell 302 is constant because the light pipe and flow cell 302 are operably connected through flow cell holder 700.

[0062] In some embodiments, the light emitters 312a, 312b, and 312c can be configured to provide pulsed illumination synchronized with one another (e.g., simultaneously) in a profile to capture still images of sample cells moving through the flow cell 302. For example, the objective lens of the high-optical resolution imaging device 304 can be opened, then the light emitters 312a, 312b, and 312c can simultaneously emit pulses of light, then an image of the sample cells can be captured by the high-optical resolution imaging device 304, and then the objective lens of the high-optical resolution imaging device 304 can be closed. This process can be repeated for any suitable number of iterations. In some cases, the duration of each pulse can be from about 1 microsecond to about 3 microseconds, such as about 2 microseconds. The pulse frequency can depend on the camera frame acquisition frequency, which can be from about 220 frames per second to about 300 frames per second. For example, 220 frames per second can correspond to one picture approximately every 4.5 milliseconds. The objective lens may be open for approximately 100 milliseconds, which may be sufficient to acquire one image. In some embodiments, a higher frame rate may be used, for example, with a reduced field of view. The increased speed may be used depending on the particular application, such as the type of camera used. It should be understood that an increased speed may provide more data (e.g., more images of more sample cells) in less time, while a smaller field of view may eliminate visual landmarks (e.g., "black lines") that may be used for focusing. It should also be understood that the pixel rate may contribute to the amount of data provided. For example, increasing the pixel rate may compensate for decreasing the frame rate to provide the same amount of data.

[0063] In some embodiments, the light emitters 312a, 312b, and 312c can be configured to emit pulses of light sequentially to operate in a diagnostic mode. For example, a time delay can be provided between each flash to acquire three separate images of a particular sample cell at three different instants along the sample cell's path. The pixel representation of distance can then be used to calculate the sample cell's velocity to determine whether the sample cell is accelerating or decelerating and / or whether the flow is too fast to acquire reliable data. This diagnostic mode can be selectively turned on and off. For example, after operating in the diagnostic mode, the light emitters 312a, 312b, and 312c can be configured to simultaneously emit pulses of light as described above in the basic operating mode.

[0064] III. Dyeing module example In some embodiments, the flow imaging system incorporates dyes and associated staining modules to enhance visualization of biological material (e.g., blood cells). The stains can be useful, for example, to stain the interior cellular regions of white blood cells to help visualize internal nuclear structures and identify cell types (e.g., identification as a subset of white blood cell types—e.g., neutrophils, lymphocytes, monocytes, eosinophils, or basophils). In some instances, dyes are applied to the outer surface of cells to enhance visualization of the cells (e.g., outer staining of red blood cells or platelets).

[0065] A. Example of a single-chamber staining module In a system such as that shown in Figure 1 or Figure 2, a staining module (also referred to as a staining device) 400 as shown in Figures 6A-6C can be used to both mix the sample with a staining agent and to incubate the sample mixture by heating before cells in the sample mixture are imaged by a camera such as the high optical resolution imaging device 24 of Figure 1 or the image sensor 210 of Figure 2. For example, the staining module 400 can be incorporated in place of the source 25 shown in Figure 1 or between the source 25 and the sample feed tube 29 shown in Figure 1 to facilitate mixing of the sample with the staining agent and incubation of the sample mixture before acquisition of an image of the sample by the high optical resolution imaging device 24. The staining agent can include any suitable composition. For example, the staining agent may be configured according to any one or more of the teachings of U.S. Pat. No. 9,279,750, entitled "Method and Composition for Staining and Sample Processing," issued March 8, 2016, the disclosure of which is incorporated herein by reference in its entirety; and / or U.S. Pat. No. 9,322,753, entitled "Method and Composition for Staining and Processing a Urine Sample," issued April 26, 2016, the disclosure of which is incorporated herein by reference in its entirety; and / or U.S. Patent Publication No. 2021 / 0108994, entitled "Method and Composition for Staining and Sample Processing," published April 15, 2021, the disclosure of which is incorporated herein by reference in its entirety.

[0066] In the illustrated embodiment, the staining module 400 includes a housing 410, a pair of ferromagnetic sheets 412, and a heater in the form of a heating coil 414 (FIG. 6C). In various embodiments, the heating coil 414 may include a resistive coil or, alternatively, an inductive coil. As best shown in FIG. 6A, the housing 410 includes multiple (e.g., four) side walls 420 that collectively define an inner chamber 422 (also referred to as a sample reservoir) for receiving a staining agent and a sample, mixing the staining agent and the sample to form a sample mixture, and incubating the sample mixture. The housing 410 also includes a top wall 424 and a port 426 that extends through the top wall 424 to the inner chamber 422. The port 426 may enable a dye dispensing device (not shown) to deliver a staining agent to the inner chamber 422 and / or a sample dispensing device (not shown) to deliver a sample to the inner chamber 422 to be added to the staining agent.

[0067] In some embodiments, the housing 410 may include a metallic material with a relatively high thermal conductivity, such as aluminum, to promote uniform heating of the housing 410 and, similarly, uniform heating of the contents of the inner chamber 422. In the embodiment shown, the sidewalls 420 of the housing 410 are layered with respective ferromagnetic sheets 412 to improve the efficiency (e.g., due to the relatively low magnetic properties of aluminum) of the heating (e.g., resistive heating, or alternatively, inductive heating) performed by the dyeing module 400. More specifically, each ferromagnetic sheet 412 is affixed to the outer surface of a corresponding pair of sidewalls 420. It should be understood that any suitable number of ferromagnetic sheets 412 may be used to layer the sidewalls 420. In the embodiment shown, a thermally conductive compound 430 is deposited on the outer surface of the sidewalls 420 to adhere the ferromagnetic sheets 412 to the sidewalls 420. As best shown in FIG. 6B, adhesive tape 432 is wrapped tightly around ferromagnetic sheet 412 to firmly engage the inner surface of ferromagnetic sheet 412 with the outer surface of sidewall 420.

[0068] As best shown in FIG. 6C , the heating coil 414 includes a wire 440 wound around the sidewall 420 of the housing 410 (and around the ferromagnetic sheet 412). The wire 440 may include a metallic material with relatively high electrical conductivity, such as copper. The wire 440 may have any suitable cross-sectional area and / or thickness and may be wound to define any suitable number of turns for the heating coil 414. The heating coil 414 in one embodiment functions as an inductor or induction coil and is operably coupled to a power supply unit 450, which may be configured to drive the heating coil 414 to a frequency such that, under excitation, the heating coil 414 behaves as a resonant circuit, producing an alternating current (AC) magnetic field at or near the heating coil 414. This magnetic field may generate an electromagnetic field (EMF) on the exterior surface of the sidewall 420, which may cause the AC current. This current, in combination with the resistivity of the housing 410, may result in power losses and heat the exterior surface of the sidewall 420. Such heating may be transferred to the contents of chamber 422, such as the stain and / or sample. It should be appreciated that such inductive heating may be performed using relatively low input power and / or may achieve uniform heating of the contents of chamber 422, thereby improving staining and / or lysis performance. In this regard, exciting the circuit at a resonant frequency may deliver maximum power, and exciting the circuit at an increasing frequency may effectively adjust power delivery. Alternative embodiments may utilize a resistive heater / resistance heating coil for heater coil 414.

[0069] In some embodiments, a temperature sensor, such as a thermistor (not shown), may be configured to continuously sense the temperature of the contents of chamber 422. The temperature sensor may be configured to send a feedback signal indicative of the sensed temperature to a controller (not shown), which may in turn be configured to send a control signal to power supply unit 450 for selectively powering heating coil 414. In this manner, the controller may cease heating of the contents of chamber 422 upon reaching a threshold temperature. In one example, the controller utilizes a heating control algorithm, and the feedback signal is incorporated into elements of the algorithm or computer-driven instructions provided to power supply unit 450 and / or heating coil 414 for optimal temperature control. In some embodiments, the controller may be configured to send a control signal to a maintenance heater (not shown) for maintaining the contents of chamber 422 at the threshold temperature.

[0070] In one embodiment, multiple staining modules are contemplated, each utilizing the structure of Figures 6A-6C (i.e., multiple structural elements 400). In this manner, multiple samples can be stained, incubated, or otherwise prepared at similar times. In one example, each staining module has its own unique heating element. In one example, the staining module has multiple chambers 422, each capable of receiving a sample, and a common heating structure connected to the entire module (e.g., a single housing 410 having a common heating coil 414 surrounding the multiple chambers 422 and the housing 410).

[0071] B. Example of a multi-chamber staining module In a system such as that shown in Figure 1 or 2, a multi-chamber staining module (also referred to as a staining device) 500 as shown in Figures 7A and 7B can be used to both mix a sample with a staining agent and to incubate the sample mixture by inductive heating before cells in the sample mixture are imaged by a camera such as the high-optical resolution imaging device 24 of Figure 1 or the image sensor 210 of Figure 2. For example, the staining module 500 can be incorporated in place of the source 25 shown in Figure 1 or between the source 25 and the sample feed tube 29 shown in Figure 1 to facilitate mixing of the sample with the staining agent and incubation of the sample mixture before acquisition of an image of the sample by the high-optical resolution imaging device 24. The staining agent can include any suitable composition. For example, the staining agent may be constructed according to any one or more of the teachings of U.S. Pat. No. 9,279,750, entitled "Method and Composition for Staining and Sample Processing," issued March 8, 2016, the disclosure of which is incorporated herein by reference in its entirety; and / or U.S. Pat. No. 9,322,753, entitled "Method and Composition for Staining and Processing a Urine Sample," issued April 26, 2016, the disclosure of which is incorporated herein by reference in its entirety; and / or U.S. Pat. No. 2021 / 0108994, entitled "Method and Composition for Staining and Sample Processing," published April 15, 2021, the disclosure of which is incorporated herein by reference in its entirety. It should be noted that these stains generally describe stains that contain a lytic agent for lysing red blood cells, a penetrating agent for penetrating white blood cells, a staining element for staining the internal contents of white blood cells, and a repair element for repairing white blood cells to prevent the dye from escaping.

