Biofluid analyzer based on light settings for cell classification

Abstract

A biofluid analyzer is disclosed. The biofluid analyzer is configured to acquire image data for one or more image planes of an image stack in a prepared biofluid sample. The image data includes first image data associated with a first image plane. Acquiring the first image data includes acquiring first primary image data for the first image plane. The first primary image data is associated with a first incident light setting. The first incident light setting has a first angular light distribution. Acquiring the first image data includes acquiring first secondary image data for the first image plane. The first secondary image data is associated with a second incident light setting. The second incident light setting has a second angular light distribution. The biofluid analyzer is configured to classify cells in the prepared biofluid sample based on the first primary image data and the first secondary image data and provide cellular parameters associated with the cells.

Description

Technical Field

[0001] The present disclosure relates to the analysis of biological fluid samples such as blood samples or cell culture samples, and more particularly to related tools, methods, and systems for cell classification based on optical settings. Accordingly, a biological fluid analyzer and related methods, particularly methods for analyzing biological fluid samples by cell classification based on optical settings, are provided.

Background Art

[0002] Currently, the analysis of biological fluid samples, such as determination of cell types, classification of cells, etc., may require a number of steps, preparations, resources, and various sophisticated instruments. Blood measurements or other cell-based measurements may rely on the discrimination of different cell types, such as the discrimination of different white blood cells (e.g., white blood cell types). The process of identifying cells largely depends on identifying specific characteristics of the cells, such as the number of nuclear lobes of the cell membrane, size, shape, and / or texture, the texture and / or area of the cytoplasm.

[0003] Finding the optimal conditions can be difficult between the quality of the optical system, e.g., how much detail can be observed regarding the cells, the cost, e.g., better quality is more expensive, and / or the magnification, e.g., the better the magnification, the more detail can be provided but the fewer cells can be imaged. This trade-off and optical specifications can lead to situations where the level of detail in the cell images is not sufficient to reliably distinguish cell types from each other.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Therefore, there is a need for a biological fluid analyzer and related methods, particularly methods for improving the analysis of biological fluid samples, discrimination of cells, and analyzing biological fluid samples with accuracy.

Means for Solving the Problems

[0005] A biofluid analyzer is disclosed. The biofluid analyzer comprises memory, an interface, and one or more processors. The biofluid analyzer is configured to acquire image data of one or more image planes of an image stack in a prepared biofluid sample, such as a blood sample or a cell culture sample. The image data includes first image data associated with a first image plane. Acquiring the first image data includes acquiring first primary image data of the first image plane. The first primary image data is associated with a first incident light setting. The first incident light setting may optionally have a first angular light distribution. Acquiring the first image data includes acquiring first secondary image data of the first image plane. The first secondary image data is associated with a second incident light setting. The second incident light setting may optionally have a second angular light distribution. Based on the first primary image data and / or the first secondary image data, the biofluid analyzer is configured to classify cells in a prepared biofluid sample, such as a blood sample or a cell culture sample, and to provide cell parameters associated with the cells.

[0006] Furthermore, a method for classifying cells in a prepared biological fluid sample, such as a blood sample or a cell culture sample, is disclosed. This method includes the step of acquiring image data of one or more image planes in an image stack of the prepared biological fluid sample, such as a blood sample or a cell culture sample, wherein the image data includes first image data associated with a first image plane. Acquiring the first image data includes acquiring first primary image data of the first image plane. The first primary image data is associated with a first incident light setting having a first angular light distribution. The step of acquiring the first image data includes the step of acquiring first secondary image data of the first image plane. The first secondary image data is associated with a second incident light setting having a second angular light distribution. This method includes the step of classifying cells in the prepared biological fluid sample, such as a blood sample or a cell culture sample, based on the first primary image data and the first secondary image data. This method includes the step of providing cell parameters associated with the cells based on the cell classification. This method can be performed using a biological fluid analyzer disclosed herein.

[0007] Also disclosed is a system comprising a microscope, an imaging system, an image acquisition device, a biofluid sample cavity for containing a prepared biofluid sample such as a blood sample or a cell culture sample, and a biofluid analyzer, wherein the biofluid analyzer is the biofluid analyzer according to this disclosure. Optionally, the system comprises an imaging system. The imaging system may comprise one or more of a light source assembly configured to emit light, a lens assembly configured to guide light from the light source assembly, and an aperture device configured to apply an aperture to indirectly define probe light, thereby allowing light from the lens assembly to pass through the aperture.

[0008] The advantage of this disclosure is that it provides improved biofluid analysis. This disclosure provides improved cell classification, such as improved single cell classification based on light settings. For example, it is possible to achieve more efficient, accurate, precise, and robust image-based cell parameter determination, such as cell classification and / or single cell classification, such as determination of the type and / or cell concentration of leukocytes (WBCs) in a biological fluid sample, such as the concentration of WBCs, platelets, and / or specific pathological cell types. Furthermore, improved cell classification with higher accuracy is provided, and improved cell analysis such as detailed cell classification, such as analysis and / or classification of leukocytes is provided. By classifying cells based on image data acquired under different incident light settings, such as first primary image data and first secondary image data, the Disclosure provides classification based on more information than known techniques, such as additional cell information. The Disclosure thereby allows for consideration of different incident light settings when classifying cells in a biological fluid sample. In other words, the Disclosure can provide cell classification based on light settings.

[0009] The advantage of this disclosure is to provide more detailed, efficient, precise, and customized analysis of biological fluid samples. For example, it is possible to determine cellular parameters such as the classification of cells, including leukocytes, and cell counting, within one or more image planes. Another advantage of this disclosure is to provide improved cell differentiation, such as improved differentiation of leukocytes. Thus, it is possible to detect abnormalities in biological fluid samples with greater precision. This disclosure can also alleviate the challenges related to trade-offs between optical system quality, cost, magnification, and / or optical specifications by providing improved cell differentiation, even with limited instrument quality and / or cost, for example.

[0010] The above and other features and advantages of the present invention will be readily apparent to those skilled in the art through the following detailed description of exemplary embodiments of the invention with reference to the accompanying drawings. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram of an exemplary biological fluid analyzer as described in this disclosure. [Figure 2] This figure schematically illustrates an exemplary system comprising an exemplary biofluid analyzer as described herein. [Figure 3] This diagram schematically shows an exemplary system equipped with an exemplary imaging system. [Figure 4] This is a flowchart illustrating the exemplary method described herein. [Figure 5] This figure shows exemplary images of cells (such as cell regions) acquired under different image planes and different incident light settings, where the exemplary methods and / or biofluid analyzers described herein are performed and / or used. [Figure 6] This figure shows exemplary images of cells (such as cell regions) acquired under different image planes and different incident light settings, where the exemplary methods and / or biofluid analyzers described herein are performed and / or used. [Figure 7] This figure shows exemplary images of cells (such as cell regions) acquired under different image planes and different incident light settings, where the exemplary methods and / or biofluid analyzers described herein are performed and / or used. [Figure 8] This figure shows exemplary images of cells (such as cell regions) acquired under different image planes and different incident light settings, where the exemplary methods and / or biofluid analyzers described herein are performed and / or used. [Figure 9] This figure shows exemplary images of cells (such as cell regions) acquired under different image planes and different incident light settings, where the exemplary methods and / or biofluid analyzers described herein are performed and / or used. [Modes for carrying out the invention]

[0012] Various exemplary embodiments and details are described below with reference to the relevant figures. Note that these figures may not be drawn to scale, and throughout these figures, elements of similar structures or functions are represented by similar reference numerals. Note that these figures are intended solely to facilitate the description of the embodiments. These figures are not intended to be an exhaustive description of the invention or a limitation on the scope of the invention. In addition, the embodiments shown do not necessarily have all of the aspects or advantages shown. Aspects or advantages described in relation to a particular embodiment are not necessarily limited to that embodiment and may be implemented in any other embodiment, even if not shown or explicitly stated as such.

[0013] These figures are schematic and simplified for clarity, showing only the details that aid in understanding this disclosure, and omitting other details. Throughout these figures, the same reference numbers are used for identical or corresponding parts.

[0014] Whenever the proximal side of the image plane is referred to, the reference refers to the side closest to the camera or sensor (e.g., a microscope) when the image is acquired / captured, or the surface facing the camera or sensor. Similarly, when the distal side of the image plane is referred to, the reference refers to the side furthest from the camera or sensor when the image is acquired / captured, or the surface facing away from the camera or sensor. In other words, the proximal side or proximal surface is the side or surface closest to the camera or sensor when the image is acquired / captured, and the distal side is the side or surface opposite to the image plane. In other words, the distal side may be the side or surface closest to the bottom of a container containing a prepared biological fluid sample, such as a blood sample or a cell culture sample, when the image is acquired / captured. An image stack, such as a stack of image planes, can be considered to contain one or more slices of the sample in the image. The optical sensor may be, for example, an image sensor having a pixel resolution of at least 1 megapixel. In one or more exemplary biological fluid analyzers, the camera or optical sensor is configured to be non-replaceable. Non-replaceable means that, during normal operation of the biofluid analyzer, it is not possible to access the camera or optical sensor directly, and that the camera or optical sensor cannot be removed without removing a separate component of the biofluid analyzer, such as removing a light-shielding panel. This improves the simplicity of the biofluid analyzer and allows for a relatively compact design, as it eliminates the need for the user to easily access and replace the camera or optical sensor.

[0015] A biological fluid analyzer is disclosed. The biological fluid analyzer includes a memory, an interface, and one or more processors. The biological fluid analyzer can include an electronic device such as a computer, for example, a laptop computer or a PC, a tablet computer, and / or a mobile phone, for example, a smartphone. The biological fluid analyzer can be, for example, a point-of-care (POC) device. The biological fluid analyzer can be configured to be integrated with, for example, a blood gas analyzer. The biological fluid analyzer can be a user device such as a computer or a mobile phone configured to analyze a biological fluid sample such as a prepared biological fluid sample, for example, a blood sample or a cell culture sample. The biological fluid analyzer can be, for example, part of a laboratory device. The biological fluid analyzer can be used as an instrument near a patient, for example, a point-of-care device. The biological fluid analyzer can be configured to perform blood measurement and / or analysis.

[0016] The biological fluid analyzer can be a blood analyzer. In other words, the biological fluid analyzer can be configured to analyze human blood and / or animal blood, for example, mammalian blood. Thus, the prepared biological fluid sample can be a prepared blood sample.

[0017] The biological fluid analyzer can also be a cell culture analyzer. In other words, the biological fluid analyzer can be configured to analyze a cell culture, for example, a culture of cells derived from a multicellular eukaryote such as mammalian cells, animal cells, and / or human cells, and / or a culture of cells grown from a plant tissue culture, a fungal culture, and / or a microbial culture (microorganisms). Thus, the prepared biological fluid sample can be a prepared cell culture sample.

[0018] In one or more exemplary biological fluid analyzers, the biological fluid analyzer is a server device, for example, acting as a server device. In other words, the biological fluid analyzer can be regarded as being implemented on a server device. For example, the biological fluid analyzer can be configured to execute and / or operate on a server device. The biological fluid analyzer acting as a server device can be regarded as a device configured to act as a server that communicates with client devices such as a computer, for example, a laptop computer or a PC, a tablet computer, and / or a mobile phone, for example, a smartphone. For example, the biological fluid analyzer can be a remote server device configured to communicate with client devices. The biological fluid analyzer acting as a server device can be configured to perform any one or more of, for example, acquiring image data such as first image data, acquiring first primary image data, acquiring first secondary image data, classifying cells in a prepared biological fluid sample such as a blood sample or a cell culture sample, and providing cell parameters associated with the cells. The biological fluid analyzer acting as a server device can be configured to output cell parameters to a client device, for example.

[0019] In one or more exemplary biological fluid analyzers, the biological fluid analyzer is configured to acquire first secondary image data less than 20 seconds after acquiring the first primary image data, for example, less than 10 seconds, for example, less than 5 seconds, for example, less than 1 second. This enables relatively rapid acquisition of the first primary image data and the first secondary image data, thereby further improving the possibility of acquiring the first primary image data and the first secondary image data with at least a partially same volume of the prepared biological fluid sample.

[0020] In one or more exemplary biofluid analyzers, a first primary image data is acquired at a first probe volume, and a first secondary image data is acquired at a second probe volume, with at least a portion of the first and second probe volumes overlapping. In some examples, at least 90%, at least 70%, or at least 50% of the first and second probe volumes overlap. The biofluid analyzer may be configured to maintain the probe volume, and optionally the container, in a stationary state during, for example, a change from a first throttling configuration to a second throttling configuration. Additionally or alternatively, this allows imaging of at least a portion of the same volume of prepared biofluid by the throttling devices of the first and second throttling configurations. This can be particularly advantageous when combined with an exemplary biofluid analyzer, wherein the imaging system is configured to selectively provide a first probe light containing only incident light angles within a first optical angle range, and / or the imaging system is configured to selectively provide a second probe light containing only incident light angles within a second optical angle range, thereby enabling the effective acquisition of image data of at least a portion of the same volume of prepared biofluid sample acquired at different incident light angles.

[0021] In one or more exemplary biofluid analyzers, the biofluid analyzer defines an optical path corresponding to the optical path of a transmission microscope. In other words, the imaging system can be configured to acquire image data from probe light transmitted through the probe volume. This allows imaging of the prepared bodily fluid sample without relying solely on fluorescence emitted by the prepared fluid analyzer. Additionally, this can improve the simplicity and reduce the footprint of the biofluid analyzer, which can be particularly useful for cell classification, especially in therapeutic and / or clinical settings. Furthermore, for richer image data and, if applicable, improved cell classification, the biofluid analyzer can be enabled to acquire an image stack of the image plane.

