Leukocyte classification method, blood analyzer, readable storage medium and program product
By estimating and fitting the distribution of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions, the problem of inaccurate classification caused by cell feature drift in aged blood samples was solved, and higher white blood cell classification accuracy was achieved.
Patent Information
- Application Number
- CN202510833895.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-20
- Publication Date
- 2025-10-28
AI Technical Summary
When blood samples age, changes in cell characteristics cause particle positions to drift in a three-dimensional scatter plot, with neutrophils entering the lymphocyte classification region, leading to inaccurate white blood cell classification results.
By estimating the nuclear density of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions, mixed distribution density curves are obtained. These curves are then fitted and decomposed to obtain their respective true distribution estimation curves. Based on these curves, the white blood cell classification results are determined.
It improves the accuracy of white blood cell classification in aged blood samples, solves the problem that traditional methods cannot handle cell distribution feature drift, and achieves more accurate cell classification.
Smart Images
Figure CN120852844A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a white blood cell classification method, a blood analyzer, a readable storage medium, and a program product. Background Technology
[0002] White blood cell differential counting uses laser scattering to acquire the characteristics of various white blood cells in a sample from three angles and map them onto a three-dimensional scatter plot. The cell type to which the particle belongs is determined based on the different regions where the cell particles are located in the main view of the three-dimensional scatter plot. This method requires that the characteristics of various cell types in the sample remain stable in the regions where they are located in the main view of the three-dimensional scatter plot.
[0003] However, when blood samples age, cell characteristics change, manifested as particle position drift in a three-dimensional scatter plot. Neutrophils may enter the lymphocyte classification region, leading to inaccurate white blood cell classification results. Summary of the Invention
[0004] Therefore, it is necessary to provide a white blood cell classification method, device, blood analyzer, computer-readable storage medium, and computer program product that can improve the accuracy of white blood cell classification in response to the above-mentioned technical problems.
[0005] In a first aspect, this application provides a method for classifying white blood cells, including:
[0006] Obtain a scatter plot of white blood cells generated for the target blood sample;
[0007] Based on the leukocyte scatter plot, the nuclear density of lymphocytes and neutrophils is estimated in the forward large angle direction and the forward small angle direction, respectively, to obtain the first mixed distribution density curve corresponding to the forward large angle direction and the second mixed distribution density curve corresponding to the forward small angle direction.
[0008] The first mixed distribution density curve is fitted and decomposed to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction.
[0009] The second mixed distribution density curve is fitted and decomposed to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction;
[0010] Based on the estimated distribution curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions, the white blood cell classification result of the target blood sample is determined.
[0011] In some embodiments, determining the white blood cell classification result of the target blood sample based on the estimated distribution curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions respectively includes:
[0012] For each coordinate of the white blood cell scatter plot, based on the estimated curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, the proportion of neutrophils and lymphocytes at the coordinates are determined.
[0013] The number of particles in each of the neutrophils and lymphocytes at the coordinates is determined based on the proportion of neutrophils and lymphocytes.
[0014] The white blood cell classification result of the target blood sample is determined based on the number of neutrophils and lymphocytes at each coordinate point of the white blood cell scatter plot.
[0015] In some embodiments, determining the proportion of neutrophils and lymphocytes at the coordinates based on the estimated distribution curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions respectively includes:
[0016] Substitute the signal values at the coordinates in the forward large angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward large angle direction at the coordinates.
[0017] Substitute the signal values at the coordinates in the forward small angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward small angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward small angle direction at the coordinates.
[0018] The proportions of neutrophils and lymphocytes at the coordinates are determined based on their respective distribution densities at the large forward angle and the small forward angle.
[0019] In some embodiments, determining the proportion of neutrophils and the proportion of lymphocytes at the coordinate location based on their respective distribution densities in the forward large-angle direction and their respective distribution densities in the forward small-angle direction at the coordinate location includes:
[0020] Based on the distribution density of lymphocytes and neutrophils at the coordinates at the large forward angle and the small forward angle, respectively, the proportion of neutrophils and lymphocytes at the coordinates are determined using the following formula:
[0021]
[0022]
[0023] in, Represents the coordinates in the forward large angle direction. This represents the coordinates in the forward small-angle direction. This indicates the proportion of neutrophils at the corresponding coordinate. This indicates the proportion of lymphocytes at the corresponding coordinate. This represents the curve representing the estimated true distribution of neutrophils. This represents the estimated curve of the true distribution of lymphocytes.
[0024] In some embodiments, fitting and decomposing the first mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward large-angle direction includes:
[0025] Determine the fitted distribution density curves of lymphocytes and neutrophils in the forward large-angle direction;
[0026] The first fitting curve is determined by the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction.
[0027] With the goal of minimizing the difference between the first fitted curve and the first mixed distribution density curve, the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction are optimized to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction.