[0072] In the embodiment shown, the staining module 500 includes a housing 510, a bracket (also referred to as a sleeve) 512, and a heater in the form of a heating coil 514. The housing 510 includes multiple internal chambers 522a, 522b, 522c, 522d (also referred to as sample reservoirs) for receiving a stain and a sample, mixing the stain and the sample to form a sample mixture, and incubating the sample mixture. The housing 510 also includes a top wall 524 and multiple ports 526a, 526b, 526c, 526d that extend through the top wall 524 to corresponding internal chambers 522a, 522b, 522c, 522d. Ports 526a, 526b, 526c, 526d may enable a dye dispensing device (not shown) to deliver staining agent to the corresponding inner chambers 522a, 522b, 522c, 522d and / or enable a sample dispensing device (not shown) to deliver sample to the corresponding inner chambers 522a, 522b, 522c, 522d to be added to the staining agent. Although four inner chambers 522a, 522b, 522c, 522d and corresponding ports 526a, 526b, 526c, 526d are shown, it should be understood that there may be any suitable number of inner chambers 522a, 522b, 522c, 522d and corresponding ports 526a, 526b, 526c, 526d, such as two, three, or more than four inner chambers 522a, 522b, 522c, 522d and corresponding ports 526a, 526b, 526c, 526d. In some variations, the first and second inner chambers 522a, 522b may be configured for use as white blood cell (WBC) chambers 522a, 522b, while the third inner chamber 522c may be configured for use as a red blood cell (RBC) chamber 522c.

[0073] In some embodiments, the housing 510 may comprise a metallic material having a relatively high thermal conductivity, such as aluminum, to promote uniform heating of the housing 510 and likewise uniform heating of the contents of the inner chambers 522a, 522b, 522c, 522d.

[0074] In the embodiment shown, a bracket or sleeve 512 is positioned about the housing 510. The bracket 512 includes an inner bore 530 sized and configured to receive at least a portion of the housing 510. In some embodiments, the inner bore 530 may be sized and configured to slidably receive a portion of the housing 510 such that the portion of the housing 510 can be selectively inserted into and / or removed from the inner bore 530. The bracket 512 also includes upper and lower edges 532, 534 that define a recessed region 536 therebetween. The recessed region 536 is sized and configured to accommodate at least a portion of the heating coil 514.

[0075] The heating coil 514 includes a wire 540 wound around the bracket 512 over the recessed region 536. The wire 540 may include a metallic material with relatively high electrical conductivity, such as copper. The wire 540 may have any suitable cross-sectional area and / or thickness and may be wound to define any suitable number of turns for the heating coil 514. The heating coil 514 is operably coupled to a power supply unit 550, which may be configured to drive the heating coil 514 to a frequency such that, under excitation, the heating coil 514 behaves as a resonant circuit, producing an alternating current (AC) magnetic field at or near the heating coil 514; in this manner, the heating coil 514 acts as an inductor and may be configured as an induction coil or induction heating coil. This magnetic field may generate an electromagnetic field (EMF) on the exterior surface of the housing 510, which may cause an AC current. This current, in combination with the resistance of the housing 510, may result in power losses and heat the exterior surface of the housing 510. Such heating may be transferred to the contents of one or more chambers 522 a, 522 b, 522 c, 522 d, such as staining agent and / or sample. It should be understood that such inductive heating may be performed using relatively low input power and / or may achieve uniform heating of the contents of one or more chambers 522 a, 522 b, 522 c, 522 d, thereby improving staining and / or lysis performance. In this regard, exciting the circuit at a resonant frequency may deliver maximum power, and exciting the circuit at increasing frequencies may effectively adjust power delivery.

[0076] In some embodiments, the bracket or sleeve 512 is made of a conductive material (e.g., a metallic material such as aluminum) to enhance heat transfer to the housing and interior surfaces that receive the blood sample and dye. In some embodiments, the bracket or sleeve 512 is made of a ferromagnetic material. In some embodiments, the bracket or sleeve 512 is not utilized, and instead, the heater / heater coil 514 is attached directly to the exterior surface of the housing 510.

[0077] In some embodiments, a temperature sensor, such as a thermistor (not shown), may be configured to continuously sense the temperature of the contents of one or more chambers 522 a, 522 b, 522 c, 522 d. The temperature sensor may be configured to send a feedback signal indicative of the sensed temperature to a controller (not shown), which may in turn be configured to send a control signal to the power supply unit 550 for selectively activating the heating coil 514. In this manner, the controller may cease heating of the contents of the chamber 522 when a threshold temperature is reached. In some embodiments, the controller may be configured to send a control signal to a maintenance heater (not shown) for maintaining the contents of one or more chambers 522 a, 522 b, 522 c, 522 d at the threshold temperature.

[0078] C. Sample Preparation Process Example In a system such as that shown in FIG. 1 or FIG. 2, a process such as that shown in FIG. 8 can be used to perform sample preparation before cells are imaged by a camera such as the high-optical resolution imaging device 24 of FIG. 1 or the image sensor 210 of FIG. 2. First, in the process of FIG. 8, a staining agent can be delivered to a chamber, such as chamber 422 of the staining module 400 shown in FIGS. 6A-6C or one or both of the WBC chambers 522a, 522b of the staining module 500 shown in FIGS. 7A-7B, in step 601. This can include, for example, delivering the staining agent to chambers 422, 522a, 522b through corresponding ports 426, 526a, 526b via a dye dispensing device. The staining agent can then be preheated in chambers 422, 522a, 522b, such as by induction heating, in step 602. Next, a sample can be delivered to chambers 422, 522a, 522b in step 603. This may include, for example, delivering the sample to the chambers 422, 522a, 522b through the corresponding ports 426, 526a, 526b via a dye dispensing device to be added to the staining agent. In some embodiments, delivering the sample to the chambers 422, 522a, 522b may include mixing the sample with preheated dye within the chambers 422, 522a, 522b. In the process of FIG. 8 , a homogenous sample mixture may then be formed within the chambers 422, 522a, 522b in step 604. This may include, for example, using fluid energy to mix the sample and dye, such as by periodically drawing the sample from and pushing the sample back into the chambers 422, 522a, 522b through corresponding tangential ports in the housings 410, 510 to perform backflow mixing. Alternatively, this may involve using a magnet to drive a spherical ferromagnetic ball placed within the chamber 422, 522a, 522b to effect the agitated mixing. As another example, this may involve introducing one or more air bubbles into the bottom of the chamber 422, 522a, 522b to create a vortex.

[0079] The homogeneous sample mixture may then be heated in chambers 422, 522a, 522b, such as by inductive or resistive heating, in step 605. In some embodiments, the homogeneous sample mixture may be heated to a threshold temperature by inductive or resistive heating and then maintained at the threshold temperature by a maintenance heater. It should be understood that in embodiments using a multi-chamber staining module 500, the sample mixture in both WBC chambers 522a, 522b may be heated simultaneously by inductive heating, and any sample in RBC chamber 522c may also be heated by inductive heating (even if such heating of the sample in RBC chamber 522c is not required prior to imaging), while the fourth chamber 522d may remain empty. In some other embodiments using the multi-chamber staining module 500, one or more chambers 522a, 522b, 522c, 522d, such as the first WBC chamber 522a, may be used to heat the sample mixture while one or more of the other chambers 522a, 522b, 522c, 522d, such as the RBC chamber 522c, are being flushed simultaneously; in such cases, increased power may be provided to the heating coil 540 (e.g., by adding an amount of energy equal to the energy lost due to such a cooling effect) to counteract any cooling effect that the flushing of the RBC chamber 522c may otherwise have on the heating of the sample mixture in the first WBC chamber 522a.

[0080] After the homogeneous sample mixture reaches the threshold temperature, the sample mixture may be transferred to a flow cell, such as flow cell 22 of Figure 1, to be imaged by a camera, such as high optical resolution imaging device 24 of Figure 1. For example, the homogeneous sample mixture may be transferred directly from chamber 422, 522a, 522b to flow cell 22 (e.g., without further preparation). It should be appreciated that heating the sample mixture in the same chamber 422, 522a, 522b in which it is formed may improve the throughput of the staining process.

[0081] While the formation and inductive heating of the sample mixture is described as occurring within the chambers 422, 522 of the housings 410, 510, it should be understood that alternative arrangements may include a tube having a lumen (not shown) in which the sample mixture may be formed and inductively heated in a manner similar to that described above. Additionally, or alternatively, any one or more of the teachings herein may be combined with any one or more of the teachings disclosed in U.S. Patent No. 9,429,524, entitled "Systems and Methods for Imaging Fluid Samples," issued August 30, 2016, the disclosure of which is incorporated herein by reference in its entirety.

[0082] In some embodiments, the addition of diluent is part of the preparation step, and the diluent is added to each chamber 522a-522d before, after, or both before and after the blood sample is added to each chamber. For example, the RBC chamber may receive a diluent as the primary or only preparation reagent, while the WBC chamber may receive both a diluent and a dye.

[0083] It should be understood that the preparation steps for the RBC chamber may differ from those for the WBC chamber. For example, the RBC chamber may utilize preparation steps that involve receiving a) a diluent followed by a blood sample, b) a blood sample followed by a diluent, or c) a diluent followed by a blood sample followed by additional diluent, but not a dye. In this manner, the preparation time for the RBC chamber may be shorter, and the workflow may involve running the RBC sample through the imaging process while the WBC sample is still being prepared.

[0084] In some embodiments, the staining reagent utilizes both a lysing agent (to lyse red blood cells) and a staining agent (to penetrate the remaining white blood cells, stain their interior areas, and repair the white blood cells so that the dye does not escape). In this manner, a single staining reagent can be used to process a particular type of cell (e.g., white blood cells) to remove red blood cells and stain the remaining white blood cells. Other embodiments may utilize multiple compositions, e.g., a first lysing reagent to lyse red blood cells and a second staining reagent to stain white blood cells, and the workflow involves a chamber (e.g., a WBC chamber) receiving a separate lysing reagent and a separate staining reagent to prepare the WBC sample for visualization.

[0085] In some embodiments, various chambers (e.g., 522a-522d) are not intended to strictly prepare dedicated cell types; in other words, cell types can be rotated. For example, a chamber can alternate between being used for RBC preparation and being used for WBC preparation. In this manner, once a sample in a chamber is prepared for imaging, a cleaning cycle can be utilized to clean the chamber before receiving a subsequent blood sample (e.g., chamber 522a can be configured to first prepare a specific amount of WBCs for the same preparation run, followed by a specific amount of RBCs for a sample preparation run, e.g., one WBC preparation, followed by one RBC preparation, or two WBC preparations, followed by one RBC preparation, followed by two more WBC preparations, etc.). Cleaning reagents, such as diluents or cleaning agents, can be used between sample runs to eliminate carryover. Even in situations where a particular chamber is used only for a specific cell type (e.g., 522a is used only as a WBC chamber), there can be a cleaning step run after the sample is prepared and imaged to eliminate carryover.