[0022] The biofluid analyzer is configured to acquire image data of one or more image planes of an image stack within a prepared biofluid sample, such as a blood sample or cell culture sample, also represented by an ID. The image data may include one or more images, for example, multiple images, for example, a stack of images, and / or an image stack. The image data may include multiple images of the prepared biofluid sample, such as a blood sample or cell culture sample, acquired by a microscope and camera, such as a CMOS image sensor camera. The image data may include, for example, at least 10 images, at least 20 images, at least 30 images, at least 40 images, at least 50 images, or at least 100 images. The images in the image data may have an area corresponding to the area of ​​the camera image sensor and the microscope magnification, for example A = A_im / M 2Here, A is the area of ​​the captured image, M is the microscope magnification of the microscope, and A_im is the area of ​​the camera image sensor. The image data can have pixel sizes ranging from 0.1 μm to 5 μm, for example, 0.5 μm, 1 μm, or 2 μm, depending on the resolution of the camera and objective lens used. The image data can include multiple images of a prepared biological fluid sample, such as a blood sample or a cell culture sample, and each image of the multiple images is associated with the image plane of the prepared biological fluid sample, such as a blood sample or a cell culture sample. The microscope and camera can acquire / obtain multiple images by moving along the z-axis in the optical focal plane, such as perpendicular to the prepared biological fluid sample, such as a blood sample or a cell culture sample. Thus, the image data can include multiple images associated with an image plane, and each image plane is separated by a distance Δz from the next acquired / obtained image plane and / or the previously acquired / obtained image plane. Δz can be the step increment for each acquired / obtained image. For example, image data may include multiple images of a prepared biological fluid sample, such as a blood sample or a cell culture sample, and each image may be associated with an image plane equidistant from the next acquired / obtained image plane and / or the previously acquired / obtained image plane. In other words, image data may include 3D image stacks, such as an image stack where each image in the image stack is associated with an image plane having a different associated height along the z-axis of the prepared biological fluid sample, such as a blood sample or a cell culture sample. In other words, each image plane may be associated with an intrinsic height within the prepared biological fluid sample, such as a blood sample or a cell culture sample contained in a container, for example, a blood sample or a cell culture sample contained in a cuvette. The distance between two image planes can be expressed as the inter-image distance. The distance between two image planes may vary, for example, depending on the type of cell of interest. For example, the distance between two image planes may also vary depending on the numerical aperture (NA) of the microscope used, and therefore on the depth of field (DOF).This can be done to achieve an image in an image stack where the cell has the best focus. For example, when the cell of interest is a platelet, for example, a platelet has a diameter in the range of 1 μm to 5 μm, for example, in the range of 2 μm to 3 μm, so the distance between the two image planes can be, for example, in the range of 1 μm to 10 μm, for example, in the range of 2 μm to 8 μm, in the range of 3 μm to 6 μm, in the range of 1 μm to 8 μm, and / or in the range of 1 μm to 6 μm. For example, when the cell of interest is a platelet, for example, a platelet has a diameter in the range of 1 μm to 5 μm, for example, in the range of 2 μm to 3 μm, so the distance between the two image planes can be, for example, 5.04 μm. For example, when the cell of interest is a leukocyte, the distance between the two image planes can be, for example, in the range of 4 μm to 15 μm, for example, in the range of 5 μm to 12 μm, in the range of 5 μm to 10 μm, in the range of 8 μm to 12 μm, and / or in the range of 9 μm to 11 μm. For example, the distance between two image planes can be, for example, 4 μm, 5 μm, 6 μm, 7 μm, 8 μm, 9 μm, 10 μm, and / or 11 μm. For example, a leukocyte with a diameter in the range of 5 μm to 10 μm may belong to two image planes. The image data may include multiple images of the central portion of a biological fluid sample (such as a prepared biological fluid sample, like a blood sample or a cell culture sample). In other words, the image data may include multiple acquired / obtained images of a prepared biological fluid sample, such as a blood sample or a cell culture sample, representing the area or volume of the prepared biological fluid sample, such as a blood sample or a cell culture sample, located away from the rim of the container containing the prepared biological fluid sample. The advantage of having images of a prepared biological fluid sample that represent the area or volume of the prepared biological fluid sample, located away from the rim of the container containing the prepared biological fluid sample, is that it is possible to avoid seeing the rim of the container's glass, such as dirt on the glass of the container. One or more exemplary biological fluid analyzers can crop the image data, such as one or more images of the image data.For example, by cropping 20% ​​of the side length of the field of view (FOV), an image obtained with a resolution of 20 megapixels can be cropped. The cropped image can be of the central part of the biological fluid sample, such as the reduced portion of the FOV. The central part of the biological fluid sample can have the best optical resolution and the least optical aberration. An advantage of using cropped images is that a larger number of images can be selected from the image data. For example, virtually all images from the image data can be selected, such as at least 20 images, at least 30 images, or at least 40 images. Selecting more images makes it possible to compensate for inaccurate distance shifts in the microscope's focusing mechanism (such as mechanical delta-Z motion). A further advantage of using cropped images is the saving of computing resources for image characterization, such as determining cell region clusters.

[0023] Each image data ID may contain multiple representations. Multiple representations may include multiple particles, such as cells, such as leukocytes (WBCs), platelets (PLTs), red blood cells (RBCs), clots of blood components, cellular debris, and / or external particles, such as dust, precipitates, or residues from a container. Multiple representations may include multiple cells, such as mature cells, such as reticulocytes (with slightly immature RBCs), lymphocytes, and / or monocytes, segmented and band granulocytes (with slightly immature neutrophils), neutrophils, eosinophils, and / or basophils, as well as immature cells, such as normoblasts, erythroblasts, proerythroblasts, metamyelocytes, myelocytes, promyelocytes, myeloblasts, monoblasts, and / or lymphoblasts.

[0024] A prepared biological fluid sample may include a biological fluid sample prepared by one or more reagents, chemicals, treatments, and / or processes. A prepared biological fluid sample may include, for example, a stained biological fluid sample, such as a chemically stained biological fluid sample. A prepared biological fluid sample may include a biological fluid sample that is positioned / fixed so that substantially no cell movement occurs during the acquisition / acquisition of images of the prepared biological fluid sample. A prepared biological fluid sample can be understood as a solution containing biological fluid and one or more reagents and / or chemicals. A prepared biological fluid sample can be understood as a lysate, such as a lysate biological fluid sample. A prepared biological fluid sample may be placed / positioned in a container such as a cuvette while image data, such as multiple images of the prepared biological fluid sample, are acquired / acquired. The height to which the image plane is associated may be, for example, the height or distance on the z-axis from the bottom of the container / cubet or camera / microscope when the image is acquired / captured. The image plane to which multiple images can extend may be a two-dimensional plane, such as an xy-plane perpendicular to the z-axis.

[0025] In an exemplary biofluid analyzer where the cuvette is a multipurpose cuvette, the biofluid analyzer can be configured as a multipurpose device equipped with the necessary fluid systems and mechanisms for performing multiple measurements. Such exemplary biofluid analyzer may further include a solution pack containing one or more solutions, and the exemplary biofluid analyzer may be configured, by means of its fluid system and mechanisms, to manage and release the solution pack so as to automatically prepare the prepared body fluid sample at least partially after aspiration, and may be configured to control the fluid system so as to run at least a cleaning program for the multipurpose cuvette before and / or after biofluid analysis.

[0026] A prepared biological fluid sample can be a prepared blood sample prepared by one or more reagents, chemicals, treatments, and / or processes. A prepared blood sample may include, for example, stained blood samples, such as chemically stained blood samples. A prepared blood sample may include, for example, a hemolyzed blood sample, such as one in which most of the red blood cells in the blood sample have been removed. A prepared blood sample may include a positioned / fixed blood sample, such as one in which substantially no cell movement occurs during the acquisition / acquisition of an image of the prepared blood sample. A prepared blood sample can be understood as a solution containing blood and one or more reagents and / or chemicals. A prepared blood sample can be understood as a lysate, such as a lysed blood sample. A prepared blood sample may be placed / positioned in a container such as a cuvette while image data, such as multiple images of the prepared blood sample, are acquired / acquired. The height to which the image plane is associated may be, for example, the height or distance on the z-axis from the bottom of the container / cubet or camera / microscope when the image is acquired / captured. The image plane to which multiple images can extend may be a two-dimensional plane, such as an xy-plane orthogonal to the z-axis.

[0027] Optionally, the image data ID includes image data that includes the first image data ID_1 associated with a first image plane, which is also represented as a first image data ID_1, for example, IP_1. In other words, the image data may include first image data that includes one or more images associated with a first image plane in an image stack. Optionally, the biofluid analyzer may be configured to select an image also represented as I_i, where i is the number of selected images associated with an image plane also represented as IP_i of the prepared biofluid sample from the image data ID, such as an image stack. The biofluid analyzer may be configured to select a first image also represented as I_1 associated with a first image plane IP_1 of the prepared biofluid sample from the image data ID. In other words, selecting image I_i may include selecting a first image I_1 associated with a first image plane IP_1 of the prepared biofluid sample from the image data ID. The first image I_1 may be selected from multiple images obtained from the image data ID. Optionally, the biofluid analyzer may be configured to select a second image I_2, a third image I_3, a fourth image I_4, and / or a fifth image I_5. In one or more exemplary biofluid analyzers, the biofluid analyzer may be configured to select more images, e.g., 10 images, 20 images, or more. The images selected from the image data may be selected from a set of images, e.g., at least 20 images, each image associated with an image plane of the prepared biofluid sample. Selecting image data may include storing one or more images of the prepared biofluid sample in a dataset to provide, for example, a stack of images. Each image in the stack of images may be associated with an image plane having a different associated height along the z-axis of the prepared biofluid sample. In other words, each image plane may be associated with a different height along the z-axis of the prepared biofluid sample.

[0028] Acquiring the first image data ID_1 includes acquiring the first primary image data ID_1_1 of the first image plane IP_1. The first primary image data ID_1_1 is associated with the first incident light setting ILS_1. Optionally, the first incident light setting ILS_1 may have a first angular light distribution ALD_1. In other words, the first primary image data ID_1_1 can be considered to have been acquired by and / or in accordance with the first incident light setting ILS_1 having the first angular light distribution ALD_1. The first primary image data ID_1_1 can be associated with image data acquired from a prepared biological fluid sample while the prepared biological fluid sample is illuminated by probe light according to the first incident light setting ILS_1 having the first angular light distribution ALD_1.

[0029] The first incident light setting ILS_1 may include one or more microscope settings, one or more light source settings, and / or one or more aperture settings. The first incident light setting can provide probe light for investigating a prepared biological fluid sample, such as light incident on the prepared biological fluid sample. In other words, the first incident light setting ILS_1 may be provided via one or more of the microscope settings, light source settings, and / or aperture settings.

[0030] In one or more exemplary biofluid analyzers, a first image plane is associated with a first height, also represented by H_1, within the prepared biofluid sample. The first height to which the first image plane is associated can be the height on the z-axis, for example, relative to the bottom of the container / cuvette or camera / microscope, when the first image data, such as the first image, is acquired / captured.

[0031] Acquiring the first image data ID_1 includes acquiring the first secondary image data ID_1_2 of the first image plane IP_1. The first secondary image data ID_1_2 is associated with the second incident light setting ILS_2. Optionally, the second incident light setting ILS_2 may have a second angular light distribution ALD_2. In other words, the first secondary image data ID_1_2 can be considered to have been acquired by and / or in accordance with the second incident light setting ILS_2 having the second angular light distribution ALD_2. The first secondary image data ID_1_2 can be associated with image data acquired from the prepared biological fluid sample while the prepared biological fluid sample is illuminated by probe light according to the second incident light setting ILS_2 having the second angular light distribution ALD_2.

[0032] The second incident light setting ILS_2 may include one or more microscope settings, one or more light source settings, and / or one or more aperture settings. The second incident light setting can provide probe light for investigating a prepared biological fluid sample, such as light incident on the prepared biological fluid sample. In other words, the second incident light setting ILS_2 may be provided via one or more of the microscope settings, light source settings, and / or aperture settings.

[0033] The angular light distribution can be considered as the spatial distribution of incident light. In other words, the angular light distribution can be considered as the spatial distribution of one or more light components incident on a prepared biological fluid sample. For example, the angular light distribution can indicate one or more light angles (such as spatial light angles) of probe light used to investigate a prepared biological fluid sample.

[0034] In one or more exemplary biofluid analyzers, acquiring first image data includes acquiring first tertiary image data ID_1_3 of a first image plane IP_1. In one or more exemplary biofluid analyzers, the first tertiary image data ID_1_3 is associated with a third incident light setting ILS_3 having a third angular light distribution ALD_3. In one or more exemplary biofluid analyzers, classifying cells in a prepared biofluid sample is based on the first tertiary image data ID_1_3.

[0035] In other words, the first tertiary image data ID_1_3 can be considered to have been acquired by and / or in accordance with a third incident light setting ILS_3 having a third angular light distribution ALD_3. The first tertiary image data ID_1_3 can be associated with image data acquired from a prepared biological fluid sample while the prepared biological fluid sample is illuminated by probe light according to a third incident light setting ILS_3 having a third angular light distribution ALD_3.