[0028] In some embodiments, fitting and decomposing the second mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward small-angle direction includes:
[0029] Determine the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction;
[0030] The second fitting curve is determined by the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction.
[0031] With the goal of minimizing the difference between the second fitted curve and the second mixed distribution density curve, the fitted distribution density curves of lymphocytes and neutrophils in the forward small angle direction are optimized to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction.
[0032] In some embodiments, the target blood sample includes an aged blood sample.
[0033] Secondly, this application also provides a white blood cell classification device, comprising:
[0034] The scatter plot generation module is used to obtain a scatter plot of white blood cells for a target blood sample;
[0035] The mixed distribution density curve determination module is used to estimate the nuclear density of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, respectively, based on the white blood cell scatter plot, to obtain the first mixed distribution density curve corresponding to the forward large angle direction and the second mixed distribution density curve corresponding to the forward small angle direction.
[0036] The curve fitting module is used to fit and decompose the first mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward large angle direction; and to fit and decompose the second mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward small angle direction.
[0037] The classification result determination module is used to determine the white blood cell classification result of the target blood sample based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, respectively.
[0038] Thirdly, this application also provides a blood analyzer, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring a leukocyte scatter plot generated for a target blood sample; estimating the nuclear density of lymphocytes and neutrophils in the forward large-angle direction and the forward small-angle direction based on the leukocyte scatter plot, respectively, to obtain a first mixed distribution density curve corresponding to the forward large-angle direction and a second mixed distribution density curve corresponding to the forward small-angle direction; fitting and decomposing the first mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction; fitting and decomposing the second mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small-angle direction; and determining the leukocyte classification result of the target blood sample based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction and the forward small-angle direction.
[0039] Fourthly, this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the following steps: acquiring a leukocyte scatter plot generated for a target blood sample; estimating the nuclear density of lymphocytes and neutrophils in both the forward large-angle direction and the forward small-angle direction based on the leukocyte scatter plot, obtaining a first mixed distribution density curve corresponding to the forward large-angle direction and a second mixed distribution density curve corresponding to the forward small-angle direction; fitting and decomposing the first mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction; fitting and decomposing the second mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small-angle direction; and determining the leukocyte classification result of the target blood sample based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction and the forward small-angle direction.
[0040] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps: acquiring a leukocyte scatter plot generated for a target blood sample; estimating the nuclear density of lymphocytes and neutrophils in both the forward large-angle direction and the forward small-angle direction based on the leukocyte scatter plot, obtaining a first mixed distribution density curve corresponding to the forward large-angle direction and a second mixed distribution density curve corresponding to the forward small-angle direction; fitting and decomposing the first mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction; fitting and decomposing the second mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small-angle direction; and determining the leukocyte classification result of the target blood sample based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction and the forward small-angle direction.
[0041] The aforementioned white blood cell classification method, device, blood analyzer, computer-readable storage medium, and computer program product acquire a white blood cell scatter plot generated for a target blood sample. Based on the white blood cell scatter plot, the nuclear density of lymphocytes and neutrophils is estimated in both the forward large-angle and forward small-angle directions, respectively, to obtain a first mixed distribution density curve corresponding to the forward large-angle direction and a second mixed distribution density curve corresponding to the forward small-angle direction. The first mixed distribution density curve is fitted and decomposed to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction, respectively. The second mixed distribution density curve is then fitted and decomposed. By fitting and decomposing the data, the true distribution estimation curves of lymphocytes and neutrophils in the forward small-angle direction are obtained. Based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions, the white blood cell classification result of the target blood sample is determined. It can be seen that in this application, by fitting and decomposing the distribution density curves of neutrophils and lymphocytes, a more accurate distribution density curve is obtained and adaptive classification of cell categories is achieved. This solves the problem that traditional region-based methods cannot handle the drift of cell distribution characteristics in aged blood samples, and improves the white blood cell classification accuracy of aged blood samples. Attached Figure Description
[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0043] Figure 1 This is a schematic diagram of the forward large angle direction and the forward small angle direction in some embodiments;
[0044] Figure 2 This is an example schematic diagram of the front view of a scatter plot of white blood cells in some embodiments;
[0045] Figure 3 This is a diagram illustrating the application environment of the white blood cell classification method in some embodiments;
[0046] Figure 4 This is a flowchart illustrating the white blood cell classification method in some embodiments;
[0047] Figure 5 This is a schematic diagram illustrating the mixed distribution density curves in some embodiments;
[0048] Figure 6 This is a flowchart illustrating the steps for determining white blood cell classification results in some embodiments;
[0049] Figure 7 This is an example schematic diagram of the true distribution estimation curve in some embodiments;
[0050] Figure 8 Here are some structural block diagrams of the white blood cell sorting device in some embodiments;
[0051] Figure 9 Here are some structural block diagrams of the white blood cell sorting device in some embodiments;
[0052] Figure 10 This is an internal structural diagram of a computer device in some other embodiments. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0054] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.