[0086] Other embodiments may still utilize multiple dyes as part of the preparation process. For example, a first dye configured to stain white blood cells in the manner described herein and a second dye configured to stain at least one of platelets or reticulocytes. These staining compositions may be used uniquely in various workflows. For example, a first chamber of the housing 410, 510 may be used to prepare a white blood cell sample, including receiving at least a WBC dye and a lytic reagent, while a second chamber of the housing 410, 510 may be used to prepare a platelet sample, which is different from the WBC dye and lytic reagent—this chamber receiving at least a platelet reagent.

[0087] While the terms white blood cell (WBC) chamber and red blood cell (RBC) chamber are used to refer to sample preparation chambers for imaging, it should be noted that the sample imaged as a result of the preparation process may enable in vivo imaging of multiple cell types. For example, a WBC chamber utilizes lysis to eliminate red blood cells, but lysis may still retain platelets and reticulocytes, so a sample prepared in a WBC chamber may still image, for example, at least white blood cells, platelets, and reticulocytes. Similarly, an RBC chamber may undergo a different preparation procedure than a WBC chamber (e.g., no lysis or no dye / lysis combination reagent), but a sample prepared in an RBC chamber may still visualize multiple cell types, such as red blood cells and one or more of white blood cells, platelets, and reticulocytes.

[0088] Additional information regarding lighting and dyeing modules can be found in U.S. Patent Application Nos. 18 / 224937, 18 / 224947, and 18 / 224953, the contents of which are incorporated herein by reference in their entireties.

[0089] IV. Examples of Maturity Determinations The systems of FIG. 1 or 2 generally illustrate imaging systems for acquiring images of particles (e.g., blood cells). In the case of certain cells, such as reticulocytes and platelets, these cells start out as immature versions with relatively high RNA content. Being able to quantify cell maturity, e.g., quantifying immature platelets or immature reticulocytes, can provide detailed information about a patient's health and thus can be valuable. In some embodiments herein, image analysis techniques can be utilized to analyze images of cell types and also, for example, analyze the nuclear region of cells to correlate with RNA content assessments, classify or quantify cell maturity (e.g., identify cells as immature platelets or immature reticulocytes, and identify the number of such cells in a blood sample). These techniques can, in various embodiments, be used to generally identify and / or enumerate immature cells (e.g., not just immature platelets or immature reticulocytes) in a blood sample.

[0090] In systems such as those shown in FIG. 1 or 2, the maturity of particles in a sample can be determined using a process that acquires an image of the particle and then uses the image to determine its maturity. An illustration of such a process is provided in FIG. 9, which illustrates not only acquiring an image of a particle 901 and determining its maturity 902, but also illustrates specific operations that may be performed during image acquisition. As illustrated in FIG. 9, this may optionally include one or more sample preparation steps. These may include, for example, treating the sample with a lysing agent 903 to remove one or more classes of particles that are not of interest. For example, if the sample is a blood sample and the process of FIG. 9 is used to determine the maturity of reticulocytes or platelets in the sample, the sample may be treated with a lysing agent (e.g., saponin) that destroys mature red blood cells in the sample 903. Alternatively (or additionally), sample preparation may include depositing 904 a staining composition (e.g., New Methylene Blue (NMB)) that stains RNA inside the cells in the sample and thus may distinguish immature platelets and reticulocytes, which have relatively more RNA than mature platelets or reticulocytes, and depositing 905 the sample into a chamber where the sample may be mixed 906. In embodiments in which these types of preparation steps are performed, after the sample is prepared, an image of the stained blood cells may be acquired 907. This image acquisition 907 may occur in the context of additional activities, such as flowing 98 the sample through a flow cell (e.g., when using a flow imaging system such as that shown in FIG. 1).

[0091] While FIG. 9 depicts sample preparation steps that may be performed in some embodiments, it should be noted that the steps and their depiction in FIG. 9 are intended to be merely illustrative and are not intended to suggest limitations on how sample preparation may be performed (in the embodiments in which it is performed, if at all). For example, while FIG. 9 illustrates lysis and staining as essentially separate processes, in some cases, a single composition may include both a lysis component for lysing mature red blood cells and a staining composition for staining the remaining cells. For example, step 904 may include depositing a composition containing both a lysis compound (e.g., saponin) and a staining compound (e.g., new methylene blue) as a single step. In some examples, multiple reagents or compositions may be used (e.g., a lysis composition and a separate staining composition added after the lysis composition). It is also possible that the different steps illustrated in FIG. 9 may be performed in a different order, for example, by depositing 905 the biological sample simultaneously with, before, or after depositing 904 the staining composition. Similarly, in some embodiments, the preparation involves only staining the blood sample, but not lysing the blood sample, i.e., the mature red blood cells remain intact. Descriptions of dyes and dye / lysing compounds can be found in U.S. Pat. No. 9,279,750 and U.S. Patent Publication No. 2021 / 0108994, the contents of which are incorporated herein by reference in their entireties.

[0092] However, once image acquisition 901 is performed (e.g., via flow imaging as shown in FIG. 1 or slide imaging as shown in FIG. 2) and an image depicting blood cells is obtained, the image can be used to determine 902 the maturity of the cells. This can include classifying 1000 the depicted cells, for example, using a method that performs classification based on morphological features. When this type of classification is performed, cells whose maturity is not of interest can be identified, and maturity determination need not be completed for those cells (although data about those cells can be retained for other purposes). For example, if a blood sample is expected to contain white blood cells, platelets, and reticulocytes (e.g., because mature red blood cells have been removed by treatment with a lytic agent), and maturity determination is performed to calculate immature platelet and reticulocyte fractions, maturity determination can be omitted for cells classified as white blood cells, but the remaining cells can have their maturity determined based on their classification as reticulocytes or platelets. An illustration of how this type of classification 1000 can be performed based on morphological features is set forth below in the context of FIG.

[0093] 10, an intensity image is generated 1001 based on an image acquired by the system. In particular, the intensity image includes pixels of the image acquired by the system and associates each of these pixels with a respective intensity associated with it. For example, if the system is configured to acquire an RGB image, the intensity image may be generated 1001 by associating each pixel of the image acquired by the system with the average value of the R, G, and B color channels for that pixel.

[0094] Following step 1001, foreground and background portions may be identified 1002 within these intensity images. This may be done, for example, by binarization, where darker pixels representing blood cells are separated from lighter pixels representing background; for example, by binarization at a particular intensity value, where pixels above an intensity value are classified as foreground and pixels below an intensity value are classified as background, or vice versa, depending on the encoding of the intensity value. For example, in some embodiments, each channel of each pixel in an image acquired by the system has a value between 0 and 255. In this case, pixels associated with intensities greater than or equal to, for example, an intensity value equal to about 204 are considered to belong to the foreground, and pixels associated with intensities less than an intensity value equal to about 204 are considered to belong to the background. These intensity values may depend on imaging system conditions (which may include, for example, lighting conditions, dye quality, camera imaging characteristics, and cell velocity when the cell image is acquired). In some examples, the pixel intensity threshold may have various values, for example, numbers within the ranges of approximately 170-230, 190-210, or 200-207, depending on the quality of these systems.

[0095] Once the foreground and background pixels have been identified, intensities may be calculated 1003 for the foreground pixels. This may be done, for example, by calculating 1005 an average red intensity and calculating 1006 an average blue intensity of the foreground pixels from the original RGB image. Other techniques for calculating 1003 intensities for the foreground pixels are possible and may be used instead of or in addition to RGB-based calculations. For example, if the image is encoded using a hue, saturation, value color model—i.e., an HSV image—calculating 1003 intensities may simply involve treating the V values from the pixels of the HSV image as intensities. Thus, the description of calculating 1003 intensities should be understood to be merely illustrative and should not be treated as limiting.

[0096] Once calculated 1003, the intensities may be used to classify 1004 the type of imaged cell. For example, a photograph may be treated as depicting a white blood cell (e.g., denoted WBC) if the mean intensity of the red channel for its foreground pixels (e.g., denoted MASK_R_MEAN) is less than a specified white blood cell (WBC) red channel intensity cutoff value and the mean intensity of the blue channel for its foreground pixels (e.g., denoted MASK_B_MEAN) is less than a specified white blood cell (WBC) blue channel intensity cutoff value. Similar approaches may be used when identifying other types of cells, such as platelets and reticulocytes, although more complex classifications are possible. For example, in some cases, rather than simply comparing the foreground pixel red channel mean intensity (e.g., denoted as MASK_R_MEAN) and the foreground pixel blue channel mean intensity (e.g., denoted as MASK_B_MEAN) to a cutoff, the classification may include one or more of: (i) comparing the foreground pixel red channel mean intensity (e.g., denoted as MASK_R_MEAN) to the foreground pixel blue channel mean intensity (e.g., denoted as MASK_B_MEAN); (ii) comparing a function of the foreground pixel red channel mean intensity (e.g., denoted as MASK_R_MEAN) to a function of the foreground pixel blue channel mean intensity (e.g., denoted as MASK_B_MEAN); and / or (iii) comparing a function of the foreground pixel red channel mean intensity (e.g., denoted as MASK_R_MEAN) and a function of the foreground pixel blue channel mean intensity (e.g., denoted as MASK_B_MEAN) to a cutoff value.

[0097] To illustrate classification 1004 in the method of FIG. 10 , WBC, platelet, and reticulocyte classification criteria for images acquired using a blood cell imaging analysis device (in one example, a blood cell imaging analysis device that utilizes flow imaging, where cells are imaged as they travel past a camera in a flow cell and binarized (e.g., with a binarization value of approximately 204) with intensity values used to separate foreground from background pixels) are set forth below in Table 1. For purposes of the table below, MASK_B_MEAN refers to foreground pixel blue channel mean intensity, and MASK_R_MEAN refers to foreground pixel red channel mean intensity.