[0036] The third incident light setting ILS_3 may include one or more microscope settings, one or more light source settings, and / or one or more aperture settings. The third incident light setting can provide probe light for investigating a prepared biological fluid sample, such as light incident on the prepared biological fluid sample. In other words, the third incident light setting ILS_3 may be provided via one or more of the microscope settings, light source settings, and / or aperture settings.

[0037] The description of the first incident light setting ILS_1 and / or the second incident light setting ILS_2 can also be applied to the third incident light setting ILS_3. In one or more exemplary biofluid analyzers, the first incident light setting includes one or more of the lens assembly setting, aperture setting, angle setting, and light source setting. In other words, the first incident light setting ILS_1 may include one or more of the first lens assembly setting, first aperture setting, first angle setting, and first light source setting.

[0038] In one or more exemplary biofluid analyzers, the second incident light setting ILS_2 includes one or more of the lens assembly setting, aperture setting, angle setting, and light source setting. In other words, the second incident light setting ILS_2 may include one or more of the second lens assembly setting, second aperture setting, second angle setting, and second light source setting.

[0039] A lens assembly configuration can be considered as one or more configurations associated with one or more lens assemblies, such as a first lens assembly, a second lens assembly, and a third lens assembly, which can be formed from one or more lenses. A lens assembly configuration can be considered as one or more lenses of a lens assembly that can be arranged to guide light received from a light source according to a desired light pattern. For example, a lens assembly can be configured to guide received light toward the back focal point of the lens assembly. A lens assembly configuration may include configurations of lens assemblies to achieve a desired light pattern, such as a first incident light configuration ILS_1 and / or a second incident light configuration ILS_2. This can be achieved by a suitable combination of lenses, such as convex and concave lenses with suitable refractive indices.

[0040] An aperture setting can be considered as one or more settings associated with one or more aperture assemblies, such as a first aperture assembly, a second aperture assembly, and a third aperture assembly, which can be formed from one or more apertures. An aperture setting can include aperture sizes such as 2 mm, 3 mm, 4 mm, and / or 5 mm. The aperture size can be in the range of 1 mm to 10 mm. An aperture setting can be configured to provide a first incident light setting ILS_1 and / or a second incident light setting ILS_2. In other words, an aperture setting can define a set of settings for one or more aperture assemblies, such as an aperture assembly of a microscope, to provide, for example, a first incident light setting ILS_1 and / or a second incident light setting ILS_2. An aperture setting can include configurations of aperture assemblies to achieve a desired light pattern, such as a first incident light setting ILS_1 and / or a second incident light setting ILS_2.

[0041] A light source setting can be considered as one or more settings associated with one or more light sources, for example, one or more incident light source assemblies. A light source assembly can be formed from support elements that support multiple light sources, such as multiple LEDs. A light source assembly can include electrical circuits for providing power to multiple light sources. A light source assembly can be configured to emit light according to one or more configurations, such as one or more light configurations. A light source setting can be configured to provide a first incident light setting ILS_1 and / or a second incident light setting ILS_2. In other words, a light source setting can define a set of settings for one or more light source assemblies, such as a microscope light source assembly, to provide, for example, a first incident light setting ILS_1 and / or a second incident light setting ILS_2. A light source setting can include configurations of light source assemblies to achieve a desired light pattern, such as a first incident light setting ILS_1 and / or a second incident light setting ILS_2. A light source setting such as a first incident light setting ILS_1 and / or a second incident light setting ILS_2 can include pattern settings and / or intensity settings.

[0042] An angle setting can be considered as one or more settings associated with one or more angles, for example, one or more incident light angles of probe light. An angle setting can indicate an incident light angle in the range of 0° to 90°. For example, certain cellular features, such as cell size and / or cell shape, can be observed at larger angles, for example, larger apertures (such as larger numerical apertures). An angle setting can be provided through one or more of the lens assembly settings, aperture settings, and light source settings. An angle setting can be configured to provide a first incident light setting ILS_1 and / or a second incident light setting ILS_2, for example, a first light angle LA_1 and / or a second light angle LA_2. In other words, an angle setting can define a set of settings for one or more lens assemblies, aperture assemblies, and / or light source assemblies to provide, for example, a first incident light setting ILS_1 and / or a second incident light setting ILS_2. The angle setting may include one or more configurations of lens assembly settings, aperture settings, and light source settings to achieve a desired angle pattern, such as a first incident light setting ILS_1 and / or a second incident light setting ILS_2.

[0043] In one or more exemplary biofluid analyzers, a first incident light setting ILS_1 is configured to provide incident light that is also represented by a first probe light containing a first optical component LC_1 such that a first optical angle LA_1 is greater than a first angle A_1. The first optical component LC_1 may contain one or more rays contained within the first optical angle LA_1. The first optical component LC_1 may contain a first optical range. In other words, a first primary image data ID_1_1 can be associated with a first optical component LC_1 and / or a first optical angle LA_1. The first primary image data ID_1_1 can be obtained from a prepared biofluid sample, for example, a first image plane IP_1 illuminated by the first probe light and / or the first optical component LC_1 at, for example, a first optical angle LA_1. Being greater than a first angle A_1 can be understood as the first optical component LC_1 having a first optical angle LA_1 that is at least a first angle A_1. The first angle A_1 can be considered as the first incident light angle of the light striking the prepared biological fluid sample. The first angle A_1 can be in the range of 0° to 60°, for example, the first light component is greater than the first angle A_1 in the range of 0° to 30°. The first angle A_1 can be measured with respect to the optical axis of the imaging device, for example, an axis perpendicular to the prepared biological fluid sample, for example, it can be measured around an axis perpendicular to the prepared biological fluid sample.

[0044] The first probe light provided according to the first incident light setting ILS_1 may include light whose incident light angle with respect to the optical axis of the imaging system is smaller than the first up-angle. The first up-angle can be 15 degrees or less than 15 degrees, for example, 15 degrees or less than 10 degrees, or even 5 degrees or less than 5 degrees. In one or more exemplary biofluid analyzers, the first probe light provided according to the first incident light setting ILS_1 does not have, or substantially does not have, light whose incident light angle with respect to the optical axis is greater than the first up-angle.

[0045] In one or more exemplary biofluid analyzers, the first probe light provided according to the first incident light setting ILS_1 may include light whose incident light angle with respect to the optical axis is greater than the first under-light angle. The first under-light angle may be 0 degrees or greater than 0 degrees, for example, 2 degrees or greater than 2 degrees, 5 degrees or greater than 5 degrees, or 10 degrees or greater than 10 degrees. In one or more exemplary biofluid analyzers, the first probe light provided according to the first incident light setting ILS_1 may not have, or substantially not have, light whose incident light angle with respect to the optical axis is less than the first under-light angle.

[0046] The first downward light angle and the first upward light angle can define a first optical angle range of the first probe light. The first optical angle range can be 0 to 15 degrees, for example 0 to 10 degrees, for example 5 to 10 degrees.

[0047] In other words, the imaging system can be configured to selectively provide a first probe beam containing only light having an incident light angle within a first optical angle range. In one or more exemplary biofluid analyzers, a second incident light setting ILS_2 is configured to provide incident light that is also represented by a second probe light containing a second optical component LC_2 such that the second optical angle LA_2 is greater than the second angle A_2. The second optical component LC_2 may contain one or more rays contained within the second optical angle LA_2. The second optical component LC_2 may contain a second optical range. In other words, a first secondary image data ID_1_2 can be associated with the second optical component LC_2 and / or the second optical angle LA_2. The first secondary image data ID_1_2 can be obtained from a prepared biofluid sample, for example, a second image plane IP_2 illuminated by the second probe light and / or the second optical component LC_2, for example, at the second optical angle LA_2. The second angle being greater than A_2 can be understood as the second optical component LC_2 having a second optical angle LA_2 that is at least the second angle A_2. The second angle A_2 can be considered as the second incident light angle of the light striking the prepared biological fluid sample. The second angle A_2 can be in the range of 10° to 90°, for example, the second light component is greater than the second angle A_2 in the range of 15° to 90°. The second angle A_2 can be measured with respect to the optical axis of the imaging device, for example, the axis perpendicular to the prepared biological fluid sample, or it can be measured around the axis perpendicular to the prepared biological fluid sample.

[0048] The second probe light provided according to the second incident light setting ILS_2 may include light whose incident light angle with respect to the optical axis of the imaging system is smaller than the second uplight angle. The second uplight angle may be 30 degrees or less than 30 degrees, for example, 20 degrees or less than 20 degrees, or even 17 degrees or less than 17 degrees. In one or more exemplary biofluid analyzers, the second probe light provided according to the second incident light setting ILS_2 does not have, or substantially does not have, light whose incident light angle with respect to the optical axis is greater than the second uplight angle.

[0049] In one or more exemplary biofluid analyzers, the second probe light provided according to the second incident light setting ILS_2 may include light whose incident light angle with respect to the optical axis is greater than the second lower light angle. The second lower light angle may be greater than the first upper light angle. The second lower light angle may be 0 degrees or greater than 0 degrees, for example, 2 degrees or greater than 2 degrees, 5 degrees or greater than 5 degrees, or 10 degrees or greater than 10 degrees. In one or more exemplary biofluid analyzers, the second probe light provided according to the second incident light setting ILS_2 may not have, or substantially not have, light whose incident light angle with respect to the optical axis is less than the second lower light angle.

[0050] The second downward and second upward angles can define a second optical angle range for the second probe light. The second optical angle range can be 0 to 20 degrees, for example, 5 to 20 degrees, or for example, 10 to 17 degrees. The second optical angle range and the first optical angle range do not overlap.

[0051] In other words, the imaging system can be configured to selectively provide a second probe beam containing only light having an incident light angle within a second optical angle range. In one or more exemplary biofluid analyzers, N incident light settings ILS_1, ILS, ILS_2, ..., ILS_N can be applied to each image plane. The number of incident light settings N can be 2, 3, 4, 5, 6, 7, or more. N can be in the range of 2 to 5.

[0052] In one or more exemplary biofluid analyzers, the first incident light setting ILS_1 includes an aperture setting indicating a first aperture size AS_1 used to acquire first primary image data. The first aperture size AS_1 can be 2 mm, 3 mm, 4 mm, and / or 5 mm. The first aperture size AS_1 can be in the range of 1 mm to 10 mm. In other words, the first primary image data ID_1_1 can be acquired when the first aperture size AS_1 is used to illuminate a prepared biofluid sample. In other words, the first incident light setting ILS_1 can be acquired by the first aperture AP_1.

[0053] In one or more exemplary biofluid analyzers, the second incident light setting ILS_2 includes an aperture setting indicating a second aperture size AS_2 used to acquire a second primary image data. The second aperture size AS_2 can be 2 mm, 3 mm, 4 mm, and / or 5 mm. The second aperture size AS_2 can be in the range of 1 mm to 10 mm. In other words, the first secondary image data ID_1_2 can be acquired when the second aperture size AS_1 is used to illuminate a prepared biofluid sample. The aperture size can be considered as the opening size of the aperture assembly. In other words, the second incident light setting ILS_2 can be acquired by the second aperture AP_2.

[0054] In one or more exemplary biofluid analyzers, the second incident light setting ILS_2 is configured to provide an incident light angle that does not overlap with the incident light angle provided by the first incident light setting ILS_1. In other words, the second incident light setting ILS_2 can be configured to provide incident rays that do not overlap with the incident rays provided by the first incident light setting ILS_1. For example, the first optical component LC_1 may not overlap with the second optical component LC_2. In other words, the second incident light setting ILS_2 can be configured to provide a spatial distribution of optical components that does not overlap with the spatial distribution of optical components provided by the first incident light setting ILS_1.

[0055] In one or more exemplary biofluid analyzers, the first aperture size is different from the second aperture size. For example, the first aperture size may be 3 mm and the second aperture size may be 4 mm. In one or more exemplary biofluid analyzers, the shape of the first aperture AP_1 is different from the shape of the second aperture AP_2. The first aperture may have a first shape that is circular, elliptical, rectangular, square, non-circular, or any other preferred shape. The second aperture may have a second shape that is circular, elliptical, rectangular, square, non-circular, or any other preferred shape.

[0056] In one or more exemplary biofluid analyzers, the first incident light setting ILS_1 and / or the second incident light setting ILS_2 include aperture settings that indicate a numerical aperture in the range of 0 to 0.7.

[0057] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to determine a set of cell regions also represented by SCR_i based on an image data ID. In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to determine a set of cell regions also represented by SCR based on a first image data ID_1.

[0058] In one or more exemplary biofluid analyzers, determining a set of cell regions SCR_i may include characterizing image data, for example, characterizing one or more images I_i in an image stack. In one or more exemplary biofluid analyzers, determining a set of cell regions SCR_i based on image data may include determining a set of cell regions also represented by SCR_i belonging to an image plane IP_i. A cell region, also represented by CR_k_i, k=1,2,...K, can be understood as a group of pixels in image I_i representing one or more cells, parts of cells, several parts of cells, or an optical phenomenon associated with one or more cells, where K is the number of cell regions in the set of cell regions SCR_i and i is the number of selected images. In other words, a set of cell regions SCR_i includes one or more cell regions CR_k_i, for example, a group of pixels in image I_i representing one or more cells, one or more parts of one or more cells, or an optical phenomenon associated with one or more cells. The cellular region can preferably represent a single cell, a part of a single cell, or an optical phenomenon related to a single cell.