[0055] The white blood cell differential counting function acquires the characteristics of various white blood cell types in a sample from three angles using laser scattering and maps them to a three-dimensional scatter plot. Then, based on this 3D scatter plot, it classifies, counts, and analyzes five types of white blood cells—neutrophils (NEU), lymphocytes (LYM), monocytes (MON), eosinophils (EOS), and basophils (BAS)—to obtain reportable clinical parameters. Since neutrophils and lymphocytes constitute the majority (over 80%) of white blood cells, the white blood cell correction in this invention refers to correcting the classification results for neutrophils and lymphocytes.
[0056] The commonly used white blood cell differential counting method in the industry determines the different cell types to which an ion belongs by determining the different regions where the particle is located in the main view of a three-dimensional scatter plot. The main view is a view composed of the intensity values of scattered light in the forward large angle (FL) and forward small angle (FS) directions. For example... Figure 1 The ( Figure 1 In the diagram, the large blue ellipse represents the cell, and the smaller ellipses within it represent the cell contents, such as the nucleus and mitochondria. When acquiring cell characteristics using laser scattering, the angle of scattered light in the FS direction is relatively small, for example, between 1 and 5 degrees, while the angle of scattered light in the FL direction is relatively large, for example, between 7 and 15 degrees. However, this method requires that the characteristics of various white blood cell types in the sample remain stable within the region of the 3D scatter plot.
[0057] However, when blood samples age (also known as aged blood, referring to blood samples stored beyond their expiration date), cell characteristics change, manifesting as particle position drift in a three-dimensional scatter plot, leading to inaccurate white blood cell classification results. (Reference) Figure 2 This shows the scatter plot of white blood cells after fresh blood samples have been stored for different periods of time. Figure 2 Figure (a) in the figure is a scatter plot of white blood cells from a blood sample that has been left at room temperature for 0 hours. Figure 2 Figure (b) is a scatter plot of white blood cells from a blood sample that has been left at room temperature for 8 hours. Figure 2 Figure (c) is a scatter plot of white blood cells from a blood sample left at room temperature for 16 hours. Figure 2 It can be observed that as the blood sample is left for longer, the distribution boundary between neutrophils and lymphocytes tends to become blurred.
[0058] In impoverished and underdeveloped areas with poor medical and health conditions, blood samples often require long transportation times before testing, by which time fresh blood has become aging blood. Therefore, white blood cell classification correction for aging blood samples has significant practical implications.
[0059] The white blood cell classification method proposed in this application can adaptively reclassify neutrophils and lymphocytes based on their distribution characteristics in the forward large-angle and forward small-angle directions, which can effectively solve the problem of inaccurate classification results caused by scatter plot distribution drift in aged blood samples.
[0060] The white blood cell classification method provided in this application embodiment can be applied to, for example... Figure 3The application environment is shown. Terminal 302 communicates with server 304 via a network. A data storage system can store the data that server 304 needs to process. The data storage system can be integrated onto server 304 or placed on the cloud or other network servers. Terminal 302 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, blood analyzers, drones, low-altitude aircraft, IoT devices, and portable wearable devices. Specifically, the blood analyzer can be a blood cell analyzer, such as a fully automated blood cell analyzer. A fully automated blood cell analyzer can classify, count, and analyze various types of cells in blood, and features high accuracy, fast detection speed, multiple detection parameters, and simple operation; it is one of the most commonly used instruments in clinical testing both domestically and internationally. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. A 304 error can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.
[0061] The white blood cell classification method provided in this application embodiment can be executed by a computer device, which refers to an electronic device with data computing, processing, and storage capabilities. Figure 1 Taking the application environment shown as an example, the white blood cell classification method can be executed by the terminal 302 alone, or by the server 304 alone, or by the terminal 302 and the server 304 interacting and cooperating. This application does not limit this.
[0062] Taking server 304 as an example, server 304 can obtain a scatter plot of white blood cells generated for the target blood sample. Based on the scatter plot, it estimates the nuclear density of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, respectively, to obtain the first mixed distribution density curve corresponding to the forward large angle direction and the second mixed distribution density curve corresponding to the forward small angle direction. It fits and decomposes the first mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction. It fits and decomposes the second mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction. Based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, it determines the white blood cell classification result of the target blood sample. Server 304 can further send the white blood cell classification result to terminal 302.
[0063] In one exemplary embodiment, such as Figure 4 As shown, a method for classifying white blood cells is provided. The method is illustrated using a computer device as an example. This computer device can be... Figure 1 The terminal 302 or server 404 includes the following steps 402 to 410. Wherein:
[0064] Step 402: Obtain a scatter plot of white blood cells generated for the target blood sample.