[0098] [Table 1]

[0099] It should be understood that the classification criteria in Table 1 (as well as the threshold for separating foreground from background 1003) are intended to be merely exemplary. In embodiments in which cells are classified 1000, different approaches may be used to perform the classification other than the approach described above in the context of FIG. 10. For example, rather than using the morphology-based classification described in the context of FIG. 10, some embodiments may classify cells 1000 using a machine learning model. An example of such a machine learning model is shown in FIG. 11. When using model 1100 of FIG. 11, input image 1101 is analyzed in a series of stages 1102a-1102n, each of which may be referred to as a "layer," and is illustrated in more detail in FIG. 12. As shown in FIG. 12, input 1201 (which in the initial layer 1102a of FIG. 11 is input image 1101, and which is otherwise the output of a preceding layer) is provided to layer 1202, where it is processed to generate one or more transformed images 1203a-1203n. This processing may involve convolving the input 1201 with a set of filters 1204a-1204n, each of which identifies a type of feature from the underlying image that is captured in that filter's corresponding transformed image. For example, as a simple example, convolving an image with the filters shown in Table 2 may produce a transformed image that captures edges from the input image 1201.

[0100] [Table 2]

[0101] As shown in FIG. 12 , in addition to generating transformed images 1203 a–1203 n, a layer may also generate a pooled image 1205 a–1205 n for each of the transformed images 1203 a–1203 n. This may be done, for example, by organizing the appropriate transformed image into a set of regions and replacing the values in each of the regions with a single value, such as the maximum value for that region or the average of the values for that region. The result is a pooled image whose resolution is reduced relative to its corresponding transformed image based on the size of the regions into which the transformed image was divided (e.g., if a transformed image has dimensions N×N and is divided into 2×2 regions, the pooled image has size (N / 2)×(N / 2)). These pooled images 1205 a–1205 n may then be combined into a single output image 1206, with each of the pooled images 1205 a–1205 n treated as a separate channel in the output image 1206. The output image 1206 may be provided as input to the next layer as shown in FIG.

[0102] Returning to the discussion of FIG. 11 , after the final output image 1103 has been created through the various stages 1102 a-1102 n of processing, the final output image 1103 may be provided as an input to a neural network 1104. This may be done, for example, by providing the value of each channel of each pixel in the output image 1103 to the input nodes of a densely connected single-layer network. The output of the neural network 1104 may then be treated as a classification of the original input image 1101. For example, if the neural network 1104 is as shown in FIG. 11 with multiple output nodes, each of those output nodes may be treated as corresponding to a cell classification (e.g., one output node corresponding to WBC, one output node corresponding to reticulocytes, and one output node corresponding to platelets), and the corresponding classification for the output node with the highest value may be treated as the classification for the cell depicted in the input image that resulted in that value being reached.

[0103] A machine learning model such as that illustrated in FIGS. 11 and 12 can be trained to classify cells using blood cell images with known classes to minimize cross-entropy loss between output nodes of the neural network 1104. Such blood cell images can be obtained through human annotation of images generated during normal operation of the analyzer (e.g., a human inspecting images and then labeling them with a cell class), but they can also be obtained in other ways. For example, images can be classified using morphology-based classification as discussed above in the context of FIG. 10, and those classified images can then be used to train a machine learning model such as that illustrated in FIGS. 11 and 12. This training can include splitting the classified images into multiple subsets, or folds, and then training and evaluating the model multiple times, with a different fold of training images retained as a validation set each time (i.e., K-fold cross-validation). In this manner, performance metrics from each training instance may be averaged to verify the model's generalization ability, and, provided performance is acceptable, the final trained version of the model (e.g., whichever trained model had the best individual performance) may be used to influence generation (i.e., classify cell images). Additional types of machine learning models, such as models with a single output, are described in Patent Cooperation Treaty Application No. PCT / US22 / 52702, filed December 13, 2022, the disclosure of which is incorporated herein by reference in its entirety, and may be used in place of the machine learning model of FIG. 11 (e.g., a single-output machine learning model may be trained to provide different output values for different types of cells (e.g., 0 for WBC, 1 for reticulocytes, and 2 for platelets), with the value closest to the output value generated by the model based on a particular input image being treated as the classification for the cells depicted in that input image). Similarly, other types of cell sorting may be used, such as those described in US Pat. No. 11,403,751, which is incorporated herein by reference in its entirety.Therefore, the discussion of the use of machine learning models for classification set forth above in the context of Figures 11 and 12 should be understood to be merely illustrative and not to be treated as limiting.

[0104] In embodiments that include classifying 1000 the imaged cells, after the classification is complete, a maturity score may be generated for the imaged cells, such as using the method shown in FIG. 13. As shown in FIG. 13, generating 1300 a maturity score for the imaged cells may include utilizing 1301 a number of pixels contained in the foreground portion of the image. For example, if a maturity score is generated 1300 to calculate the immature platelet fraction and the immature reticulocyte fraction, utilizing 1301 the foreground pixel count may include determining 1302 whether a threshold pixel count is greater than a threshold. If the number of pixels in the foreground of the image is above the pixel threshold, the depicted cell may be classified as immature, while if the number of pixels is below the threshold, it may be classified as mature. In embodiments that take this approach, the pixel threshold used in this determination 1302 may depend on how the cells for which the maturity score was generated were classified. For example, in an image in which each pixel corresponds to a square with sides 0.14 μm long, a threshold of 490 pixels may be used to separate immature from mature platelets, with images having platelets covering more than 490 pixels being treated as immature and images having platelets covering 490 or fewer pixels being treated as mature. Alternatively or additionally, in images acquired using the same device, a threshold of 700 pixels may be used to separate immature from mature reticulocytes, with images having reticulocytes covering more than 700 pixels being treated as immature and images having reticulocytes covering 700 or fewer pixels being treated as mature. Different thresholds may be used in images acquired using equipment with different pixel sizes or for other types of cells of interest, and the particular threshold to be used in a particular context may be identified using methods known in the art, such as using a clustering algorithm to determine a best-fit line separating labeled images of a particular type of immature and mature cell.

[0105] Other methods of utilizing 1301 the number of foreground pixels when generating 1300 the maturity of an imaged cell are also possible. For example, as illustrated in FIG. 13 , the number of foreground pixels can be utilized 1301 in calculating 1303 an average parameter value for that cell. This type of approach can exploit the fact that the maturity of a cell can be correlated with a particular measurable parameter. For example, because more immature reticulocytes or platelets tend to have more RNA than more mature reticulocytes or platelets, or in other words, because the RNA content decreases as these cells mature, the staining process can result in a measurable color difference that is correlated to (im)maturity (e.g., more immature cells can tend to have bluer pixels than less immature cells). Thus, the values of the color channels, which measurably differ depending on the immaturity, can be averaged over the foreground pixels, thereby providing the maturity of the cell in terms of the average of that parameter (e.g., the average “blueness” value). Other variations are possible and can be implemented by those skilled in the art without undue experimentation based on this disclosure. For example, rather than making a binary distinction between "mature" and "immature," or treating maturity as a value on a continuum, like a parameter mean, cells may be placed into one of a set of maturity buckets based on where the average parameter value (e.g., blueness) falls on a continuum of possible values. Similarly, in some cases, other approaches may be used, such as calculating maturity based on the number of foreground pixels in the nucleus relative to the number of foreground pixels in the cell at issue, based on the boundary of the nucleus relative to a region of the cell at issue, or based on a combination of two or more of the previously listed (or other) factors. Thus, discussion of utilizing foreground pixel count 1301 for binary mature / immature classification should be understood as merely illustrative and should not be treated as suggesting a limitation on the protection provided by this document or any other document claiming the benefit of this document.

[0106] However, once maturity data for cells depicted in the image under analysis is generated and available, it may be stored 1304, such as for combination with maturity data for other cells to provide overall information about the biological sample. To illustrate, consider FIG. 14, which illustrates how maturity information such as may be generated using the disclosed techniques is used to generate overall information about the biological sample. When performing a method such as that shown in FIG. 14, multiple additional images are acquired 1401, such as through acquiring images of additional cells contained in the biological sample being analyzed. Once those additional images are acquired, the maturity of cells depicted in one of those images may be determined 1402 (e.g., using the techniques described above as possibly being used to determine 902 the maturity of cells in the method of FIG. 9). The process then proceeds 1403 to the next image, so long as there are photographs of cells whose maturity has not yet been determined. Finally, once maturity has been determined 1402 for all of the depicted cells of interest (e.g., platelets and reticulocytes), an analysis output may be generated 1404 based on the maturity data for those cells. 14, generating 1404 an analytical output may be performed in a variety of ways. For example, if the disclosed technology is used to separate reticulocytes and / or platelets into "mature" and "immature" categories, generating 1404 an analytical output may include determining 1405 at least one of an immature reticulocyte fraction (i.e., the number of reticulocytes classified as "immature" divided by the total number of reticulocytes, abbreviated IRF) and an immature platelet fraction (i.e., the number of platelets classified as "immature" divided by the total number of platelets, abbreviated IPF). Alternatively, when the disclosed techniques are used to generate maturity values along a continuum (e.g., using factor averaging as previously discussed in the context of FIG. 13 ), generating 1404 the analysis output may include generating 1406 a graph showing the distribution of reticulocyte maturity values across a range of reticulocyte maturity values and / or generating a graph showing the distribution of platelet maturity values across a range of platelet maturity values.Other types of analytical output (e.g., a histogram showing the distribution of reticulocytes and / or platelets if the imaged cells are bucketed based on maturity) may also be generated 1404, and so the example illustrated in FIG. 14 should not be treated as imposing limitations on the types of output that may be generated by embodiments of the disclosed technology.

[0107] Variations are possible in aspects other than the type of output that may be generated based on the maturity data. For example, in some embodiments, determining 902 the maturity of a cell may include classifying 1000 the cell, followed by generating 1300 a maturity for the cell, while in other embodiments, determining 902 the maturity of a cell may be performed without separate classifying 1000 and generating 1300 steps. Illustrating this, FIG. 15 depicts a method in which a cell's maturity is generated as part of classifying a cell. Initially, in the method, a cell is presented 1501 to a machine learning model, such as by providing an image of the cell as input to a machine learning model including a convolutional neural network, as shown in FIGS. 11 and 12 . The machine learning model may then utilize 1502 the convolutional neural network to classify the cell. The machine learning model may generate this classification in a manner similar to that discussed above in the context of FIGS. 11 and 12 , but may also provide 1503 a maturity if the cell being classified is of a type for which maturity is of interest. For example, if maturity is determined for reticulocytes and platelets, when a cell is classified 1504 into the reticulocyte class and when a cell is classified 1505 into the platelet class, the machine learning model may also provide 1503 a maturity for the cell. This may be done by structuring the dense layer 1104 to include both a set of type nodes (e.g., a node corresponding to WBC, a node corresponding to reticulocyte, and a node corresponding to platelet) and a maturity node that is trained to provide maturity and that can be polled if the type node indicates that the cell was a reticulocyte or platelet. Alternatively, if maturity is a binary decision of mature or immature, the machine learning model may not only include a single platelet class and a single reticulocyte class, but may instead include an immature reticulocyte class, a mature reticulocyte class, an immature platelet class, and a mature platelet class, and the type of platelet / reticulocyte class into which the cell was classified may be treated as providing the maturity of the cell.