[0059] In one or more exemplary biofluid analyzers, determining a cell region set SCR_i may include characterizing a first image I_1. In one or more exemplary biofluid analyzers, determining a cell region set may be based on a first image data ID_1. In one or more exemplary biofluid analyzers, determining a cell region set SCR based on image data may include determining a first cell region set SCR_1 belonging to a first image plane IP_1. In other words, characterizing image I_i may include characterizing the first image I_1. In other words, determining a cell region set SCR_i based on image data may include determining a cell region set SCR_i belonging to an image plane IP_i. In other words, determining a cell region set SCR_i belonging to an image plane IP_i may include determining a first cell region set SCR_1 that is in focus within or associated with the first image plane IP_1. Being in the image plane, for example being in focus, can be considered as the cell region CR_k_i (such as a cell) in the first cell region set SCR_1 being best in focus. In other words, a cell region set SCR_i, for example the first cell region set SCR_1, may contain one or more cell regions, and for example, one or more groups of pixels in the first image I_1 may represent one or more cells, one or more parts of one or more cells, or an optical phenomenon associated with one or more cells. In one or more exemplary biofluid analyzers, determining a cell region set SCR_i may include storing one or more cell regions CR_k_i associated with a group of pixels in image I_i that represent one or more cells, parts of cells, several parts of cells, or an optical phenomenon associated with one or more cells in a dataset.

[0060] Belonging to image plane IP_i, for example belonging to the first image plane IP_1, can be understood as representing a cell (e.g., a cell volume) that is mostly located within image plane IP_i at the time the image is acquired / captured, or the cell region is assigned to the image plane, or is in focus within the image plane. For example, belonging to image plane IP_i can be understood as representing a cell CR_k_i that is mostly located within the volume around image plane IP_i, for example, a cell that is centrally located around image plane IP_i. For example, belonging to image plane IP_i can be understood as representing a cell CR_k_i that is located within the volume around image plane IP_i. For example, when the cells of interest are platelets, since platelets have a diameter in the range of 1 μm to 5 μm, for example, in the range of 2 μm to 3 μm, the distance between the two image planes, for example, the first distal distance, also represented by DD_1, between the first image plane IP_1 and the first distal image plane DIP_1 distal to the first image plane IP_1, and the first proximal distance, also represented by PD_1, between the first image plane IP_1 and the first proximal image plane PIP_1 proximal to the first image plane IP_1, can be in the range of 1 μm to 20 μm, for example, in the range of 2 μm to 15 μm, for example, in the range of 2 μm to 10 μm, for example, in the range of 2 μm to 8 μm, for example, in the range of 3 μm to 6 μm, in the range of 1 μm to 8 μm, and / or in the range of 1 μm to 6 μm. For example, when the cells of interest are platelets, and platelets have a diameter in the range of 1 μm to 5 μm, the first distal distance DD_1 between the first image plane IP_1 and the first distal image plane DIP_1, and the first proximal distance PD_1 between the first image plane IP_1 and the first proximal image plane PIP_1, can be, for example, 3 μm, 3.5 μm, 4 μm, 4.5 μm, 5 μm, 5.5 μm, 6 μm, 7 μm, 8 μm, 9 μm, and / or 10 μm. For example, the distance D between image plane IP_i and the next neighboring image plane is 5.04 μm, and belonging to image plane IP_i can be understood as representing a cell region CR_k_i located within a volume of +2.02 μm and -2.02 μm around image plane IP_i.Belonging to image plane IP_i can be understood as representing a cell region CR_k_i located within the volume between image plane IP_i and the next neighboring image plane, for example, the next neighboring distal image plane and / or the next neighboring proximal image plane. In one or more exemplary biofluid analyzers, a cell region set can extend into two or more image planes. For example, when a cell region represents a cell greater than the distance between two image planes, this cell can extend into two or more image planes. In one or more exemplary biofluid analyzers, a cell region set can be assigned to an image plane, for example, the first image plane IP_1. In one or more exemplary biofluid analyzers, for example, to ensure that a cell belongs to an image plane, the distance between two neighboring image planes can be based on the size of the cell type of interest. For example, a leukocyte with a diameter in the range of 5 μm to 10 μm may belong to two image planes.

[0061] A biofluid analyzer is configured to classify cells, also represented by CE, in a prepared biofluid sample based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. In other words, a biofluid analyzer can be configured to characterize the cellular content of a prepared biofluid sample based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. For example, a biofluid analyzer can be configured to classify each cell in a cellular region of a first image plane IP_1 based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. In one or more exemplary biofluid analyzers, the biofluid analyzer can be configured to classify cells, for example, a first cell CE_1 in a first cellular region CR_k_1 of a cellular region set SCR_i, based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. Classifying a first cell CE_1 within a first cell region CR_k_1 of cell region set SCR_i may include characterizing the cellular content of a prepared biological fluid sample based on a first primary image data and / or a first secondary image data ID_1_2.

[0062] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify each cell in a cellular region of a first image plane IP_1 based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2.

[0063] The biofluid analyzer is configured to classify cell CEs in a prepared biofluid sample based on a first primary image data and / or a first secondary image data ID_1_2, and to provide cell parameters also represented by CPs associated with the cell CEs.

[0064] In other words, the biofluid analyzer is configured to provide a cell parameter CP_k_i indicating the cell type of a cell CE based on the classification of the cell CE. The biofluid analyzer can be configured to determine a cell parameter, also represented by CP_k_i, for each cell region CR_k_i of the cell region set SCR_i, where i is the number of selected images, e.g., image planes, and k is the number of cell regions. Providing the cell parameter CP_k_i may include classifying the cell CE associated with or represented by the cell region CR_k_i based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. The cell parameter CP_k_i may include, for example, cell type information. The cell parameter CP_k_i may include, for example, a cell type identifier indicating the cell type of the cell. Providing the cell parameter CP_k_i may include determining the cell parameter CP_k_i based on the classification. Providing the cell parameter CP_k_i may include classifying cell CEs associated with or represented by cell region CR_k_i based on optical phenomena (such as optical phenomena of cells in the neighboring image plane and / or under different incident light settings), for example, optical phenomena detected in first primary image data ID_1_1 and / or first secondary image data ID_1_2. Providing the cell parameter CP_k_i may include classifying cell CEs associated with or represented by cell region CR_k_i based on information determined from first primary image data ID_1_1 and / or first secondary image data ID_1_2.

[0065] A biofluid analyzer can be configured to classify a first cell CE_1 within a first cell region CR_1 of a cell region set SCR_i based on a first primary image data and / or a first secondary image data ID_1_2, and to provide a first cell parameter, also represented by CP_1, which indicates the cell type of the first cell CE_1. The cell parameter may include a first cell parameter. In other words, the biofluid analyzer can be configured to provide a cell parameter CP_k_i indicating the cell type of the first cell CE_1 based on the classification of the first cell CE_1. The biofluid analyzer can be configured to determine a first cell parameter, also represented by CP_k_i, for each cell region CR_k_i of the cell region set SCR_i, where i is the number of selected images and k is the number of cell regions. Providing the cell parameter CP_k_i may include classifying the first cell CE_1_i associated with or represented by the first cell region CR_k_1 based on the first primary image data and / or the first secondary image data ID_1_2. The cell parameter CP_k_i may include, for example, cell type information. The cell parameter CP_k_i may include, for example, a cell type identifier indicating the cell type of the first cell. Providing the cell parameter CP_k_i may include determining the cell parameter CP_k_i based on classification. Providing the cell parameter CP_k_i may include classifying the first cell CE_1_i associated with or represented by the first cell region CR_k_1 based on optical phenomena (optical phenomena of cells in the neighboring image plane, as well as / or image data acquired by different incident light settings, such as the first primary image data acquired by the first incident light setting ILS_1 and / or the first secondary image data acquired by the second incident light setting ILS_2). The advantage of acquiring a first primary image data obtained with a first incident light setting ILS_1, and / or a first secondary image data obtained with a second incident light setting ILS_2, is that additional information about the cell can be obtained.For example, different incident light settings can produce different optical phenomena. For instance, cells can act as lenses, and a "lens effect" occurs depending on the incident light settings (angle, etc.) of the illumination light used to examine a prepared biological fluid sample. In other words, the combination of conventional cell features and the "lens effect" can provide more information about cells than just cell features when using, for example, reduced magnification and / or moderate quality optics, thus improving classification.

[0066] Providing the cell parameter CP_k_i may include classifying the first cell CE_1_i associated with or represented by the first cell region CR_k_1 based on information determined from the first primary image data and / or the first secondary image data ID_1_2.

[0067] In one or more exemplary biofluid analyzers, classifying cellular CEs involves applying a classification model to one or more of the following: first primary image data ID_1_1, first secondary image data ID_1_2, and first tertiary image data ID_1_3. In one or more exemplary biofluid analyzers, classifying cellular CEs involves applying a classification model to one or more of the following: first primary image data ID_1_1, first secondary image data ID_1_2, first tertiary image data ID_1_3, second primary image data ID_2_1, second secondary image data ID_2_2, and second tertiary image data ID_2_3.

[0068] In one or more exemplary biofluid analyzers, the biofluid analyzer / processor comprises a classification circuit configured to operate according to one or more classification models. In one or more exemplary biofluid analyzers, providing a cell parameter CP_k_i involves applying a classification model to one or more of the first primary image data ID_1_1, the first secondary image data ID_1_2, and the first tertiary image data ID_1_3. Classifying cells in a prepared biofluid sample, such as within a cell region, may include determining whether the cell region and / or cells satisfy one or more criteria of the classification model, such as one or more features (e.g., cell features). Classifying cells in a prepared biofluid sample, such as within a cell region, may include determining the cell type of the cells based on the classification model. The biofluid analyzer may be configured to extract one or more features, such as cell features, from the first primary image data, the first secondary image data, and / or the first tertiary image data, using the classification circuit, etc. Cell features may represent one or more cells, a part of a cell, several parts of a cell, or an optical phenomenon associated with one or more cells. The biofluid analyzer can be configured to extract one or more features from cellular regions, for example, from multiple cellular regions of a cellular region set SCR_i, using a classification circuit or the like. The extracted features can be supplied by the biofluid analyzer as input to a classification model, for example to a classification circuit. The input to the classification model may include, for example, a first primary image data ID_1_1, a first secondary image data ID_1_2, and / or a first tertiary image data ID_1_3, which include a cellular information vector, for example, a cellular feature vector. The classification circuit may comprise a neural network with one or more hidden layers. Each layer of the neural network may comprise one or more nodes.For example, the classification of cells within a cell region may involve comparing one or more features (such as cellular features and / or optical features) present (e.g., extracted) in a first primary image data ID_1_1, a first secondary image data ID_1_2, and / or a first tertiary image data ID_1_3 with one or more model cells, e.g., cell regions, that contain cellular features known to represent a particular type of cell and / or optical phenomenon. The classification model may be a neural network having an input layer, one or more hidden layers, e.g., multiple hidden layers, and an output layer. The input to the classification model may include cell regions (e.g., cell regions), multiple cell regions, and / or one or more stored features. For example, the input to the classification model may include cell regions having a cell region size of 20*20 μm, for example, when having a pixel resolution of 0.5 μm. 2 It may include pixels. In one or more exemplary biofluid analyzers, the classification circuit comprises a neural network for each cell type, e.g., cell class, and thus the output layer of the neural network may have one node. In one or more exemplary biofluid analyzers, the biofluid analyzer / processor comprises a neural network for all cell types of interest. Thereafter, the output layer of the neural network may have one node for each cell type or class. The output layer may be connected to a final hidden layer. The classification model may include an artificial neural network ANN, e.g., a decision tree classifier. The classification model may be configured to detect and / or identify representative features, e.g., cellular features. For example, the classification model may perform interference detection of features across a cell population. The classification model may be configured to detect and / or identify representative features in a scatter flow cytometry scatter plot of a prepared biofluid sample.

[0069] In one or more exemplary biofluid analyzers, the first image data ID_1 includes a first composite image data based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2, for example, a first tertiary image data ID_1_3, a second primary image data ID_2_1, a second secondary image data ID_2_2, and a second tertiary image data ID_2_3.

[0070] A biofluid analyzer can be configured to perform segmentation classification based on a first composite image, using a classification model or the like. For example, a biofluid analyzer can be configured to apply segmentation classification on one or more of the first primary image data ID_1_1, the first secondary image data ID_1_2, and the first tertiary image data ID_1_3. In other words, a biofluid analyzer can be configured to apply segmentation classification on one or more image segments of the first primary image data ID_1_1, the first secondary image data ID_1_2, and the first tertiary image data ID_1_3.

[0071] The classification model can be any suitable machine learning model that is well-suited for classification, or may include such a machine learning model. For example, the classification model may implement at least one machine learning model, such as at least one multilayer perceptron (MLP), at least one convolutional neural network (CNN), at least one recurrent neural network (RNN), at least one autoencoder, at least one transformer, and so on.

[0072] In one or more exemplary biofluid analyzers, the neural network may have a first hidden layer after the input layer. The input layer may be connected to the first hidden layer. The input layer may have the same number of nodes as the length of the feature vector, for example, the number of components. The first hidden layer may have at least three nodes, for example, at least 20 nodes. In one or more exemplary neural networks, the first hidden layer may have nodes in the range of 8 to 100, or nodes in the range of 100 to 1,000, for example, nodes in the range of 200 to 500, for example, about 300 nodes. In one or more exemplary neural networks, the neural network may have a second hidden layer after the first hidden layer. The second hidden layer may have at least five nodes, for example, at least 20 nodes. The second hidden layer may optionally have nodes in the range of 100 to 1,000, for example, nodes in the range of 8 to 100, or nodes in the range of 200 to 500, for example, about 300 nodes. In one or more exemplary neural networks, the neural network has fewer than 10 hidden layers, for example, fewer than 5 hidden layers. The output / output layer of the neural network can contain one or more output variables, for example, at least 5 output variables. In one or more exemplary neural networks, the number of output variables is in the range of 6 to 15.