[0065] The leukocyte scatter plot is a visual distribution map created by a blood analyzer using laser scattering to detect the physical and chemical characteristics of leukocytes in a blood sample, mapping cell characteristic parameters onto a two- or three-dimensional coordinate system. It is a core tool in clinical testing for leukocyte differential counting, enabling the identification and counting of neutrophils, lymphocytes, monocytes, and other cell types by observing the distribution and density of different cell populations on the map. The target blood sample refers to the blood sample requiring leukocyte differential counting; for example, the target blood sample may include aged blood samples.
[0066] Specifically, the computer device can acquire a scatter plot of white blood cells generated for the target blood sample, and then obtain the coordinate values of the forward large angle direction and the forward small angle direction based on the main view of the scatter plot to perform white blood cell classification and counting.
[0067] Step 404: Based on the leukocyte scatter plot, the nuclear density of lymphocytes and neutrophils is estimated in the forward large angle direction and the forward small angle direction, respectively, to obtain the first mixed distribution density curve corresponding to the forward large angle direction and the second mixed distribution density curve corresponding to the forward small angle direction.
[0068] Kernel density estimation (KDE) is a nonparametric statistical method used to estimate the probability density function of a random variable. It smooths the influence of each sample point using a kernel function and controls the degree of smoothing using bandwidth. Ultimately, it estimates the overall density distribution using the "cumulative effect" of all samples, avoiding the limitations of parametric models.
[0069] Specifically, the computer device can obtain the coordinate values of lymphocytes and neutrophils in the forward large angle direction based on the leukocyte scatter plot generated for the target blood sample. This allows for the estimation of the nuclear density of the distribution of lymphocytes and neutrophils in the forward large angle direction, resulting in a first mixed distribution density curve corresponding to the forward large angle direction. This first mixed distribution density curve reflects the common distribution of lymphocytes and neutrophils in the forward large angle direction.
[0070] Computer equipment can obtain the coordinate values of lymphocytes and neutrophils in the forward small angle direction based on the leukocyte scatter plot generated for the target blood sample. This allows for the estimation of nuclear density of lymphocytes and neutrophils in the forward small angle direction, resulting in a second mixed distribution density curve corresponding to the forward small angle direction. This second mixed distribution density curve reflects the common distribution of lymphocytes and neutrophils in the forward small angle direction.
[0071] Step 406: Fit and decompose the first mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction.
[0072] Step 408: Fit and decompose the second mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction.
[0073] Among them, the true distribution estimation curve refers to the curve that estimates the true distribution density. For example, the true distribution estimation curve of lymphocytes in the forward large angle direction refers to the curve that estimates the true distribution density of lymphocytes in the forward large angle direction.
[0074] Specifically, such as Figure 5 The diagram shown is a schematic representation of the mixed distribution density curves in some embodiments. Figure 5 It can be seen that, in the fl direction, neutrophils are distributed between 600 and 900, and lymphocytes are distributed between 200 and 500. In the fs direction, neutrophils are distributed between 600 and 800, and lymphocytes are distributed between 200 and 550.
[0075] In addition, from Figure 5The mixed distribution density curve clearly shows that the cell distribution at 0 hours and 16 hours is completely different. At 0 hours, the distribution peaks of neutrophils and lymphocytes are relatively independent and do not interfere with each other. After 16 hours, the boundary between the distribution peaks of neutrophils and lymphocytes becomes blurred, and a large number of neutrophils enter the region of lymphocytes, which will lead to serious bias in the classification results. Therefore, in this embodiment, the computer device can fit and decompose the distribution peaks in the fl and fs directions to obtain the true distribution estimation curves of neutrophils and lymphocytes respectively.
[0076] Step 410: Based on the estimated curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, determine the white blood cell classification result of the target blood sample.
[0077] Specifically, for each coordinate of the leukocyte scatter plot, the computer device can determine the proportion of neutrophils and lymphocytes at the coordinate based on the estimated curves of the actual distribution of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions, and then determine the number of particles of neutrophils and lymphocytes at the coordinate based on the proportions of neutrophils and lymphocytes. Finally, based on the number of particles of neutrophils and lymphocytes at each coordinate of the leukocyte scatter plot, the leukocyte classification result of the target blood sample is determined.