[0108] However, after a maturity value is provided 1503 by a machine learning model, the maturity value may be provided 1503 in the manner of FIG. 15 , and the maturity value from that model may be treated 1506 as the maturity value for the cell under analysis. For example, if a separate maturity node existed in the dense layer 1104 of the machine learning model after the architecture of FIG. 11 , the value on that output node may simply be treated 1506 as the maturity value for the cell whose submission 1501 to the machine learning model led to that value being generated. Alternatively, if there were output nodes corresponding to immature reticulocytes, mature reticulocytes, immature platelets, and mature platelets, the cell may be treated 1506 as immature if it was classified into the immature platelet or immature reticulocyte class, or as mature if it was classified into the mature reticulocyte or mature platelet class. Thus, the discussion of an embodiment in which a cell's maturity value is generated 1300 after the cell is classified 1000 should be understood to be merely illustrative and not limiting.

[0109] Other variations on potential implementations of the disclosed technology are possible and should be readily apparent to those skilled in the art in light of this disclosure. For example, while machine learning models such as those shown in FIGS. 11 and 12 may simply take images depicting cells as input, it is also possible that other information could be provided as input to such models. For example, in addition to or instead of cell images, models could be provided with derived information such as the number of foreground pixels, the ratio of the number of pixels within the nucleus to the number of pixels within the cell, and / or other parameters described herein as useful for determining cell maturity (either as part of cell classification or separately). As another example, a machine learning model (or other classification function, such as a morphology-based function as described in the context of FIG. 10) may be designed to classify cells in a sample that has previously been lysed to remove mature red blood cells (RBCs), but the disclosed technology could also be implemented to classify samples in which RBCs may be present (e.g., by adding an additional output node for RBCs to the dense layer 1104 of the machine learning model as shown in FIG. 11). Variations are also possible with regard to the physical devices that may be used in different implementations. For example, in some cases, analysis of images associated with determining the maturity of depicted cells may be performed using a processor local to the system that may be used to acquire the images themselves, such as the systems shown in Figures 1 and 2. In other cases, however, analysis and collection of data may be separated, for example, in systems in which acquired images are transmitted over a network connection to a remote processor, which analyzes them and then returns the results (e.g., the analysis output generated 1404 as described in the context of Figure 14) to their source (or another endpoint) for review.

[0110] Other applications are possible. For example, while the above description focused on determining maturity, aspects of the disclosed technology can also be used for other types of analysis, such as detecting cells infected with malaria or other parasites. This is because infected cells, such as immature platelets and reticulocytes, have relatively more RNA and may therefore be distinguishable from other cells using techniques similar to those described above to identify the maturity of reticulocytes and / or platelets (e.g., binarization using the number of dark pixels in a cell image). As further illustrations of potential implementations and applications of the disclosed technology, the following examples are provided of non-exclusive ways in which the teachings herein can be combined or applied. It should be understood that the following examples are not intended to limit the scope of any claims that may be filed at any time in this application or in any subsequent filing of this application. No disclaimers are intended. The following examples are provided solely for illustrative purposes. It is contemplated that the teachings herein may be arranged and applied in numerous other ways. It is also contemplated that some variations may omit certain features mentioned in the examples below. Accordingly, the aspects and features mentioned below should not be considered essential unless later expressly otherwise indicated as such by the inventors or their successors 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 shall not be presumed to have been added for any reasons related to patentability.

[0111] [Example 1] 1. A computer-implemented image analysis method for detecting maturity of blood cells, comprising: depositing a staining composition in a chamber; depositing a biological sample in the chamber; mixing the biological sample and the staining composition in the chamber; acquiring images of stained blood cells from the biological sample with a camera; and determining the maturity of the stained blood cells based on the images of the stained blood cells acquired with the camera.

[0112] [Example 2] 2. The image analysis method of Example 1, wherein the method further comprises treating a blood sample with a lysing agent and flowing the blood sample through a flow cell past a camera, and wherein acquiring the image of the stained blood cells with the camera is performed while the biological sample is flowing through the flow cell past the camera.

[0113] [Example 3] 3. The image analysis method of example 2, wherein determining the maturity of the stained blood cells comprises classifying the stained blood cells, and wherein classifying the stained blood cells comprises classifying the stained blood cells as at least one of reticulocytes or platelets.

[0114] [Example 4] 4. The image analysis method of example 3, further comprising: acquiring a plurality of additional images, each image from the plurality of additional images depicting additional stained blood cells corresponding to the image; determining, for each image from the plurality of additional images, a maturity of the additional stained blood cells corresponding to the image; and generating an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images.

[0115] [Example 5] 5. The image analysis method of example 4, wherein generating the analysis output includes determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

[0116] [Example 6] 6. The image analysis method of Example 4 or 5, wherein generating the analysis output includes generating at least one of a graph showing a distribution of reticulocytes in the biological sample across a reticulocyte maturity range and a graph showing a distribution of platelets in the biological sample across a platelet maturity range.

[0117] [Example 7] 7. The image analysis method according to any one of Examples 3 to 6, wherein classifying the stained blood cells comprises utilizing a convolutional neural network.

[0118] [Example 8] The image analysis method of Example 7, wherein the convolutional neural network is included by a machine learning model configured to, when presented with input stained blood cells, classify the input stained blood cells as reticulocytes by classifying them into a reticulocyte class, provide a maturity level for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class, and classify the input stained blood cells as platelets by classifying them into a platelet class, and provide the maturity level for the input stained blood cells when the input stained blood cells are classified into the platelet class, and determining the maturity level of the stained blood cells comprises presenting the stained blood cells as the input stained blood cells to the machine learning model and treating the maturity level provided by the machine learning model as the maturity level of the stained blood cells.

[0119] [Example 9] The image analysis method of Example 8, wherein the machine learning model is configured to classify the input stained blood cells into the platelet class and, when the input stained blood cells are classified into the platelet class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature platelet class and a mature platelet class; and the machine learning model is configured to classify the input stained blood cells into the reticulocyte class and, when the input stained blood cells are classified into the reticulocyte class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature reticulocyte class and a mature reticulocyte class.

[0120] [Example 10] The image analysis method according to any one of Examples 3 to 7, wherein determining the maturity of the stained blood cells comprises generating the maturity of the stained blood cells after the stained blood cells are classified.

[0121] [Example 11] 8. The image analysis method of any one of Examples 3 to 7, wherein classifying the stained blood cells comprises identifying a foreground in the image based on an intensity of each pixel in the image.

[0122] [Example 12] Example 12. The image analysis method of Example 11, comprising calculating an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image, and classifying the stained blood cells based on the average red intensity and the average blue intensity.

[0123] [Example 13] 13. The image analysis method of any one of Examples 1 to 12, wherein determining the maturity of the stained blood cells comprises utilizing pixel foreground counts.

[0124] [Example 14] 13. The image analysis method of any of Examples 1-7 or 10-12, wherein determining the maturity of the stained blood cells comprises determining whether a pixel foreground count exceeds a threshold amount.

[0125] [Example 15] 15. The image analysis method of any one of Examples 1 to 14, wherein the method includes preheating the staining composition in the chamber before depositing the biological sample in the chamber, and heating the biological sample and the staining composition in the chamber.

[0126] [Example 16] 16. The image analysis method of example 15, wherein both preheating the staining composition in the chamber and heating the biological sample and the staining composition in the chamber comprise increasing the chamber temperature using a heating coil.

[0127] [Example 17] 17. The image analysis method of example 16, wherein the heating coil is attached to a mounting bracket that is connected to the chamber and one or more other mixing chambers.

[0128] [Example 18] 1. A computer-implemented image analysis method for detecting maturity of blood cells, comprising: flowing a biological sample through a flow cell and past a camera; capturing images of stained blood cells with the camera while the biological sample flows through the flow cell and past the camera; and determining maturity of the stained blood cells based on the images of the stained blood cells captured by the camera.

[0129] [Example 19] 20. The image analysis method of Example 18, wherein the method further comprises treating the biological sample with a lysing agent.

[0130] [Example 20] 20. The image analysis method of Example 19, wherein determining the maturity of the stained blood cells comprises classifying the stained blood cells, and wherein classifying the stained blood cells comprises classifying the stained blood cells as at least one of reticulocytes or platelets.

[0131] [Example 21] 21. The image analysis method of Example 20, wherein the method further includes acquiring a plurality of additional images, each image from the plurality of additional images depicting additional stained blood cells corresponding to the image; determining, for each image from the plurality of additional images, a maturity of the additional stained blood cells corresponding to the image; and generating an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images.

[0132] [Example 22] 22. The image analysis method of example 21, wherein generating the analysis output includes determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

[0133] [Example 23] 23. The image analysis method of Example 21 or 22, wherein generating the analysis output includes generating at least one of a graph showing the distribution of reticulocytes in the biological sample across a reticulocyte maturity range and a graph showing the distribution of platelets in the biological sample across a platelet maturity range.

[0134] [Example 24] 24. The image analysis method according to any one of Examples 20 to 23, wherein classifying the stained blood cells comprises utilizing a convolutional neural network.

[0135] [Example 25] Example 25. The image analysis method of Example 24, wherein the convolutional neural network is included by a machine learning model configured to: when presented with input stained blood cells, classify the input stained blood cells as reticulocytes by classifying them into a reticulocyte class, provide a maturity level for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class, and classify the input stained blood cells as platelets by classifying them into a platelet class, and provide the maturity level for the input stained blood cells when the input stained blood cells are classified into the platelet class; and determining the maturity level of the stained blood cells comprises presenting the stained blood cells as the input stained blood cells to the machine learning model and treating the maturity level provided by the machine learning model as the maturity level of the stained blood cells.

[0136] [Example 26] 26. The image analysis method of Example 25, wherein the machine learning model is configured to classify the input stained blood cells into the platelet class and, when the input stained blood cells are classified into the platelet class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature platelet class and a mature platelet class; and wherein the machine learning model is configured to classify the input stained blood cells into the reticulocyte class and, when the input stained blood cells are classified into the reticulocyte class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature reticulocyte class and a mature reticulocyte class.