[0073] A biofluid analyzer (for example, acting as a server) can be configured to train a classification model based on one or more of the first primary image data ID_1_1, the first secondary image data ID_1_2, and the first tertiary image data ID_1_3 (for example, based on one or more stored features).

[0074] In one or more exemplary biofluid analyzers, classifying cells in a prepared biofluid sample includes identifying the cell type of the cells. In one or more exemplary biofluid analyzers, classifying cells includes identifying cells (such as one or more cells) within a first cellular region. In other words, classifying cells includes identifying one or more groups of pixels representing cells within a cellular region. In other words, classifying first cells includes identifying one or more groups of pixels representing cells in one or more of the first primary image data ID_1_1, the first secondary image data ID_1_2, and the first tertiary image data ID_1_3.

[0075] The cell types disclosed herein may be considered, for example, leukocytes (WBCs), platelets (PLTs), red blood cells (RBCs), blood component clumps, cellular debris, and / or external particles, such as dust, precipitates, or residues from a container. The cell types disclosed herein may be considered, for example, mature cells, such as reticulocytes, lymphocytes, monocytes, segmented and band granulocytes, neutrophils, eosinophils, and / or basophils, and / or immature cells, such as normoblasts, erythroblasts, proerythroblasts, metamyelocytes, myelocytes, promyelocytes, myeloblasts, monoblasts, and / or lymphoblasts.

[0076] In one or more exemplary biofluid analyzers, classifying cells includes determining cellular features associated with cells, for example, cellular regions containing cells. In one or more exemplary biofluid analyzers, classifying cells includes determining cellular features associated with cellular regions based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. In other words, classifying cells includes determining cellular features associated with cells. Classifying cells may include determining multiple cellular features associated with cellular regions, including a first cellular feature, a second cellular feature, and so on. Cellular features may include one or more functions of lobe features, area features, contrast features, roundness features, particle size features, nuclear features, optical features, cytoplasmic features, membrane features, morphological features, and one or more of the aforementioned features. In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify cells based on the determination of cellular features, which are one or more functions of one or more of the following: lobe features, area features, contrast features, roundness features, particle size features, nuclear features, optical features, cytoplasmic features, membrane features, morphological features, and one or more of the aforementioned features. Based on one or more cellular features, cellular parameters, for example, a first cellular parameter, can be determined.

[0077] In one or more exemplary biofluid analyzers, providing cellular parameters for a first cell includes determining and providing cellular parameters for multiple cellular regions of a set of cellular regions based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. Providing cellular parameters for a first cell may include determining and providing cellular parameters for multiple cellular regions of a set of cellular regions based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2. In other words, a biofluid analyzer can be configured to determine cellular parameters for each of the cellular regions of a set of cellular regions.

[0078] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to determine the cellular representation of a prepared biofluid sample based on cellular parameters. In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to determine the cellular representation of a prepared biofluid sample based on multiple cellular parameters. Determining the cellular representation of a prepared biofluid sample may include determining the cellular representation of an image plane, e.g., a first image plane, and / or the cellular representation of image data. The cellular representation can be considered as the biofluid parameters of the prepared biofluid sample. Determining the cellular representation of a prepared biofluid sample may include determining the number of cellular regions containing the same or similar cellular parameters, cellular features, and / or cell types, e.g., one or more cell counts, e.g., white blood cell count and / or platelet count. Determining the cellular representation of a prepared biofluid sample may include determining the number of cellular regions having the same or similar cellular parameters, e.g., one cellular parameter. The cellular representation may include one or more cell concentrations, e.g., white blood cell concentration and / or platelet concentration. Cellular representation may include different types of leukocytes, such as basophils, eosinophils, lymphocytes, monocytes, neutrophils, and / or leukocyte counts or concentrations of plastic beads. The first blood parameter may include a 3-category WBC DIFF and / or a 5-category WBC DIFF. Determining cellular representation may include counting the number of cellular regions CR_k_i within one or more image planes IP_i that have the same or similar cellular parameters and / or cellular features.

[0079] In one or more exemplary biofluid analyzers, the provision of cellular parameters is based on cellular features that exhibit one or more functions of one or more of the aforementioned features, including lobe features, area features, contrast features, roundness features, particle size features, cell nuclear features, optical features, and so on. In one or more exemplary biofluid analyzers, cellular features include membrane features, geometric features, morphological features, and / or cell classification and / or type features. Membrane features may, for example, indicate information about the shape and / or texture of the cell membrane.

[0080] A lobe feature can be considered a feature that indicates information about one or more lobes of a cell, such as the cell in question. For example, a lobe feature may include information about the lobe (leaf) structure of a cell. A lobe feature may indicate cell segmentation, such as blob and / or leaf segmentation of a cell. A lobe feature may indicate one or more of the following: the number of cell nuclear lobes of a cell, the size of one or more lobes of a cell, the location of one or more lobes of a cell, and / or the size ratio between one or more lobes of a cell and that cell. A lobe feature included in a cell feature can be considered a lobe cell feature. For example, a lobe feature can be considered a feature that indicates information about one or more lobes of multiple cells in a prepared biological fluid sample. A lobe feature may indicate, for example, a cell containing one, two, or three lobes.

[0081] Area features can be considered features that indicate information about the area of ​​a cell, such as a cell in question. For example, area features may include information about the area size of a cell. Area features may indicate one or more of the following: pixel size, pixel area, cell area, leaf area, and cell nucleus area. Area features included in cell features can be considered area cell features. For example, area features can be considered features that indicate information about the area of ​​multiple cells in a prepared biological fluid sample. The cell area is 10 μm². 2 ~350μm 2 It can be within the range of

[0082] Contrast features can be considered features that indicate information about the contrast of a cell, such as the cell in question. For example, contrast features may include information about the contrast value of a cell. Contrast features may indicate the average pixel intensity of the cell nucleus and / or cytoplasm, as well as one or more color parameters. Contrast features included in cell features can be considered contrast cell features. For example, contrast features can be considered features that indicate information about the contrast of multiple cells in a prepared biological fluid sample. Contrast features can be considered the difference in light intensity between the image (e.g., within a cell region) and the adjacent background relative to the overall background intensity. The contrast of a cell can be in the range of 10% to 90%, for example, 50%.

[0083] Roundness features can be considered features that indicate information about the roundness and / or roundness of cells, such as the cell in question. For example, roundness features may include information about the roundness value and / or roundness value of a cell. Roundness features included in cell features can be considered roundness cell features. For example, roundness features can be considered features that indicate information about the roundness of multiple cells in a prepared biological fluid sample. The roundness parameter is given by the formula 4*Area(A)*Pi(π) / (÷)Perimeter^2(P 2 This can be determined by the following: The roundness parameter can be in the range of 0 to 1, where 1 is the roundness of a perfect disk. For example, a cell region can be characterized as a platelet when it satisfies the roundness criterion, for example, when the cell region exceeds the roundness threshold and / or when the cell region is within the roundness range. When detecting, identifying, classifying, and / or characterizing platelets, the roundness threshold can be set to, for example, 0.8.

[0084] Particle size features can be considered features that indicate information about the particle size and / or complexity of cells, such as the cell in question. For example, particle size features may include information about the particle size value of a cell. Particle size features may indicate one or more of the following: lateral scattering measurement information, internal cell complexity, and cell type. Particle size features included in cell features can be considered particle size cell features. For example, particle size features can be considered features that indicate information about the particle size of multiple cells in a prepared biological fluid sample.

[0085] Nuclear features can be considered features that indicate information about the cell nucleus of a cell, such as the cell in question. For example, nuclear features may include information about the size and / or type of the cell nucleus. Nuclear features may indicate the area of ​​the cell nucleus. Nuclear features included in cell features can be considered nuclear cell features. For example, nuclear features may be features that indicate information about the cell nuclei of multiple cells in a prepared biological fluid sample. The area of ​​the cell nucleus may be in the range of 0.1 μm to 5 μm, for example, in the range of 0.5 μm to 2 μm.

[0086] Optical features can be considered features that indicate information about cellular optical phenomena, such as optical phenomena within a cellular region containing a cell. For example, optical features may include information about bright spots, such as bright spot detection, and / or dark spots, such as dark spot detection. Optical features included in cellular features can be considered optical cellular features. For example, optical features can be considered features that indicate information about the optical phenomena of multiple cells in a prepared biological fluid sample.

[0087] Cellular features can be functions of different features derived from one or more of the following: lobe features, area features, contrast features, roundness features, granularity features, optical features, and nuclear features.

[0088] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify cells based on lobe features, area features, contrast features, roundness features, particle size features, cell nuclear features, optical features, and one or more functions of the aforementioned features. In other words, a biofluid analyzer can be configured to determine the cell type of a cell based on lobe features, area features, contrast features, roundness features, particle size features, cell nuclear features, and one or more functions of the aforementioned features.

[0089] In one or more exemplary biofluid analyzers, classifying a first cell involves using an autoencoder to determine an intermediate parameter, such as an intermediate representation. In other words, a classification model may include one or more intermediate layers for providing one or more intermediate parameters of a cell, such as an autoencoder.

[0090] In one or more exemplary biofluid analyzers, acquiring image data includes acquiring a second image data ID_2 associated with a second image plane IP_2. In one or more exemplary biofluid analyzers, obtaining a second image data ID_2 includes obtaining a second primary image data ID_2_1 of a second image plane IP_2 in the prepared biofluid sample, and associating the second primary image data ID_2_1 with a first incident light setting ILS_1; and obtaining a second secondary image data ID_2_2 of the second image plane IP_2 of the prepared biofluid sample, and associating the second secondary image data ID_2_2 with a second incident light setting ILS_2. In one or more exemplary biofluid analyzers, obtaining a second image data ID_2 includes obtaining a second tertiary image data ID_2_3 of a second image plane IP_2 in the prepared biofluid sample, and associating the second tertiary image data ID_2_3 with a third incident light setting ILS_3.

[0091] In one or more exemplary biofluid analyzers, a second image plane is associated with a second height, also represented by H_2, within the prepared biofluid sample. The second height to which the second image plane is associated can be the height, for example, on the z-axis relative to the bottom of the container / cuvette or camera / microscope when the second primary image data and / or second secondary image data, such as the second image, are acquired / captured. The second height H_2 may be different from the first height H_1.

[0092] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify cells in a prepared biofluid sample based on one or more of a second primary image data ID_2_1 and a second secondary image data ID_2_2.

[0093] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify cells in a prepared biofluid sample based on one or more of the following: first primary image data ID_1_1, first secondary image data ID_1_2, first tertiary image data ID_1_3, second primary image data ID_2_1, second secondary image data ID_2_2, and second tertiary image data ID_2_3.

[0094] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify cells in a prepared biofluid sample based on a second primary image data ID_2_1 and a first primary image data ID_1_2.

[0095] In one or more exemplary biofluid analyzers, determining the cell region set SCR_i is based on one or more of the second image data ID_2, for example, the second primary image data ID_2_1 and the second secondary image data ID_2_2.

[0096] A computer program product is disclosed comprising a non-temporary computer-readable medium having a computer program containing program instructions. The computer program is loadable into a data processing unit and is configured to perform the operation of one of the biofluid analyzers disclosed herein when executed by the data processing unit.

[0097] Furthermore, a method for classifying cells in a prepared biological fluid sample is disclosed. This method can be performed by a biological fluid analyzer disclosed herein. This method includes acquiring image data of one or more image planes in an image stack within the prepared biological fluid sample, the image data including first image data. Acquiring the first primary image data includes acquiring first primary image data of the first image plane. The first primary image data is associated with a first incident light setting having a first angular light distribution. Acquiring the first primary image data includes acquiring first secondary image data of the first image plane. The first secondary image data is associated with a second incident light setting having a second angular light distribution. This method includes classifying cells in the prepared biological fluid sample based on the first primary image data and the first secondary image data. This method includes providing cell parameters associated with the cells based on the cell classification.

[0098] Please understand that the descriptions of method-related features are also applicable to the corresponding features in biofluid analyzers and / or systems, and vice versa. Figure 1 schematically shows an exemplary biofluid analyzer BA, which comprises memory, an interface, and one or more processors. The biofluid analyzer BA is configured to acquire image data IDs of one or more image planes of an image stack of a prepared biofluid sample using an image module IM, etc., and the image data IDs include a first image data ID_1 associated with a first image plane IP_1. The biofluid analyzer BA is configured to acquire a first primary image data ID_1_1 of the first image plane IP_1 using an image module IM, etc. The biofluid analyzer BA is configured to acquire a first secondary image data ID_1_2 of the first image plane IP_1 using an image module IM, etc. The biofluid analyzer BA can be configured to determine a cell region set SCR_i based on the image data IDs using an image module IM, etc. Optionally, the biofluid analyzer can be configured to transmit, for example, image data included in the dataset, such as a first image data ID_1 (such as a first primary image data and / or a first secondary image data) and / or a cell region set SCR_i from the image module IM to the feature extractor module FEM (302A). The feature extractor module FEM can be configured to extract one or more features from the image data ID, such as a first image data ID_1 and / or a cell region set SCR_i. For example, the feature extractor module FEM can be configured to extract one or more cell features from the image data ID, such as a first image data ID_1 and / or a cell region set SCR_i. For example, the feature extractor module FEM can be configured to extract one or more cell features from the first primary image data and / or a first secondary image data. Optionally, the biofluid analyzer can be configured to transmit the extracted one or more features from the feature extractor module FEM to the classification circuit module CCM (302B).