[0078] In the aforementioned white blood cell classification method, a white blood cell scatter plot is generated for the target blood sample. Based on the scatter plot, the nuclear density of lymphocytes and neutrophils is estimated in both the forward large-angle and forward small-angle directions. This yields a first mixed distribution density curve corresponding to the forward large-angle direction and a second mixed distribution density curve corresponding to the forward small-angle direction. The first mixed distribution density curve is fitted and decomposed to obtain the true distribution estimates of lymphocytes and neutrophils in the forward large-angle direction. The second mixed distribution density curve is fitted and decomposed to obtain the true distribution estimates of lymphocytes and neutrophils in the forward small-angle direction. The true distribution estimation curves of lymphocytes and neutrophils in the angular direction are obtained. Based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, the white blood cell classification result of the target blood sample is determined. It can be seen that in this application, by fitting and decomposing the distribution density curves of neutrophils and lymphocytes, a more accurate distribution density curve is obtained and adaptive classification of cell categories is achieved. This solves the problem that traditional region-based methods cannot handle the drift of cell distribution characteristics in aged blood samples and improves the white blood cell classification accuracy of aged blood samples.
[0079] In some embodiments, fitting and decomposing the first mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction includes: determining the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction; determining the first fitted curve based on the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction; optimizing the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction with the optimization objective of minimizing the difference between the first fitted curve and the first mixed distribution density curve, to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction.
[0080] Specifically, the computer device can determine the fitted distribution density curves of lymphocytes and neutrophils in the forward large-angle direction. For example, considering that aging-induced cell characteristic drift is usually a continuous, unidirectional skewed change (such as the left skew of the fl signal of neutrophils due to component degradation), the skewed normal Gaussian distribution is determined by parameters. To directly characterize this skewness, computer devices can use a partially normal Gaussian distribution function to model the true distribution of neutrophils and lymphocytes, thereby determining the fitted distribution density curve. The partially normal Gaussian distribution function is shown below:
[0081]
[0082] in, Indicates signal amplitude. Indicates the center location of the distribution peak. Indicates the distribution width of the peak. Indicates the degree of skewness in the distribution. The error function is denoted as . In some other embodiments, the computer device may also use other models such as the log-normal distribution or the generalized normal distribution to determine the fitted distribution density curve.
[0083] The computer device can further determine a first fitting curve based on the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction. With minimizing the difference between the first fitting curve and the first mixed distribution density curve as the optimization objective, the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction are optimized to obtain the estimated curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction.
[0084] For example, the computer device can use Levenberg-Marquardt (LM) as the objective function for fitting optimization. In this case, the difference between the first fitted curve and the first mixed distribution density curve is the mean squared error, that is, the optimization objective is the mean squared error between the sum of the fitted distribution density curves of neutrophils and lymphocytes and the original distribution density curve. For example, in some other embodiments, the computer device can also use the gradient descent algorithm for fitting optimization or use any one of the following as the objective function: mean absolute error (MAE), Kullback-Leibler divergence, etc.
[0085] In some embodiments, fitting and decomposing the second mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction includes: determining the fitted distribution density curves of lymphocytes and neutrophils in the forward small angle direction; determining the second fitted curve based on the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward small angle direction; optimizing the fitted distribution density curves of lymphocytes and neutrophils in the forward small angle direction with the optimization objective of minimizing the difference between the second fitted curve and the second mixed distribution density curve, to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction.
[0086] For the fitting and decomposition of the true distribution estimation curve in the forward small angle direction, please refer to the embodiment of fitting and decomposition of the true distribution estimation curve in the forward large angle direction in the above embodiment, which will not be repeated here.
[0087] In the above embodiments, by minimizing the fitting error, the most likely true distribution parameters are deduced from the mixed data. The resulting distribution curve not only conforms to the data observation but also to the physical laws of cell aging, resulting in a more accurate distribution density curve for neutrophils and lymphocytes, which can be considered as a "true distribution estimate".
[0088] refer to Figure 6 As shown in Figure 7, the true distribution estimation curves are schematic diagrams in some embodiments. As can be seen from Figure 7, after splitting each true distribution estimation curve, two true distribution estimation curves can be obtained. The skewed normal Gaussian model can effectively separate overlapping peaks in aged blood samples, and the fitted curves have a high degree of agreement with the original data.
[0089] Depend on Figure 6It can also be seen that a large portion of the neutrophil distribution curve fitted in the fl direction enters the lymphocyte distribution area. This is precisely why algorithms based on region division in related technologies cannot accurately classify and count aging blood. To obtain more accurate white blood cell classification results, after calculating the estimated true distribution curves of neutrophils and lymphocytes, this embodiment can further calculate the reclassification ratio of neutrophils and lymphocytes at each coordinate position of the main-view scatter plot. This will be specifically explained through the following embodiments.
[0090] In one exemplary embodiment, such as Figure 7 As shown, based on the estimated distribution curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions, the white blood cell classification results of the target blood sample are determined, including:
[0091] Step 702: For each coordinate of the leukocyte scatter plot, based on the estimated curves of the actual distribution of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, determine the proportion of neutrophils and lymphocytes at the coordinate.