[0137] [Example 27] 25. The image analysis method of any one of Examples 20 to 24, wherein determining the maturity of the stained blood cells comprises generating the maturity of the stained blood cells after the stained blood cells are classified.

[0138] [Example 28] 24. The image analysis method of any one of Examples 20 to 23, wherein classifying the stained blood cells comprises identifying a foreground in the image based on an intensity of each pixel in the image.

[0139] [Example 29] Example 29. The image analysis method of Example 28, further comprising calculating an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image, and classifying the stained blood cells based on the average red intensity and the average blue intensity.

[0140] [Example 30] 30. The image analysis method of any one of Examples 18 to 29, wherein determining the maturity of the stained blood cells comprises utilizing pixel foreground counts.

[0141] [Example 31] 30. The image analysis method of any of Examples 18-24 or 27-29, wherein determining the maturity of the stained blood cells comprises determining whether a pixel foreground count exceeds a threshold amount.

[0142] [Example 32] 32. The image analysis method of any one of Examples 18 to 31, wherein the method includes depositing the biological sample in the chamber and mixing the biological sample and the staining composition in the chamber.

[0143] [Example 33] 33. The image analysis method of Example 32, further comprising preheating the staining composition in the chamber prior to depositing the biological sample in the chamber, and heating the biological sample and the staining composition in the chamber.

[0144] [Example 34] 34. The image analysis method of Example 33, wherein both preheating the staining composition in the chamber and heating the biological sample and the staining composition in the chamber comprise increasing the chamber temperature using a heating coil.

[0145] [Example 35] 35. The image analysis method of example 34, wherein the heating coil is attached to a mounting bracket that is connected to the chamber and one or more other mixing chambers.

[0146] [Example 36] 1. An image analysis system for detecting the maturity of blood cells, comprising: one or more chambers configured to receive a biological sample and a staining composition; a camera configured to acquire images of stained blood cells; and one or more processors configured to determine the maturity of the stained blood cells based on the images of the stained blood cells acquired by the camera.

[0147] [Example 37] 37. The image analysis system of Example 36, wherein determining the maturity of the stained blood cells includes classifying the stained blood cells as at least one of reticulocytes or platelets.

[0148] [Example 38] The image analysis system of Example 37, wherein the one or more processors are further configured to: acquire a plurality of additional images, each image from the plurality of additional images depicting additional stained blood cells corresponding to the image; determine, for each image from the plurality of additional images, a maturity of the additional stained blood cells corresponding to the image; and generate an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images.

[0149] [Example 39] 39. The image analysis system of Example 38, wherein generating the analysis output includes determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

[0150] [Example 40] 40. The image analysis system of Example 38 or 39, wherein generating the analysis output includes generating at least one of a graph showing the distribution of reticulocytes in the biological sample across a reticulocyte maturity range and a graph showing the distribution of platelets in the biological sample across a platelet maturity range.

[0151] [Example 41] 41. The system of any one of Examples 37 to 40, wherein the one or more processors are configured to utilize a convolutional neural network to classify the stained blood cells.

[0152] [Example 42] Example 42. The image analysis system of Example 41, wherein the convolutional neural network is included by a machine learning model configured to: when presented with input stained blood cells, classify the input stained blood cells as reticulocytes by classifying them into a reticulocyte class, provide a maturity level for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class, and classify the input stained blood cells as platelets by classifying them into a platelet class, and provide the maturity level for the input stained blood cells when the input stained blood cells are classified into the platelet class; and the one or more processors are configured to determine the maturity level of the stained blood cells by performing operations including presenting the stained blood cells as the input stained blood cells to the machine learning model and treating the maturity level provided by the machine learning model as the maturity level of the stained blood cells.

[0153] [Example 43] The system of Example 42, wherein the machine learning model is configured to classify the input stained blood cells into the platelet class and, when the input stained blood cells are classified into the platelet class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature platelet class and a mature platelet class; and the machine learning model is configured to classify the input stained blood cells into the reticulocyte class and, when the input stained blood cells are classified into the reticulocyte class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature reticulocyte class and a mature reticulocyte class.

[0154] [Example 44] The system described in any one of Examples 37 to 41, wherein the one or more processors are configured to determine the maturity of the stained blood cells by performing an operation including generating the maturity of the stained blood cells after the stained blood cells are classified.

[0155] [Example 45] 45. The system of any of Examples 37-41 or 44, wherein the one or more processors are configured to classify the stained blood cells based on identifying foreground in the image based on the intensity of each pixel in the image.

[0156] [Example 46] The system of Example 45, wherein the one or more processors are further configured to calculate an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image, and wherein the one or more processors are configured to classify the stained blood cells based on the average red intensity and the average blue intensity.

[0157] [Example 47] The system of any one of Examples 36-41 or 44-46, wherein the one or more processors are configured to determine the maturity of the stained blood cells based on a pixel foreground count.

[0158] [Example 48] The system of any one of Examples 36-41 or 44-47, wherein the one or more processors are configured to determine that the stained blood cells are immature based on a pixel foreground count exceeding a threshold amount.

[0159] [Example 49] The system of any one of Examples 36 to 48, wherein the one or more chambers are further configured to receive a dissolution composition.

[0160] [Example 50] The system of any one of Examples 36 to 48, wherein the staining composition further comprises a lysis compound.

[0161] [Example 51] The system described in any one of Examples 36 to 50, further comprising a heater configured to heat the biological sample and the staining composition.

[0162] [Example 52] The system of Example 51, wherein the heater comprises an induction coil.

[0163] [Example 53] The system of Example 51 or 52, wherein the one or more chambers include two or more chambers, and the heater is connected to all of the two or more chambers.

[0164] [Example 54] The system of Example 53, wherein the heater comprises a mounting bracket connected to all of the two or more chambers, and a heating element attached to the mounting bracket.

[0165] [Example 55] 1. An image analysis system for detecting the maturity of cells in a biological sample, comprising: a flow cell configured to flow stained cells; a camera configured to acquire images of the stained blood cells as the stained blood cells flow past the camera within an imaging area of the flow cell; and one or more processors configured to determine the maturity of the stained blood cells based on the images of the stained blood cells acquired by the camera.

[0166] [Example 56] 56. The image analysis system of Example 55, wherein determining the maturity of the stained blood cells comprises classifying the stained blood cells, and wherein classifying the stained blood cells comprises classifying the stained blood cells as at least one of reticulocytes or platelets.

[0167] [Example 57] The image analysis system of Example 56, wherein the one or more processors are configured to acquire a plurality of additional images, each image from the plurality of additional images depicting additional stained blood cells corresponding to that image, determine for each image from the plurality of additional images a maturity of the additional stained blood cells corresponding to that image, and generate an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images.

[0168] [Example 58] 58. The image analysis system of Example 57, wherein generating the analysis output includes determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

[0169] [Example 59] The image analysis system of Example 57 or 58, wherein generating the analysis output includes generating at least one of a graph showing the distribution of reticulocytes in the biological sample across a reticulocyte maturity range and a graph showing the distribution of platelets in the biological sample across a platelet maturity range.

[0170] [Example 60] 60. The image analysis system of any one of Examples 56 to 59, wherein classifying the stained blood cells comprises utilizing a convolutional neural network.

[0171] [Example 61] The image analysis system of Example 60, wherein the convolutional neural network is included by a machine learning model configured to, when presented with input stained blood cells, classify the input stained blood cells as reticulocytes by classifying them into a reticulocyte class, provide the maturity for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class, and classify the input stained blood cells as platelets by classifying them into a platelet class, and provide the maturity for the input stained blood cells when the input stained blood cells are classified into the platelet class, and determining the maturity of the stained blood cells includes presenting the stained blood cells as the input stained blood cells to the machine learning model and treating the maturity provided by the machine learning model as the maturity of the stained blood cells.

[0172] [Example 62] 62. The image analysis system of Example 61, wherein the machine learning model is configured to classify the input stained blood cells into the platelet class and, when the input stained blood cells are classified into the platelet class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature platelet class and a mature platelet class; and wherein the machine learning model is configured to classify the input stained blood cells into the reticulocyte class and, when the input stained blood cells are classified into the reticulocyte class, provide the maturity level for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of an immature reticulocyte class and a mature reticulocyte class.

[0173] [Example 63] 61. The image analysis system of any of Examples 56 to 60, wherein determining the maturity of the stained blood cells includes generating the maturity of the stained blood cells after the stained blood cells are classified.

[0174] [Example 64] 60. The image analysis system of any one of Examples 56 to 59, wherein classifying the stained blood cells includes identifying foreground within the image based on the intensity of each pixel within the image.

[0175] [Example 65] Example 65. The image analysis system of Example 64, further comprising calculating an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image, and classifying the stained blood cells based on the average red intensity and the average blue intensity.

[0176] [Example 66] 61. The image analysis system of any one of Examples 55 to 60, wherein determining the maturity of the stained blood cells comprises utilizing pixel foreground counts.

[0177] [Example 67] An image analysis system described in any of Examples 55-60 or 63-65, wherein determining the maturity of the stained blood cells includes determining whether a pixel foreground count exceeds a threshold amount.

[0178] [Example 68] An image analysis system described in any one of Examples 55 to 67, wherein the system further comprises one or more chambers adapted to receive the biological sample and the lysis composition.

[0179] [Example 69] An image analysis system described in any one of Examples 55 to 68, wherein the system comprises one or more chambers configured to receive the biological sample and staining composition.

[0180] [Example 70] 70. The image analysis system of Example 69, wherein the system further comprises a heater configured to heat the biological sample and the staining composition.

[0181] [Example 71] 72. The image analysis system of claim 71, wherein the heater comprises an induction coil.

[0182] [Example 72] An image analysis system as described in Example 70 or 71, wherein the one or more chambers include two or more chambers, and the heater is connected to all of the two or more chambers.

[0183] [Example 73] An image analysis system as described in Example 72, wherein the heater comprises a mounting bracket connected to all of the two or more chambers, and a heating element attached to the mounting bracket.

[0184] [Example 74] A machine comprising a camera and means for determining the maturity of cells in an image acquired by said camera.