[0099] Optionally, the biofluid analyzer can be configured to directly transmit image data IDs included in the dataset, for example, the first image data ID_1 and / or the cell region set SCR_i, to the classification circuit module CCM (302).

[0100] The biofluid analyzer BA is configured to classify cells in a prepared biofluid sample based on a first primary image data ID_1 and a first secondary image data ID_1_2, using a classification circuit module CCM or the like, and to provide cell parameters associated with the cells (308). In other words, the biofluid analyzer BA can be configured to output cell parameters associated with cells to, for example, the user, a database, and / or a server device, using a classification circuit module CCM or the like (308).

[0101] In one or more exemplary biofluid analyzers, acquiring first image data includes acquiring first tertiary image data ID_1_3 of a first image plane IP_1 using an image module IM, etc. In one or more exemplary biofluid analyzers, the first tertiary image data ID_1_3 is associated with a third incident light setting ILS_3 having a third angular light distribution ALD_3. In one or more exemplary biofluid analyzers, classifying cells in a prepared biofluid sample is based on the first tertiary image data ID_1_3.

[0102] In one or more exemplary biofluid analyzers, determining a cell region set SCR_i based on an image data ID includes determining a first cell region set SCR_1 belonging to a first image plane IP_1.

[0103] In one or more exemplary biofluid analyzers, the biofluid analyzer may be configured to classify cells such as a first cell CE_1 based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2, using a classification circuit module CCM, etc.

[0104] In one or more exemplary biofluid analyzers, classifying cell CEs involves applying a classification model to one or more of the first primary image data ID_1_1, the first secondary image data ID_1_2, and the first tertiary image data ID_1_3 using a classification circuit module CCM, etc. In one or more exemplary biofluid analyzers, classifying cell CEs involves applying a classification model to one or more of the first primary image data ID_1_1, the first secondary image data ID_1_2, the first tertiary image data ID_1_3, the second primary image data ID_2_1, the second secondary image data ID_2_2, and the second tertiary image data ID_2_3 using a classification circuit module CCM, etc.

[0105] In one or more exemplary biofluid analyzers, classifying cells in a prepared biofluid sample involves identifying the cell type of the cells using a classification circuit module such as a CCM.

[0106] In one or more exemplary biofluid analyzers, acquiring image data includes obtaining a second image data ID_2 associated with a second image plane IP_2 using an image module IM, etc.

[0107] In one or more exemplary biofluid analyzers, obtaining a second image data ID_2 includes one or more of the following: obtaining a second primary image data ID_2_1 of a second image plane IP_2 in a prepared biofluid sample using an image module IM, etc., and associating the second primary image data ID_2_1 with a first incident light setting ILS_1; and obtaining a second secondary image data ID_2_2 of the second image plane IP_2 of the prepared biofluid sample using an image module IM, etc., and associating the second secondary image data ID_2_2 with a second incident light setting ILS_2. In one or more exemplary biofluid analyzers, obtaining a second image data ID_2 includes obtaining a second tertiary image data ID_2_3 of a second image plane IP_2 in a prepared biofluid sample using an image module IM, etc., and associating the second tertiary image data ID_2_3 with a third incident light setting ILS_3.

[0108] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify cells in a prepared biofluid sample based on one or more of a second primary image data ID_2_1 and a second secondary image data ID_2_2, using a classification circuit module CCM, for example.

[0109] In one or more exemplary biofluid analyzers, determining the cell region set SCR_i is based on one or more of the second image data ID_2, for example, the second primary image data ID_2_1 and the second secondary image data ID_2_2.

[0110] In one or more exemplary biofluid analyzers, providing cellular parameters for a first cell includes determining cellular parameters for multiple cellular regions of a set of cellular regions based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2, using a classification circuit module CCM, etc., and providing multiple cellular parameters.

[0111] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to determine the cellular representation of a prepared biofluid sample based on cellular parameters, using a classification circuit module such as a CCM. In one or more exemplary biofluid analyzers, the biofluid analyzer BA may be configured to output the cellular representation to, for example, the user, a database, and / or a server device, using a classification circuit module such as a CCM (308).

[0112] In one or more exemplary biofluid analyzers, the provision of cellular parameters is based on cellular features that exhibit one or more functions of lobe features, area features, contrast features, roundness features, particle size features, cell nuclear features, optical features, and one or more of the aforementioned features.

[0113] In one or more exemplary biofluid analyzers, the first image data ID_1 includes a first composite image data based on, for example, a first tertiary image data ID_1_3, a second primary image data ID_2_1, a second secondary image data ID_2_2, and a second tertiary image data ID_2_3, based on the first primary image data ID_1_1 and / or the first secondary image data ID_1_2.

[0114] Figure 2 schematically shows an exemplary system 200, which comprises a microscope 20, an image acquisition device (not shown, but implemented / integrated with the microscope, for example), a prepared biological fluid sample in a container 22 (e.g., a cuvette, cavity), an exemplary imaging system 1 (e.g., imaging system 1 in Figure 3), and a biological fluid analyzer 10. Optionally, system 200 includes an aperture device (e.g., provided in imaging system 1) configured to apply an aperture and allow light from a first lens assembly to pass through the aperture and indirectly define probe light.

[0115] The biofluid analyzer 10 is an exemplary biofluid analyzer according to this disclosure. The biofluid analyzer 10 comprises a memory 10A, an interface 10B, and one or more processors such as a processor 10C. The biofluid analyzer 10 is configured to acquire image data IDs of one or more image planes of an image stack in a prepared biofluid sample from an image acquisition device via the interface 10B, etc. (14). The image data IDs include a first image data ID_1 associated with a first image plane IP_1. Optionally, the biofluid analyzer 10 may be configured to acquire image data from a global network, such as the Internet or a telecommunications network. Optionally, the biofluid analyzer 10 may be configured to transmit information (such as cell parameters and / or cell representations) to a microscope 20 (14). For example, the biofluid analyzer 10 may be configured to acquire image data from a server device (not shown) via a network. The prepared biological fluid sample can be placed / positioned within a container 22, such as a cuvette, while an image data ID, e.g., multiple images of the prepared biological fluid sample, e.g., a first image I_1, is acquired. The height to which the image plane is associated can be, for example, the height on the z-axis relative to the bottom of the container 22 when the image is acquired / captured. The first image data can be associated with a first image plane IP_1, and the first image plane IP_1 can be associated with a first height H_1 within the prepared biological fluid sample. The image plane to which multiple images can extend can be a two-dimensional plane, e.g., the xy-plane relative to the z-axis. Thus, the image data ID can include multiple images associated with an image plane, each image plane separated by a distance Δz from the next acquired / captured image plane and / or previously acquired / captured image plane, where Δz is a step increment for each acquired / captured image. In the example in Figure 2, 16 image planes are represented, including the first image plane IP_1, the first distal image plane DIP_1, and the first proximal image plane PIP_1. The number of images and image planes can be increased to include, for example, at least 30, at least 40, or at least 100.The image data ID may include multiple images of the prepared biological fluid sample, each image being associated with an image plane equidistant from the next acquired / obtained image plane and / or the previously acquired / obtained image plane. In other words, the image data ID may include a 3D image stack, such as a stack of images where each image in the image stack is associated with an image plane having a different associated height along the z-axis of the prepared biological fluid sample. The image data ID may include multiple images of the central portion 24 of the biological fluid sample. In other words, the image data ID may include multiple acquired / obtained images of the prepared biological fluid sample representing the area or volume of the prepared biological fluid sample located away from the rim of the container 22 containing the prepared biological fluid sample. Alternatively or additionally, the image data ID may include multiple acquired / obtained images of the prepared biological fluid sample representing the entire area or volume of the container 22, for example, the entire width and / or entire height of the container 22, including, for example, the window of the container 22. The biological fluid sample may include multiple cells, for example, cell CE. For illustrative purposes, the container 22 and cells are enlarged and therefore not proportional to their actual size. In the example shown in Figure 2, cell CE represents leukocytes (WBCs). Smaller cells, such as cell CE_10, can be platelets, for example.

[0116] Each image data ID may contain multiple representations. Multiple representations may include multiple particles, such as cells, such as white blood cells (WBCs), platelets, red blood cells (RBCs), and / or external particles, such as dust or residue from a container. Obtaining a first image data ID_1 (14) includes obtaining a first primary image data ID_1_1 (14) of a first image plane IP_1. The first primary image data ID_1_1 is associated with a first incident light setting ILS_1. The first incident light setting ILS_1 may optionally have a first angular light distribution. Obtaining a first image data ID_1 (14) includes obtaining a first secondary image data ID_1_2 (14) of a first image plane IP_1. The first secondary image data ID_1_2 is associated with a second incident light setting ILS_2. The second incident light setting ILS_2 may optionally have a second angular light distribution.

[0117] The biofluid analyzer 10 is configured to classify cells in a prepared biofluid sample based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2, using a processor 10C or the like, and to provide cell parameters CP associated with the cells. In one or more exemplary systems and / or biofluid analyzers, the biofluid analyzer 10 is configured to output cell parameters CP and / or cell representations to, for example, a user U, a database, and / or a server device, using a processor 10C or the like and / or via an interface 10B (12).

[0118] In one or more exemplary biofluid analyzers, acquiring image data includes acquiring a second image data ID_2 associated with a second image plane IP_2. In one or more exemplary biofluid analyzers, obtaining a second image data ID_2 includes obtaining a second primary image data ID_2_1 of a second image plane IP_2 in the prepared biofluid sample, and associating the second primary image data ID_2_1 with a first incident light setting ILS_1; and obtaining a second secondary image data ID_2_2 of the second image plane IP_2 of the prepared biofluid sample, and associating the second secondary image data ID_2_2 with a second incident light setting ILS_2. In one or more exemplary biofluid analyzers, obtaining a second image data ID_2 includes obtaining a second tertiary image data ID_2_3 of a second image plane IP_2 in the prepared biofluid sample, and associating the second tertiary image data ID_2_3 with a third incident light setting ILS_3. The second image plane IP_2 may be a proximal image plane PIP, such as the first proximal image plane, and / or a distal image plane DIP, such as the first distal image plane DIP_1. In one or more exemplary biofluid analyzers, the second image plane IP_2 is associated with a second height, also represented by H_2, in the prepared biofluid sample. The second height H_2 to which the second image plane IP_2 is associated may be the height, for example, on the z-axis relative to the bottom of the container / cuvette or camera / microscope when the second primary image data and / or second secondary image data, such as the second image, are acquired / captured. The second height H_2 may be different from the first height H_1.

[0119] In one or more exemplary biofluid analyzers, the biofluid analyzer is configured to classify cells in a prepared biofluid sample based on one or more of a second primary image data ID_2_1 and a second secondary image data ID_2_2, using a processor 10C, etc.

[0120] In one or more exemplary systems and / or biofluid analyzers, a first proximal image plane PIP_1 is associated with a first proximal height PH_1 in the prepared biofluid sample, where the first proximal height PH_1 is different from a first height H_1.

[0121] The first distal distance, also represented by DD_1, between the first image plane IP_1 and the first distal image plane DIP_1, and the first proximal distance, also represented by PD_1, between the first image plane IP_1 and the first proximal image plane PIP_1, are in the range of 1 μm to 75 μm. In Figure 2, the first distal distance DD_1 is greater than the first proximal distance PD_1.

[0122] The biofluid analyzer 10 can be configured to perform any of the methods disclosed in Figure 4. The biofluid analyzer 10, for example, the processor 10C, is optionally configured to perform any of the operations disclosed in Figure 4 (such as one or more of S102C, S102D, S102D1, S102D2, S102D3, S104A, S108A, S108B, S108C, S108D, S110A, S112). The operations of the biofluid analyzer can be carried out in the form of executable logical routines (e.g., instruction lines, software programs, etc.) stored in a non-temporary computer-readable medium (e.g., memory 10A) and executed by the processor 10C.

[0123] Furthermore, the operation of the biofluid analyzer 10 can be considered as a method configured for the biofluid analyzer 10 to perform. While the described functions and operations can be implemented in software, such functions can also be performed through dedicated hardware or firmware, or any combination of hardware, firmware, and / or software.

[0124] Figure 3 shows an exemplary imaging system 1. Imaging system 1 can be an example of an imaging system used to acquire image data, for example, a first image data ID_1, for example, a first primary image data ID_1_1 disclosed herein, a first secondary image data ID_1_2, a first tertiary image data ID_1_3, a second primary image data ID_2_1, a second secondary image data ID_2_2, and / or a second tertiary image data ID_2_3. Imaging system 1 comprises a light source assembly 3 and a first lens assembly 4. The optical axis 2 of imaging system 1 extends across the light source assembly 3 and the first lens assembly 4. In the embodiment of Figure 3, the first lens assembly 4 comprises a first lens 41, a second lens 42, and an optional third lens 43. Lenses 41, 42, and 43 are configured to direct the light emitted by the light source assembly 3 toward a convergence point located downstream of the first lens assembly 4.

[0125] System 1 in Figure 3 may include an aperture device 5 configured to apply an aperture, allowing light from the first lens assembly 4 to pass through the aperture. In the exemplary biofluid analyzer in Figure 3, the aperture device 5 extends along the back focal plane of the first lens assembly 4. The convergence point of the light induced by the first lens assembly 4 is located at the back focal plane of the first lens assembly 4. Therefore, the aperture applied can be selectively applied to include one or more of the convergence points.