[0092] Specifically, for each coordinate of the leukocyte scatter plot, the signal value at that coordinate in the forward large-angle direction is substituted into the true distribution estimation curves of lymphocytes and neutrophils in the forward large-angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward large-angle direction at that coordinate. Similarly, the signal value at that coordinate in the forward small-angle direction is substituted into the true distribution estimation curves of lymphocytes and neutrophils in the forward small-angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward small-angle direction at that coordinate. Based on the distribution densities of lymphocytes and neutrophils in the forward large-angle direction and the distribution densities in the forward small-angle direction at that coordinate, the proportion of neutrophils and the proportion of lymphocytes at that coordinate are determined.
[0093] Specifically, after obtaining the distribution density of lymphocytes and neutrophils at a coordinate point in the forward large-angle direction and the forward small-angle direction respectively, the computer equipment can combine the distribution densities in the two directions to determine the proportion of neutrophils and lymphocytes at that coordinate point. For example, the distribution density of lymphocytes at a coordinate point in the forward large-angle direction and the forward small-angle direction can be normalized separately, and then multiplied to obtain the proportion of lymphocytes at that coordinate point.
[0094] In some embodiments, the computer device can determine the proportion of neutrophils and lymphocytes at a coordinate location using the following formulas (1) and (2) based on the distribution density of lymphocytes and neutrophils at the coordinate location in the forward large-angle direction and the distribution density of neutrophils at the coordinate location in the forward small-angle direction:
[0095] (1)
[0096] (2)
[0097] in, Represents the coordinates in the forward large angle direction. This represents the coordinates in the forward small-angle direction. This indicates the proportion of neutrophils at the corresponding coordinate. This indicates the proportion of lymphocytes at the corresponding coordinate. This represents the curve representing the estimated true distribution of neutrophils. This represents the estimated curve of the true distribution of lymphocytes.
[0098] Specifically, the computer device converts the absolute density values in the fl and fs directions into relative probabilities. For example, at coordinate i in the fl direction: SNEUT(i) / SNEUT(i)+SLYMPH(i) represents the one-dimensional probability that the particle belongs to a neutrophil at that coordinate value, with a value range of [0,1]. Essentially, this is a probability segmentation of the overlapping distribution of the two types of cells in a single direction. Further, the one-dimensional probabilities in the two directions are multiplied to obtain a ratio. The product balances the influence of both, avoiding a rigid "either / or" division.
[0099] For example, suppose the coordinates of a particle in an aged blood sample are (i=500, j=700). Through calculation, we can obtain:
[0100] In the fl direction (i=500): SNEUT=0.002, SLYMPH=0.003, then: neutrophil probability (fl) = 0.002 + 0.003 + 0.002 = 0.4, lymphocyte probability (fl) = 0.6;
[0101] In the direction of fs (j=700): SNEUT=0.0025, SLYMPH=0.0015, then: neutrophil probability (fs) = 0.0025 + 0.0015 + 0.0025 = 0.625, lymphocyte probability (fs) = 0.375.
[0102] The final calculation yields RNEUT=0.4×0.625=0.25, RLYMPH=0.6×0.375=0.22. It is understandable that due to floating-point calculation errors, in practical applications, normalization can be used to ensure that the sum is 1, so the final values can be RNEUT=0.53, RLYMPH=0.47.
[0103] It can be seen that the particle may be classified as a lymphocyte in the traditional fixed region division, but through the adaptive division of the embodiment of this application, combined with the fs direction feature, it is finally allocated proportionally as 53% neutrophils and 47% lymphocytes, which is closer to the real distribution.
[0104] In the above embodiments, using proportional quantification for fuzzy attribution can adapt to the distribution drift of aging blood samples; by calculating the joint probability of fl and fs bidirectional features, classification robustness can be improved and misjudgment in a single dimension can be avoided; in addition, since proportional calculation depends on the distribution density curve fitted in real time, the division boundary is automatically adjusted with the degree of sample aging, without the need for manual parameter preset.
[0105] Step 704: Determine the number of particles of neutrophils and lymphocytes at the coordinates based on the proportion of neutrophils and lymphocytes.
[0106] Step 706: Determine the white blood cell classification result of the target blood sample based on the number of neutrophils and lymphocytes at each coordinate of the white blood cell scatter plot.
[0107] Specifically, assuming there are N particles at a certain coordinate, the counting contribution of the two types of cells can be calculated by ratio, where:
[0108] Increase in neutrophil count = N × RNEUT(i,j);
[0109] Increase in lymphocyte count = N × RLYMPH(i,j).
[0110] Computer devices can correct classification results by summing the particle counts at all coordinate points of a scatter plot of white blood cells and traversing them.
[0111] In this embodiment, by determining the proportion of neutrophils and lymphocytes, and based on the proportion of neutrophils and lymphocytes, the particle count of each neutrophil and lymphocyte is determined. Thus, based on the particle count of each neutrophil and lymphocyte at each coordinate of the leukocyte scatter plot, the leukocyte classification result of the target blood sample is determined, and a more accurate classification result can be obtained.