[0185] Each of the calculations or operations described herein may be implemented 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 wide variety of digital and / or analog data processing hardware and / or software arranged to perform the method steps described herein. Modules optionally comprise data processing hardware adapted to perform one or more of these steps by having appropriate machine programming code associated therewith, and modules for two or more steps (or portions of two or more steps) may be integrated onto a single processor board or split across different processor boards in any of a wide variety of integrated and / or distributed processing architectures. These methods and systems often employ tangible media embodying machine-readable code with instructions for performing the method steps described above. Suitable tangible media may include memory (volatile and / or non-volatile memory), storage media (magnetic recording such as floppy disks, hard disks, tapes, or the like, optical memory such as CDs, CD-R / Ws, CD-ROMs, DVDs, or the like, or any other digital or analog storage medium), or the like.

[0186] All patents, patent publications, patent applications, journal articles, books, technical references, and the like discussed in this disclosure are hereby incorporated by reference in their entirety for all purposes.

[0187] Different arrangements of the components depicted in the figures or described above are possible, as well as components and steps not shown or described. Similarly, some features and subcombinations are useful and may be employed without reference to other features and subcombinations. Embodiments of the invention are described for illustration and not by way of limitation; alternative embodiments shall become apparent to readers of this patent. In certain cases, method steps or operations may be performed or executed in a different order, or operations may be added, deleted, or modified. It should be understood that in certain aspects of the invention, a single component may be replaced with multiple components, and multiple components may be replaced with a single component, to provide an element or structure or to perform a given function(s). Except to the extent that such substitution would not function to practice a particular embodiment of the invention, such substitution is deemed to be within the scope of the invention. Therefore, the claims should not be treated as limited to the examples, drawings, embodiments, and illustrations provided above, but rather should be understood to have the scope provided when those terms are given their broadest reasonable interpretation as provided by a general dictionary, except that when a term or expression is set forth as having a particular meaning under an express definition heading, it should be understood to have that meaning when used in the claims.

[0188] explicit definition It should be understood that in the above examples and claims, a statement that something is "based on" something else should be understood to mean that the something is at least partially determined by what it is shown to be based on. To indicate that something must be completely determined based on something else, it is described as being "based solely on" the something on which it must be completely determined.

[0189] It should be understood that in the above examples and claims, the phrase "means for determining the maturity of cells in images acquired by a camera" is a mean-plus-function limitation as provided in 35 U.S.C. 112(f), where the function is "determining the maturity of cells in images acquired by a camera," and the corresponding structure is a computer configured to determine the maturity of cells using algorithms as described in the context of determining maturity 902 as illustrated in FIG. 9, classifying cells 1000 as illustrated in FIG. 10 (which in some embodiments is described as being included in determining maturity 902), generating maturity data 1300 as illustrated in FIG. 13, determining the maturity of cells in additional images 1402 as illustrated in FIG. 14, and utilizing a convolutional neural network 1502 and treating the maturity provided by a machine learning model as the maturity of the cells 1506 as illustrated in FIG. 15.

[0190] It should be understood that in the above examples and in the claims, the term "set" is to be understood as one or more things grouped together. [Explanation of symbols]

[0191] 18 processors 21 Narrow area 21a Proximal flow channel section 21b Distal flow channel portion 22 flow cell 24 High-optical resolution imaging device 25 source 28 Distal end 29 Sample feed tube 32 Sample Stream 42 Light source 46 Objective Lens 48 Charge Coupled Device 54 Motor Drive 200 Vision Inspection System 202 slides 204 Slide Holder 206 Image Acquisition Device 208 Optical system 210 Image Sensor 212 Image Processing Device 214 processors 216 memory 218 Steering Motor System 300 Lighting Modules 302 Flow Cell 304 High Optical Resolution Imaging Device 310 Housing 312a, 312b, 312c luminous bodies 314a, 314b, 314c focusing lenses 316a, 316b, 316c Dichroic elements 318 Collimating Lens 320a, 320b, 320c reflective side 322a, 322b, 322c Filtering side 400 Dyeing Module 410 Housing 412 Ferromagnetic Sheet 414 Heating Coil 420 Side wall 422 Chamber 424 Upper Wall Port 426 430 Thermally conductive compounds 440 wire 450 power supply unit 500 Multi-Chamber Staining Module 510 Housing 512 Bracket / Sleeve 514 Heating Coil 522a, 522b, 522c, 522d chambers 524 Upper Wall Ports 526a, 526b, 526c, 526d 530 inner bore 532 Upper edge 534 Lower edge 536 Concave Area 540 Wire / Heating Coil 700 Flow Cell Holder 1101 Input image 1102a-1102n Stage 1103 Final output image 1103 1104 Dense Layer / Neural Network 1201 Input 1202 layers 1203a-1203n converted image 1205a-1205n Pool images 1206 output images

Claims

1. 1. A computer-implemented image analysis method for detecting maturity of blood cells, comprising: depositing a staining composition in the chamber; depositing a biological sample in the chamber; mixing the biological sample and the staining composition in the chamber; acquiring an image of stained blood cells from the biological sample with a camera; determining a maturity of the stained blood cells based on the image of the stained blood cells acquired by the camera; An image analysis method comprising:

2. The method comprises: treating the biological sample with a lysis agent; flowing the biological sample through a flow cell and past the camera; further comprising 2. The image analysis method of claim 1, wherein acquiring the image of the stained blood cells with the camera is performed while the biological sample flows through the flow cell and past the camera.

3. determining the maturity of the stained blood cells includes classifying the stained blood cells; The image analysis method of claim 2 , wherein classifying the stained blood cells comprises classifying the stained blood cells as at least one of reticulocytes or platelets.

4. The method comprises: acquiring a plurality of additional images, wherein each image from said plurality of additional images depicts additional stained blood cells corresponding to that image; determining, for each image from the plurality of additional images, a maturity level of the additional stained blood cells corresponding to that image; generating an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images; The image analysis method of claim 3 further comprising:

5. 5. The image analysis method of claim 4, wherein generating the analysis output comprises determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

6. generating the analysis output includes:

6. The image analysis method of claim 4, further comprising generating at least one of a graph showing the distribution of reticulocytes in the biological sample across a range of reticulocyte maturity and a graph showing the distribution of platelets in the biological sample across a range of platelet maturity.

7. 7. The image analysis method of claim 3, wherein classifying the stained blood cells comprises utilizing a convolutional neural network.

8. the convolutional neural network is comprised by a machine learning model; The machine learning model, when presented with input stained blood cells, classifying the input stained blood cells as reticulocytes by classifying them into a reticulocyte class; providing a maturity index for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class; classifying the input stained blood cells as platelets by classifying them into a platelet class; and providing the maturity of the input stained blood cells when the input stained blood cells are classified into the platelet class. configured to: Determining the maturity of the stained blood cells comprises: submitting the stained blood cells to the machine learning model as the input stained blood cells; and The image analysis method of claim 7 , further comprising treating the maturity level provided by the machine learning model as the maturity level of the stained blood cells.

9. The machine learning model is configured to classify the input stained blood cells into the platelet class, and when the input stained blood cells are classified into the platelet class, Immature platelet class, and Mature Platelet Class and providing the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of: The machine learning model is configured to classify the input stained blood cells into the reticulocyte class, and when the input stained blood cells are classified into the reticulocyte class, the machine learning model Immature reticulocyte class, and Mature reticulocyte class 9. The image analysis method of claim 8, configured to provide the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of:

10. 8. The image analysis method according to claim 3, wherein determining the maturity of the stained blood cells comprises generating the maturity of the stained blood cells after the stained blood cells have been classified.

11. 8. The image analysis method of claim 3, wherein classifying the stained blood cells comprises identifying a foreground in the image based on the intensity of each pixel in the image.

12. Calculating an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image; and classifying the stained blood cells based on the average red intensity and the average blue intensity.

13. The image analysis method of any one of claims 1 to 12, wherein determining the maturity of the stained blood cells comprises utilizing pixel foreground counts.

14. 13. The image analysis method of any of claims 1-7 or 10-12, wherein determining the maturity of the stained blood cells comprises determining whether a pixel foreground count exceeds a threshold amount.

15. The method comprises: preheating the staining composition in the chamber prior to depositing the biological sample in the chamber; heating the biological sample and the staining composition in the chamber; The image analysis method according to any one of claims 1 to 14, comprising:

16. 16. The image analysis method of claim 15, wherein both preheating the staining composition in the chamber and heating the biological sample and the staining composition in the chamber comprise increasing the chamber temperature using a heating coil.

17. 17. The image analysis method of claim 16, wherein the heating coil is attached to a mounting bracket that is connected to the chamber and one or more other mixing chambers.

18. 1. A computer-implemented image analysis method for detecting maturity of blood cells, comprising: flowing the biological sample through a flow cell and past a camera; acquiring images of stained blood cells with a camera while the biological sample flows through the flow cell and past the camera; determining a maturity of the stained blood cells based on the image of the stained blood cells acquired by the camera; An image analysis method comprising:

19. 20. The image analysis method of claim 18, wherein the method further comprises treating the biological sample with a lysing agent.

20. determining the maturity of the stained blood cells includes classifying the stained blood cells; 20. The image analysis method of claim 19, wherein classifying the stained blood cells comprises classifying the stained blood cells as at least one of reticulocytes or platelets.

21. The method comprises: acquiring a plurality of additional images, wherein each image from said plurality of additional images depicts additional stained blood cells corresponding to that image; determining, for each image from the plurality of additional images, a maturity level of the additional stained blood cells corresponding to that image; generating an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images; 21. The image analysis method of claim 20, further comprising:

22. 22. The image analysis method of claim 21, wherein generating the analysis output comprises determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

23. generating the analysis output includes:

23. The image analysis method of claim 21 or 22, comprising generating at least one of a graph showing the distribution of reticulocytes in the biological sample across a reticulocyte maturity range and a graph showing the distribution of platelets in the biological sample across a platelet maturity range.

24. 24. The image analysis method of claim 20, wherein classifying the stained blood cells comprises utilizing a convolutional neural network.

25. the convolutional neural network is comprised by a machine learning model; The machine learning model, when presented with input stained blood cells, classifying the input stained blood cells as reticulocytes by classifying them into a reticulocyte class; providing a maturity index for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class; classifying the input stained blood cells as platelets by classifying them into a platelet class; and providing the maturity of the input stained blood cells when the input stained blood cells are classified into the platelet class. configured to: Determining the maturity of the stained blood cells comprises: submitting the stained blood cells to the machine learning model as the input stained blood cells; and 25. The image analysis method of claim 24, comprising treating the maturity provided by the machine learning model as the maturity of the stained blood cells.