[0126] In the embodiment shown in Figure 3, the light source assembly comprises one or more of the first light source 31, the second light source 32, and the third light source 33. The first light source 31 is positioned on the optical axis 2 of the imaging system 1. The beams of light emitted by each of the light sources 31, 32, and 33 converge at a convergence point on the back focal plane of the first lens assembly 4. In the configuration shown in Figure 3, the applied aperture in the aperture device allows the light emitted by the three light sources 31, 32, and 33 to pass through the applied aperture.

[0127] Downstream of the aperture device 5, the imaging device 1 of system 1 in Figure 3 includes a second lens assembly 6. In system 1, the second lens assembly includes a first lens 62 and / or a second lens 62. The second lens assembly 6 is configured to guide light that has passed through the applied aperture in the aperture device 5 and to focus that light onto the back focal plane of the second lens assembly 6. Figure 3 shows that each convergence point on the back focal plane of the first lens assembly 4 produces a different angle of incidence on the back focal plane of the second lens assembly 6. Thus, the angle of incidence of the light guided onto the back focal plane of the second lens assembly 6 by the second lens assembly 6 can be customized by applying the aperture of the aperture device 5.

[0128] In the embodiment of Figure 3, the probe volume 7 is defined along the back focal plane of the second lens assembly 6. The probe volume 7 in Figure 3 receives light with three different angles of incidence. The light received by the probe volume 7 is called the probe light. The light that passes through the applied aperture is guided by the second lens assembly 6 to define the probe light, so the light that passes through the applied aperture indirectly defines the probe light. In the embodiment of Figure 3, the probe volume 7 is optionally received by a multipurpose cuvette (not shown). In such an example, the biofluid analyzer 1 can be configured as a multipurpose device with the necessary fluid systems and mechanisms (not shown) for performing multiple measurements. Such exemplary biofluid analyzer 1 may further comprise a solution pack containing one or more solutions (not shown), and the exemplary biofluid analyzer 1 is configured, by means of its fluid system and mechanisms, to manage and release the solution pack so that the prepared body fluid sample is automatically, at least partially, prepared after aspiration, and to control the fluid system so that a cleaning program for at least the multipurpose cuvette is performed before and / or after biofluid analysis.

[0129] One or more incidence angles of the probe light can be customized by the aperture device 5. To achieve such customization, system 1 includes a controller 8 configured to control the aperture device 5.

[0130] System 1 includes a controller 8 configured to control a portion of the imaging system 1. For example, the controller 8 may be configured to control the aperture device 5 via one or more aperture control signals to the aperture device 5.

[0131] In Figure 3, the aperture device 5 is controlled by the controller 8 according to an aperture configuration in which the applied aperture has a second aperture configuration. In other words, the controller transmits a second aperture control signal to the aperture device 5. As described above, the second aperture configuration allows light converging at three convergence points on the rear focal plane of the first lens assembly 4 to pass through the applied aperture.

[0132] In this embodiment, the aperture device 5 extends along the rear focal plane of the first lens assembly 4, so that the aperture device 5 can perform precise filtering of light induced by the first lens assembly 4 by selectively applying the aperture to include one or more convergence points located on the rear focal plane of the first lens assembly 4. However, the aperture device 5 can also extend along a plane other than the rear focal plane of the first lens assembly 4, and still perform suitable filtering of light induced by the first lens assembly 4.

[0133] Figure 4 shows a flowchart of an exemplary method. A method 100 for classifying cells in a prepared biological fluid sample is shown. Method 100 can be performed using a biological fluid analyzer disclosed herein, for example, the biological fluid analyzer BA in Figure 1 and / or the biological fluid analyzer 10 in Figure 2. Method 100 includes step S102 of acquiring image data which is also represented by the IDs of one or more image planes of an image stack in the prepared biological fluid sample. The image data ID includes a first image data ID_1 associated with a first image plane IP_1.

[0134] Step S102, which obtains the first image data ID_1, includes step S102A, which obtains the first primary image data ID_1_1 of the first image plane IP_1. The first primary image data ID_1_1 is associated with a first incident light setting having a first angular light distribution. Step S102, which obtains the first image data ID_1, includes step S102B, which obtains the first secondary image data ID_1_2 of the first image plane IP_1. The first secondary image data ID_1_2 is associated with a second incident light setting having a second angular light distribution.

[0135] Method 100 includes step S108 of classifying cells CE in a prepared biological fluid sample based on a first primary image data ID_1_1 and / or a first secondary image data ID_1_2.

[0136] Method 100 includes step S110, which provides cell parameters CP associated with cell CE based on the classification of cell CE S108. In one or more exemplary methods, step S102 of obtaining a first image data ID_1 includes step S102C of obtaining a first tertiary image data ID_1_3 of a first image plane IP_1, and the first tertiary image data ID_1_2 is associated with a third incident light setting having a third angular light distribution.

[0137] In one or more exemplary methods, step S108 for classifying cell CE is based on first tertiary image data ID_1_3. In one or more exemplary methods, method 100 includes step S104 of determining a cell region set SCR_i based on an image data ID.

[0138] In one or more exemplary methods, step S104 for determining a cell region set SCR_i includes step S104A for determining a cell region set SCR_i based on a first image data ID_1, such as a first cell region set SCR_1 belonging to a first image plane IP_1.

[0139] In one or more exemplary methods, step S108 for classifying cells CE includes classifying cells within a first cell region of a set of cell regions (S108A) and providing a first cell parameter CP_1 indicating the cell type of the cells.

[0140] In one or more exemplary methods, step S108 for classifying cell CE includes step S108B, which applies a classification model to one or more of the first primary image data ID_1_1, the first secondary image data ID_1_2, and the first tertiary image data ID_1_3.

[0141] In one or more exemplary methods, step S108 for classifying cell CE includes step S108C for identifying the cell type of cell CE. In one or more exemplary methods, step S102 for obtaining an image data ID includes step S102D for obtaining a second image data ID_2 associated with a second image plane IP_2. In one or more exemplary methods, step S102D for obtaining a second image data ID_2 includes step S102D1 for obtaining a second primary image data ID_2_1 of the second image plane IP_2 in the prepared biological fluid sample, where the second primary image data ID_2_1 is associated with a first incident light setting. In one or more exemplary methods, step S102D for obtaining a second image data ID_2 includes step S102D2 for obtaining a second secondary image data ID_2_2 of the second image plane IP_2 in the prepared biological fluid sample, where the second secondary image data ID_2_2 is associated with a second incident light setting. In one or more exemplary methods, step S102D of acquiring a second image data ID_2 includes step S102D3 of acquiring a second tertiary image data ID_2_3 of a second image plane IP_2 in a prepared biological fluid sample, wherein the second tertiary image data ID_2_3 is associated with a tertiary incident light setting.

[0142] In one or more exemplary methods, step S108 for classifying cells CE includes step S108D for classifying cells in a prepared biological fluid sample based on one or more of a second primary image data ID_2_1 and a second secondary image data ID_2_2.

[0143] In one or more exemplary methods, step S104, which determines the cell region set SCR_i, is based on a second image data ID_2. In one or more exemplary methods, step S110, which provides cell parameters CP, includes determining cell parameters CP for multiple cell regions of a cell region set SCR_i based on a first primary image data ID_1_1 and a first secondary image data ID_1_2 (S110A), and providing a plurality of cell parameters CP_k_1.

[0144] In one or more exemplary methods, method 100 includes step S112 of determining the cellular expression CP of a prepared biological fluid sample based on cellular parameters, for example, based on a plurality of first cellular parameters CP_k_1.

[0145] In one or more exemplary methods, step S110, which provides cell parameters CP, is based on cell features that exhibit one or more functions of lobe features, area features, contrast features, roundness features, granularity features, cell nucleus features, optical features, and one or more of the aforementioned features.

[0146] Figures 5–9 show exemplary images of cells (e.g., cell regions) acquired in different image planes (along the X-axis) and different incident light settings (along the Y-axis), exemplifying methods and / or biofluid analyzers according to this disclosure in which the techniques disclosed herein are performed and / or used. Figures 5–9 each show a series of seven images, e.g., image tiles, for each of 15 image planes (IP_1–IP_15), where these image tiles include cell regions acquired in 15 different image planes and 7 different incident light settings. The fourth tile T_4 in Figures 5–9 can be considered as the first primary image data ID_1_1 of the first image plane IP_1 acquired by the first incident light setting ILS_1 having the first angular light distribution ALD_1. The first tile T_1 in Figures 5 to 9 can be considered as the first secondary image data ID_1_2 of the first image plane IP_1 acquired by the second incident light setting ILS_2 having the second angular light distribution ALD_2. The seventh tile T_7 in Figures 5 to 9 can be considered as the first tertiary image data ID_1_3 of the first image plane IP_1 acquired by the third incident light setting ILS_3 having the third angular light distribution ALD_3.

[0147] The 11th tile T_11 in Figures 5 to 9 can be considered as the second primary image data ID_2_1 of the second image plane IP_2 acquired by the first incident light setting ILS_1 having the first angular light distribution ALD_1. The 8th tile T_8 in Figures 5 to 9 can be considered as the second secondary image data ID_2_2 of the second image plane IP_2 acquired by the second incident light setting ILS_2 having the second angular light distribution ALD_2. The 14th tile T_14 in Figures 5 to 9 can be considered as the second tertiary image data ID_2_3 of the second image plane IP_1 acquired by the third incident light setting ILS_3 having the third angular light distribution ALD_3.

[0148] Figure 5 shows a series of seven images, e.g., image tiles, for each image plane containing cellular regions within 15 different image planes with interplanar distances of approximately 5 μm. The cells observed in Figure 5 are classified as eosinophils.

[0149] Figure 6 shows a series of seven images for each image plane in an image stack, e.g., an image tile, where the seven images contain cellular regions in 15 different image planes with inter-plane distances of approximately 5 μm. The cells observed in Figure 6 are classified as lymphocytes.

[0150] Figure 7 shows a series of seven images for each image plane in an image stack, e.g., an image tile, where the seven images contain cellular regions in 15 different image planes with inter-plane distances of approximately 5 μm. The cells observed in Figure 7 are classified as monocytes.

[0151] Figure 8 shows a series of seven images for each image plane in an image stack, e.g., an image tile, where the seven images contain cellular regions in 15 different image planes with inter-plane distances of approximately 5 μm. The cells observed in Figure 8 are classified as neutrophils.

[0152] Figure 9 shows a series of seven images for each image plane in an image stack, e.g., an image tile, where the seven images contain cellular regions in 15 different image planes with inter-plane distances of approximately 5 μm. The cells observed in Figure 9 are classified as platelets.

[0153] The use of terms such as “first,” “second,” “third,” and “fourth,” “primary,” “secondary,” and “tertiary” does not suggest any particular order and is included to identify individual elements. Furthermore, the use of terms such as “first,” “second,” “third,” and “fourth,” “primary,” “secondary,” and “tertiary” does not indicate any order or importance; rather, terms such as “first,” “second,” “third,” and “fourth,” “primary,” “secondary,” and “tertiary” are used to distinguish one element from another. It should be noted that the words “first,” “second,” “third,” and “fourth,” “primary,” “secondary,” and “tertiary” are used throughout this specification for labeling purposes only and are not intended to indicate any particular spatial or temporal order.

[0154] Memory can be one or more of the following: buffers, flash memory, hard drives, removable media, volatile memory, non-volatile memory, random access memory (RAM), or other suitable devices. In a typical configuration, memory may include non-volatile memory for long-term data storage and volatile memory that functions as system memory for the processor. Memory can exchange data with the processor via a data bus. Memory can be considered a non-temporary computer-readable medium.

[0155] The memory can be configured to store information (such as cell parameters, image data, cell representation, and / or information indicating cell characteristics) in a portion of the memory. Furthermore, the labeling of the first element does not imply the existence of the second element, and vice versa.

[0156] Figures 1-9 will be understood to include several modules or operations shown by solid lines and several modules or operations shown by dashed lines. The modules or operations included by solid lines are those included in the broadest exemplary embodiment. The modules or operations included by dashed lines are exemplary embodiments that can be included in the exemplary embodiments shown by solid lines, or that can be part of the exemplary embodiments shown by solid lines, or that can be incorporated in addition to the modules or operations of the exemplary embodiments shown by solid lines. It should be understood that these operations do not need to be performed in the order presented. Furthermore, it should be understood that not all of these operations need to be performed. The exemplary operations can be performed in any order and in any combination.

[0157] Please note that the words "comprising" do not necessarily exclude the existence of elements or steps other than those listed. Please note that the word "a" or "an" preceding an element does not exclude the existence of multiple such elements.

[0158] No reference numeral is intended to limit the scope of the claims, and it should be further noted that exemplary embodiments can be implemented at least partially by both hardware and software, and that the same hardware item may represent several “means,” “units,” or “devices.”

[0159] In this specification, expressions of degree used herein, such as “approximately,” “about,” “generally,” and “substantially,” represent values, quantities, or characteristics that are still close to the stated value, quantity, or characteristic that still perform the desired function or achieve the desired result. For example, the terms “approximately,” “about,” “generally,” and “substantially” may refer to quantities within the range of 10% or less, 5% or less, 1% or less, 0.1% or less, and 0.01% or less of the stated quantity. If the stated quantity is 0 (e.g., none, not having), the above ranges may be specific ranges rather than specific percentage ranges of that value. For example, within the range of 10% by weight / volume or less, 5% by weight / volume or less, 1% by weight / volume or less, 0.1% by weight / volume or less, and 0.01% by weight / volume or less of the stated quantity.