[0112] In some specific embodiments, this application also provides a method for classifying white blood cells, executed by a computer device, comprising the following steps:
[0113] 1. Obtain a scatter plot of white blood cells generated for the target blood sample.
[0114] 2. Based on the leukocyte scatter plot, the nuclear density of lymphocytes and neutrophils is estimated in the forward large angle direction and the forward small angle direction, respectively, to obtain the first mixed distribution density curve corresponding to the forward large angle direction and the second mixed distribution density curve corresponding to the forward small angle direction.
[0115] 3. Fit and decompose the first mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction.
[0116] Specifically, the computer equipment can determine the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction; determine the first fitted curve based on the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction; optimize the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction with the optimization objective of minimizing the difference between the first fitted curve and the first mixed distribution density curve, and obtain the estimated curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction.
[0117] 4. Fit and decompose the second mixed distribution density curve to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction.
[0118] Specifically, the computer equipment can determine the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction; determine a second fitted curve based on the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction; optimize the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction with the optimization objective of minimizing the difference between the second fitted curve and the second mixed distribution density curve, and obtain the estimated curves of the true distribution of lymphocytes and neutrophils in the forward small-angle direction.
[0119] 5. For each coordinate of the leukocyte scatter plot, substitute the signal value at that coordinate in the forward large angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward large angle direction at that coordinate.
[0120] 6. Substitute the signal value at this coordinate point in the forward small angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward small angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward small angle direction at this coordinate point.
[0121] 7. Based on the distribution density of lymphocytes and neutrophils at the coordinate point in the forward large angle direction and the distribution density of lymphocytes and neutrophils at the coordinate point in the forward small angle direction, use the formulas (1) and (2) above to determine the proportion of neutrophils and lymphocytes at the coordinate point.
[0122] 8. Based on the proportion of neutrophils and lymphocytes, determine the number of particles of each neutrophil and lymphocyte at this coordinate.
[0123] 9. Determine the white blood cell classification result of the target blood sample based on the number of neutrophils and lymphocytes at each coordinate point of the white blood cell scatter plot.
[0124] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.
[0125] Based on the same inventive concept, this application also provides a white blood cell classification device for implementing the white blood cell classification method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more white blood cell classification device embodiments provided below can be found in the limitations of the white blood cell classification method described above, and will not be repeated here.
[0126] In one exemplary embodiment, such as Figure 8 As shown, a white blood cell classification device 800 is provided, comprising:
[0127] Scatter plot generation module 802 is used to obtain a white blood cell scatter plot generated for a target blood sample;
[0128] The mixed distribution density curve determination module 804 is used to estimate the nuclear density of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction respectively, based on the leukocyte scatter plot, to obtain the first mixed distribution density curve corresponding to the forward large angle direction and the second mixed distribution density curve corresponding to the forward small angle direction.
[0129] The curve fitting module 806 is used to fit and decompose the first mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward large angle direction; and to fit and decompose the second mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward small angle direction.
[0130] The classification result determination module 808 is used to determine the white blood cell classification result of the target blood sample based on the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, respectively.
[0131] In some embodiments, the classification result determination module 808 is further configured to: for each coordinate of the leukocyte scatter plot, determine the proportion of neutrophils and the proportion of lymphocytes at the coordinate based on the estimated curves of the true distribution of lymphocytes and neutrophils in the forward large-angle direction and the forward small-angle direction, respectively; determine the number of particles of neutrophils and lymphocytes at the coordinate based on the proportion of neutrophils and the proportion of lymphocytes; and determine the leukocyte classification result of the target blood sample based on the number of particles of neutrophils and lymphocytes at each coordinate of the leukocyte scatter plot.
[0132] In some embodiments, the classification result determination module 808 is further configured to: substitute the signal value at the coordinate location in the forward large angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward large angle direction at the coordinate location; substitute the signal value at the coordinate location in the forward small angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward small angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward small angle direction at the coordinate location; and determine the proportion of neutrophils and the proportion of lymphocytes at the coordinate location based on the distribution density of lymphocytes and neutrophils in the forward large angle direction and the distribution density of lymphocytes and neutrophils in the forward small angle direction at the coordinate location.
[0133] In some embodiments, the classification result determination module 808 is further configured to: determine the proportion of neutrophils and the proportion of lymphocytes at the coordinates using the following formula, based on the distribution density of lymphocytes and neutrophils at the coordinates in the forward large-angle direction and the distribution density of neutrophils at the coordinates in the forward small-angle direction:
[0134]
[0135]
[0136] in, Represents the coordinates in the forward large angle direction. This represents the coordinates in the forward small-angle direction. This indicates the proportion of neutrophils at the corresponding coordinate. This indicates the proportion of lymphocytes at the corresponding coordinate. This represents the curve representing the estimated true distribution of neutrophils. This represents the estimated curve of the true distribution of lymphocytes.