26. The machine learning model is configured to classify the input stained blood cells into the platelet class, and when the input stained blood cells are classified into the platelet class, the machine learning model Immature platelet class, and Mature Platelet Class and providing the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of: The machine learning model is configured to classify the input stained blood cells into the reticulocyte class, and when the input stained blood cells are classified into the reticulocyte class, the machine learning model Immature reticulocyte class, and Mature reticulocyte class 26. The image analysis method of claim 25, configured to provide the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of:

27. 25. The image analysis method of claim 20, wherein determining the maturity of the stained blood cells comprises generating the maturity of the stained blood cells after the stained blood cells have been classified.

28. 24. The image analysis method of claim 20, wherein classifying the stained blood cells comprises identifying foreground in the image based on the intensity of each pixel in the image.

29. Calculating an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image; classifying the stained blood cells based on the average red intensity and the average blue intensity; 29. The image analysis method of claim 28, further comprising:

30. 30. The image analysis method of any one of claims 18 to 29, wherein determining the maturity of the stained blood cells comprises utilizing pixel foreground counts.

31. 30. The image analysis method of any of claims 18-24 or 27-29, wherein determining the maturity of the stained blood cells comprises determining whether a pixel foreground count exceeds a threshold amount.

32. The method comprises: depositing a staining composition in the chamber; depositing the biological sample in the chamber; mixing the biological sample and the staining composition in the chamber; 32. The image analysis method according to any one of claims 18 to 31, comprising:

33. The method comprises: preheating the staining composition in the chamber prior to depositing the biological sample in the chamber; heating the biological sample and the staining composition in the chamber; 33. The image analysis method of claim 32, further comprising:

34. 34. The image analysis method of claim 33, wherein both preheating the staining composition in the chamber and heating the biological sample and the staining composition in the chamber comprise increasing the chamber temperature using a heating coil.

35. 35. The image analysis method of claim 34, wherein the heating coil is attached to a mounting bracket that is connected to the chamber and one or more other mixing chambers.

36. 1. An image analysis system for detecting the maturity of blood cells, comprising: one or more chambers configured to receive a biological sample and a staining composition; a camera configured to acquire images of the stained blood cells; one or more processors configured to determine a maturity of the stained blood cells based on the image of the stained blood cells acquired by the camera; An image analysis system comprising:

37. 37. The image analysis system of claim 36, wherein determining the maturity of the stained blood cells comprises classifying the stained blood cells as at least one of reticulocytes or platelets.

38. the one or more processors: acquiring a plurality of additional images, wherein each image from said plurality of additional images depicts additional stained blood cells corresponding to that image; determining, for each image from the plurality of additional images, a maturity level of the additional stained blood cells corresponding to that image; generating an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images; 38. The image analysis system of claim 37, further configured to:

39. 39. The image analysis system of claim 38, wherein generating the analysis output comprises determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

40. generating the analysis output includes:

40. The image analysis system of claim 38 or 39, comprising generating at least one of a graph showing a distribution of reticulocytes in the biological sample across a reticulocyte maturity range and a graph showing a distribution of platelets in the biological sample across a platelet maturity range.

41. 41. The system of any one of claims 37 to 40, wherein the one or more processors are configured to utilize a convolutional neural network to classify the stained blood cells.

42. the convolutional neural network is comprised by a machine learning model; The machine learning model, when presented with input stained blood cells, classifying the input stained blood cells as reticulocytes by classifying them into a reticulocyte class; providing a maturity index for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class; classifying the input stained blood cells as platelets by classifying them into a platelet class; and providing the maturity of the input stained blood cells when the input stained blood cells are classified into the platelet class. configured to: the one or more processors: submitting the stained blood cells to the machine learning model as the input stained blood cells; and Treating the maturity level provided by the machine learning model as the maturity level of the stained blood cells.

42. The system of claim 41, configured to determine the maturity of the stained blood cells by performing operations including:

43. The machine learning model is configured to classify the input stained blood cells into the platelet class, and when the input stained blood cells are classified into the platelet class, the machine learning model Immature platelet class, and Mature Platelet Class and providing the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of: The machine learning model is configured to classify the input stained blood cells into the reticulocyte class, and when the input stained blood cells are classified into the reticulocyte class, the machine learning model Immature reticulocyte class, and Mature reticulocyte class 43. The system of claim 42, configured to provide the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of:

44. 42. The system of any one of claims 37-41, wherein the one or more processors are configured to determine the maturity of the stained blood cells by performing operations including generating the maturity of the stained blood cells after the stained blood cells are classified.

45. 45. The system of any of claims 37-41 or 44, wherein the one or more processors are configured to classify the stained blood cells based on identifying foreground in the image based on an intensity of each pixel in the image.

46. the one or more processors are further configured to calculate an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image; 46. The system of claim 45, wherein the one or more processors are configured to classify the stained blood cells based on the average red intensity and the average blue intensity.

47. 47. The system of any one of claims 36-41 or 44-46, wherein the one or more processors are configured to determine the maturity of the stained blood cells based on a pixel foreground count.

48. 48. The system of any one of claims 36-41 or 44-47, wherein the one or more processors are configured to determine that the stained blood cells are immature based on a pixel foreground count exceeding a threshold amount.

49. The system of any one of claims 36 to 48, wherein the one or more chambers are further configured to receive a lysis composition.

50. The system of any one of claims 36 to 48, wherein the staining composition further comprises a lysis compound.

51. The system of any one of claims 36 to 50, further comprising a heater configured to heat the biological sample and the staining composition.

52. 52. The system of claim 51, wherein the heater comprises an induction coil.

53. 53. The system of claim 51 or 52, wherein the one or more chambers include two or more chambers, and the heater is coupled to all of the two or more chambers.

54. 54. The system of claim 53, wherein the heater comprises a mounting bracket connected to all of the two or more chambers, and a heating element attached to the mounting bracket.

55. 1. An image analysis system for detecting the maturity of cells in a biological sample, comprising: a flow cell configured to flow the stained cells; a camera configured to capture images of stained blood cells as the stained blood cells flow past the camera within an imaging area of the flow cell; and one or more processors configured to determine a maturity of the stained blood cells based on the image of the stained blood cells acquired by the camera; An image analysis system comprising:

56. determining the maturity of the stained blood cells includes classifying the stained blood cells; 56. The image analysis system of claim 55, wherein classifying the stained blood cells includes classifying the stained blood cells as at least one of reticulocytes or platelets.

57. the one or more processors: acquiring a plurality of additional images, wherein each image from said plurality of additional images depicts additional stained blood cells corresponding to that image; determining, for each image from the plurality of additional images, a maturity level of the additional stained blood cells corresponding to that image; generating an analysis output based on a set of maturity data including the maturity of the stained blood cells and the maturity of the stained blood cells depicted in the plurality of additional images; 57. The image analysis system of claim 56, configured to:

58. 58. The image analysis system of claim 57, wherein generating the analysis output comprises determining at least one of an immature reticulocyte fraction and an immature platelet fraction for the biological sample.

59. 59. The image analysis system of claim 57 or 58, wherein generating the analysis output comprises generating at least one of a graph showing a distribution of reticulocytes in the biological sample across a reticulocyte maturity range and a graph showing a distribution of platelets in the biological sample across a platelet maturity range.

60. 60. The image analysis system of any one of claims 56 to 59, wherein classifying the stained blood cells comprises utilizing a convolutional neural network.

61. the convolutional neural network is comprised by a machine learning model; The machine learning model, when presented with input stained blood cells, classifying the input stained blood cells as reticulocytes by classifying them into a reticulocyte class; providing the maturity index for the input stained blood cells when the input stained blood cells are classified into the reticulocyte class; classifying the input stained blood cells as platelets by classifying them into a platelet class; and providing the maturity of the input stained blood cells when the input stained blood cells are classified into the platelet class. configured to: Determining the maturity of the stained blood cells comprises: submitting the stained blood cells to the machine learning model as the input stained blood cells; and 61. The image analysis system of claim 60, further comprising treating the maturity provided by the machine learning model as the maturity of the stained blood cells.

62. The machine learning model is configured to classify the input stained blood cells into the platelet class, and when the input stained blood cells are classified into the platelet class, the machine learning model Immature platelet class, and Mature Platelet Class and providing the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of: The machine learning model is configured to classify the input stained blood cells into the reticulocyte class, and when the input stained blood cells are classified into the reticulocyte class, the machine learning model Immature reticulocyte class, and Mature reticulocyte class 62. The image analysis system of claim 61, configured to provide the maturity index for the input stained blood cells by classifying the input stained blood cells into a class selected from the group consisting of:

63. 61. The image analysis system of any of claims 56 to 60, wherein determining the maturity of the stained blood cells comprises generating the maturity of the stained blood cells after the stained blood cells have been classified.

64. 60. The image analysis system of any one of claims 56 to 59, wherein classifying the stained blood cells comprises identifying foreground within the image based on the intensity of each pixel in the image.

65. Calculating an average red intensity of pixels in the foreground of the image and an average blue intensity of pixels in the foreground of the image; classifying the stained blood cells based on the average red intensity and the average blue intensity; 65. The image analysis system of claim 64, further comprising:

66. 61. The image analysis system of any one of claims 55 to 60, wherein determining the maturity of the stained blood cells comprises utilizing pixel foreground counts.

67. 66. The image analysis system of any of claims 55-60 or 63-65, wherein determining the maturity of the stained blood cells comprises determining whether a pixel foreground count exceeds a threshold amount.

68. 68. The image analysis system of any one of claims 55 to 67, wherein the system further comprises one or more chambers adapted to receive the biological sample and lysis composition.

69. 69. The image analysis system of any one of claims 55 to 68, wherein the system comprises one or more chambers configured to receive the biological sample and a staining composition.

70. 70. The image analysis system of claim 69, wherein the system further comprises a heater configured to heat the biological sample and the staining composition.

71. 72. The image analysis system of claim 71, wherein the heater comprises an induction coil.

72. 72. The image analysis system of claim 70 or 71, wherein the one or more chambers include two or more chambers, and the heater is coupled to all of the two or more chambers.

73. 73. The image analysis system of claim 72, wherein the heater comprises a mounting bracket connected to all of the two or more chambers, and a heating element attached to the mounting bracket.

74. A machine, A camera and means for determining the maturity of cells in images acquired by said camera; A machine equipped with:

Images