[0160] The various exemplary methods, devices, and systems described herein are described in a general context of method step processes, and can be implemented in one aspect by computer program products, can be implemented on computer-readable media containing computer-executable instructions such as program code, and can be executed by computers in a network environment. Computer-readable media can include, but are not limited to, removable and non-removable storage devices, including read-only memory (ROM), random access memory (RAM), compact discs (CDs), digital versatile discs (DVDs), etc. In general, program modules can include routines, programs, objects, components, data structures, etc., that perform a specified task or implement specific abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of program code for performing steps of the methods disclosed herein. A particular sequence of such executable instructions or associated data structures represents an example of corresponding behavior for implementing the functionality described in such steps or processes.

[0161] While the features have been illustrated and described, it will be apparent to those skilled in the art that these are not intended to limit the claimed invention, and that various changes and modifications can be made without departing from the spirit and scope of the claimed invention. Accordingly, this specification and the drawings should be interpreted as illustrative rather than restrictive. The claimed invention is intended to encompass all alternatives, modifications, and equivalents.

[0162] Examples of the methods and products (biofluid analyzers and systems) described herein are listed below. Item 1. A biomedical fluid analyzer comprising memory, an interface, and one or more processors, The process involves acquiring image data of one or more image planes in an image stack within a prepared biological fluid sample, wherein the image data includes first image data associated with a first image plane, and acquiring the first image data is... A first primary image data is acquired from a first image plane, and the first primary image data is associated with a first incident light setting having a first angular light distribution, and Acquisition includes acquiring a first secondary image data of a first image plane, and associating the first secondary image data with a second incident light setting having a second angular light distribution. A biofluid analyzer configured to classify cells in a prepared biofluid sample and provide cell-related cellular parameters based on a first primary image data and a first secondary image data.

[0163] Item 2. A biofluid analyzer according to Item 1, wherein acquiring first image data includes acquiring first tertiary image data of a first image plane, the first tertiary image data being associated with a third incident light setting having a third angular light distribution, and classifying cells in a prepared biofluid sample based on the first tertiary image data.

[0164] Item 3. A biofluid analyzer as described in any of the preceding items, wherein the biofluid analyzer is configured to determine a set of cell regions based on image data. Item 4. The biofluid analyzer described in Item 3, which determines the cell region cluster based on the first image data.

[0165] Item 5. A biofluid analyzer according to item 3 or 4, wherein determining a set of cell regions includes determining, based on first image data, a first set of cell regions belonging to a first image plane.

[0166] Item 6. A biofluid analyzer according to any one of items 3 to 5, comprising classifying cells in a prepared biofluid sample, classifying cells within a first cellular region of a cellular region set, and providing a first cellular parameter indicating the cellular type of the cells.

[0167] Item 7. A biofluid analyzer according to any of the preceding items, wherein classifying cells in a prepared biofluid sample involves applying a classification model to one or more of the following: first primary image data, first secondary image data, and first tertiary image data.

[0168] Item 8. A biofluid analyzer as described in any of the preceding items, which includes classifying cells in a prepared biofluid sample and identifying the cell type of the cells. Item 9. A biofluid analyzer according to any of the preceding items, wherein the first incident light setting includes one or more of the lens assembly setting, aperture setting, angle setting, and light source setting, and the first incident light setting is configured to provide incident light containing a first light component in which the first light angle is greater than the first angle.

[0169] Item 10. A biofluid analyzer as described in any of the preceding items, wherein the first incident light setting includes an aperture setting that indicates a first aperture size used to acquire first primary image data. Item 11. A biofluid analyzer according to any of the preceding items, wherein the second incident light setting includes one or more of the lens assembly setting, aperture setting, angle setting, and light source setting, and the second incident light setting is configured to provide incident light containing a second light component where the second light angle is greater than the second angle.

[0170] Item 12. A biofluid analyzer according to any of the preceding items, wherein the second incident light setting is configured to provide an incident light angle that does not overlap with the incident light angle provided by the first incident light setting. Item 13. A biofluid analyzer as described in any of the preceding items, wherein the second incident light setting includes an aperture setting that indicates a second aperture size used to acquire the first secondary image data.

[0171] Item 14. A biofluid analyzer according to any of items 10 to 13, wherein the first aperture size is different from the second aperture size and / or the shape of the first aperture is different from the shape of the second aperture.

[0172] Item 15. A biofluid analyzer as described in any of the preceding items, wherein the first incident light setting and / or the second incident light setting include an aperture setting that indicates a numerical aperture in the range of 0 to 0.7. Item 16. Acquiring image data includes acquiring second image data associated with a second image plane, and acquiring second image data is - Acquire a second primary image data of a second image plane within the prepared biological fluid sample, and associate the second primary image data with the first incident light setting, and - The biofluid analyzer acquires a second secondary image data of a second image plane of a prepared biological fluid sample, and the second secondary image data is acquired by a second incident light setting, one or more of the above, - A biofluid analyzer as described in any of the preceding items, configured to classify cells in a prepared biofluid sample based on one or more of a second primary image data and a second secondary image data.

[0173] Item 17. A biofluid analyzer described in Item 16, which is subordinate to Item 3, that determines the set of cell regions based on the second image data. Item 18. A biofluid analyzer according to any of the preceding items, which provides cell parameters by determining cell parameters for multiple cell regions of a set of cell regions based on a first primary image data and a first secondary image data, and providing multiple cell parameters.

[0174] Item 19. A biofluid analyzer as described in any of the preceding items, configured to determine the cellular expression of a prepared biofluid sample based on cellular parameters. Item 20. A biofluid analyzer according to any of the above items, wherein the provision of cellular parameters is based on cellular features that exhibit one or more functions of one or more of the following: lobe features, area features, contrast features, roundness features, particle size features, nuclear features, optical features, and one or more of the aforementioned features.

[0175] Item 21. A biofluid analyzer as described in any of the preceding items, wherein the first image data includes a first composite image data based on a first primary image data and / or a first secondary image data.

[0176] Item 22. A computer program product comprising a non-temporary computer-readable medium having a computer program including program instructions, wherein the computer program is loadable into a data processing unit and is configured to perform any of the operations described in items 1 to 21 when executed by the data processing unit.

[0177] Item 23. A method for classifying cells in a prepared biological fluid sample, - A step of acquiring image data of one or more image planes of an image stack in a prepared biological fluid sample, wherein the image data includes first image data associated with a first image plane, and the step of acquiring the first image data is - Acquire a first primary image data of a first image plane, and associate the first primary image data with a first incident light setting having a first angular light distribution, and - The acquisition step includes acquiring a first secondary image data of a first image plane, wherein the first secondary image data is acquired by a second incident light setting having a second angular light distribution, - A step of classifying cells in a prepared biological fluid sample based on a first primary image data and a first secondary image data, - A method comprising the step of providing cellular parameters associated with a cell based on the classification of the cell. [Explanation of Symbols]

[0178] U user 200 Systems 1. Imaging System 12 outputs 14. Transmission / Acquisition 10. Biomedical fluid analyzer 10A Memory 10B Interface 10C Processor 20 Microscopes 22 containers / cuvettes 24 Center part 302, 302A, 302B transmission 308 Output BA Biomedical Fluid Analyzer PIP_i Proximal Image Plane PIP_1 First proximal image plane IP_i Image Plane IP_1 First image plane IP_2 Second image plane DIP_i Distal image plane DIP_1 First distal image plane PH_i Proximal height PH_1 First proximal height H_i Height H_1 First height H_2 Second height DH_i Distal height DH_1 First distal height PD_i Proximal distance DD_i Distal distance PD_1 First proximal distance DD_1 First distal distance CE cells Δz step increment zz axis ID image data ID_1 First primary image data I_i Image IM Image Module FEM Feature Extraction Module CCM Classification Circuit Page PI_i Proximal image DI_i Distal image SCR_i cell region set CR_k_i cell area CP_k_i cell parameters Number of cell regions C_i ID_1_1 First primary image data ID_1_2 First secondary image data ID_1_2 First tertiary image data ID_2_1 Second primary image data ID_2_2 Second secondary image data ID_2_3 Second tertiary image data ILS incident light settings ILS_1 First Incident Light Setting ILS_2 Second Incident Light Setting ILS_3 Third Incident Light Setting ALD angular light distribution ALD_1 First angle light distribution ALD_2 Second Angular Light Distribution ALD_3 Third Angle Light Distribution A angle A_1 First angle A_2 Second angle AS Aperture Size AP_1 First aperture AP_2 Second aperture AP_3 Third aperture AS_1 First aperture size AS_2 Second aperture size LC light component LC_1 First light component LC_2 Second light component LC_3 Third light component

Claims

1. A biomedical fluid analyzer comprising memory, an interface, and one or more processors, The method involves acquiring image data of one or more image planes of an image stack in a prepared biological fluid sample, wherein the image data includes first image data associated with a first image plane, and acquiring the first image data is The first primary image data of the first image plane is acquired, and the first primary image data is associated with a first incident light setting having a first angular light distribution, and Acquisition includes acquiring a first secondary image data of the first image plane, and associating the first secondary image data with a second incident light setting having a second angular light distribution, Based on the first primary image data and the first secondary image data, the system is configured to classify the cells in the prepared biological fluid sample and provide cell parameters associated with the cells. Acquiring the aforementioned image data includes acquiring a second image data associated with a second image plane, and acquiring the aforementioned second image data is - Acquire a second primary image data of the second image plane in the prepared biological fluid sample, and associate the second primary image data with the first incident light setting, and - The biomedicine analyzer includes one or more of the following: acquiring a second secondary image data of the second image plane of the prepared biological fluid sample, and the second secondary image data being acquired by the second incident light setting, - The system is configured to classify cells in the prepared biological fluid sample based on one or more of the second primary image data and the second secondary image data. The first image plane and the second image plane are associated with different positions in the thickness direction of the prepared biological fluid sample. Biomedical fluid analyzer.

2. The biomedical fluid analyzer according to claim 1, wherein acquiring the first image data includes acquiring first tertiary image data of the first image plane, the first tertiary image data is associated with a third incident light setting having a third angular light distribution, and the classification of cells in the prepared biomedical fluid sample is based on the first tertiary image data.

3. The biofluid analyzer according to claim 1, wherein the biofluid analyzer is configured to determine a set of cell regions based on the image data.

4. The biological fluid analyzer according to claim 3, wherein the determination of the cell region set is based on the first image data.

5. The biofluid analyzer according to claim 3, wherein determining the set of cell regions includes determining a first set of cell regions belonging to the first image plane based on the first image data.

6. The biofluid analyzer according to claim 3, wherein classifying cells in the prepared biofluid sample includes classifying cells within a first cell region of the cell region collection and providing a first cell parameter indicating the cell type of the cells.

7. The biomedical fluid analyzer according to claim 2, wherein classifying cells in the prepared biomedical fluid sample includes applying a classification model to one or more of the first primary image data, the first secondary image data, and the first tertiary image data.

8. The biological fluid analyzer according to claim 1, wherein classifying the cells in the prepared biological fluid sample includes identifying the cell type of the cells.

9. The biofluid analyzer is configured to determine a set of cell regions based on the image data. The biofluid analyzer according to claim 1, wherein the determination of the cell region set is based on the second image data.

10. The biofluid analyzer according to claim 3, wherein providing cell parameters includes determining cell parameters for a plurality of cell regions of the cell region set based on the first primary image data and the first secondary image data, and providing a plurality of cell parameters.

11. The biomedium analyzer according to claim 1, wherein the biomedium analyzer is configured to determine the cellular expression of the prepared biomedium sample based on the cellular parameters.

12. The biofluid analyzer according to claim 1, wherein the provision of the cell parameters is based on cell features that exhibit one or more functions of lobe features, area features, contrast features, roundness features, particle size features, cell nucleus features, optical features, and one or more of the aforementioned features.

13. The biofluid analyzer according to claim 1, wherein the first image data includes a first composite image data based on the first primary image data and / or the first secondary image data.

14. A computer having a non-temporary computer-readable medium having a computer program including program instructions, wherein the computer program is loadable into a data processing unit, and the computer program is configured to perform the operations described in any one of claims 1 to 13 when executed by the data processing unit.

15. A method for classifying cells in a prepared biological fluid sample, - A step of acquiring image data of one or more image planes of an image stack in the prepared biological fluid sample, wherein the image data includes first image data associated with a first image plane, and the step of acquiring the first image data is ○ Acquire a first primary image data of the first image plane, and associate the first primary image data with a first incident light setting having a first angular light distribution, and ○ The acquisition step includes acquiring a first secondary image data of the first image plane, wherein the first secondary image data is acquired by a second incident light setting having a second angular light distribution, - A step of classifying the cells in the prepared biological fluid sample based on the first primary image data and the first secondary image data, - The step of providing cellular parameters associated with the cells based on the classification of the cells, The step of acquiring the aforementioned image data includes the step of acquiring a second image data associated with a second image plane, and the step of acquiring the second image data includes, - Acquire a second primary image data of the second image plane in the prepared biological fluid sample, and associate the second primary image data with the first incident light setting, and - The method includes one or both of the following: acquiring a second secondary image data of the second image plane of the prepared biological fluid sample, and the second secondary image data being acquired by the second incident light setting, - The process includes classifying the cells in the prepared biological fluid sample based on one or both of the second primary image data and the second secondary image data, A method wherein the first image plane and the second image plane are associated with different positions in the thickness direction of the prepared biological fluid sample.

Images