[0137] In some embodiments, the curve fitting module is further configured to determine the fitted distribution density curves of lymphocytes and neutrophils respectively in the forward large angle direction; determine a first fitted curve based on the sum of the fitted distribution density curves of lymphocytes and neutrophils respectively in the forward large angle direction; and optimize the fitted distribution density curves of lymphocytes and neutrophils respectively in the forward large angle direction with the optimization objective of minimizing the difference between the first fitted curve and the first mixed distribution density curve, so as to obtain the estimated true distribution curves of lymphocytes and neutrophils respectively in the forward large angle direction.
[0138] In some embodiments, the curve fitting module is further configured to determine the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction; determine a second fitted curve based on the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction; and optimize the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction with the optimization objective of minimizing the difference between the second fitted curve and the second mixed distribution density curve, thereby obtaining the estimated true distribution curves of lymphocytes and neutrophils in the forward small-angle direction.
[0139] In some embodiments, the target blood sample includes an aged blood sample.
[0140] Each module in the aforementioned white blood cell classification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0141] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores blood sample-related data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a white blood cell classification method.
[0142] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a white blood cell classification method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0143] Those skilled in the art will understand that Figure 9 , Figure 10The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0144] In one exemplary embodiment, a blood analyzer is provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, implements the steps of the white blood cell classification method described in any of the above embodiments. For example, the blood analyzer may be a blood cell analyzer for analyzing blood cells, such as a fully automated blood cell analyzer.
[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the white blood cell classification method in any of the above embodiments.
[0146] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the white blood cell classification method in any of the above embodiments.
[0147] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0148] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0149] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0150] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for classifying white blood cells, characterized in that, The method comprises: Obtain a scatter plot of white blood cells generated for the target blood sample; Based on the leukocyte scatter plot, the nuclear density of lymphocytes and neutrophils is estimated in the forward large angle direction and the forward small angle direction, respectively, to obtain the first mixed distribution density curve corresponding to the forward large angle direction and the second mixed distribution density curve corresponding to the forward small angle direction. The first mixed distribution density curve is fitted and decomposed to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction. The second mixed distribution density curve is fitted and decomposed to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction; Based on the estimated distribution curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions, the white blood cell classification result of the target blood sample is determined.
2. The method according to claim 1, characterized in that, The determination of the white blood cell classification result of the target blood sample based on the estimated distribution curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions includes: For each coordinate of the white blood cell scatter plot, based on the estimated curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction and the forward small angle direction, the proportion of neutrophils and lymphocytes at the coordinates are determined. The number of particles in each of the neutrophils and lymphocytes at the coordinates is determined based on the proportion of neutrophils and lymphocytes. The white blood cell classification result of the target blood sample is determined based on the number of neutrophils and lymphocytes at each coordinate point of the white blood cell scatter plot.
3. The method according to claim 2, characterized in that, The determination of the proportion of neutrophils and lymphocytes at the specified coordinates based on the estimated distribution curves of lymphocytes and neutrophils in the forward large-angle and forward small-angle directions includes: Substitute the signal values at the coordinates in the forward large angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward large angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward large angle direction at the coordinates. Substitute the signal values at the coordinates in the forward small angle direction into the estimation curves of the true distribution of lymphocytes and neutrophils in the forward small angle direction, respectively, to obtain the distribution density of lymphocytes and neutrophils in the forward small angle direction at the coordinates. The proportions of neutrophils and lymphocytes at the coordinates are determined based on their respective distribution densities at the large forward angle and the small forward angle.
4. The method according to claim 3, characterized in that, The determination of the proportion of neutrophils and lymphocytes at the coordinate point based on their respective distribution densities in the forward large-angle direction and the forward small-angle direction at the coordinate point includes: Based on the distribution density of lymphocytes and neutrophils at the coordinates at the large forward angle and the small forward angle, respectively, the proportion of neutrophils and lymphocytes at the coordinates are determined using the following formula: in, Represents the coordinates in the forward large angle direction. This represents the coordinates in the forward small-angle direction. This indicates the proportion of neutrophils at the corresponding coordinate. This indicates the proportion of lymphocytes at the corresponding coordinate. This represents the curve representing the estimated true distribution of neutrophils. This represents the estimated curve of the true distribution of lymphocytes.
5. The method according to claim 1, characterized in that, The process of fitting and decomposing the first mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward large-angle direction includes: Determine the fitted distribution density curves of lymphocytes and neutrophils in the forward large-angle direction; The first fitting curve is determined by the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction. With the goal of minimizing the difference between the first fitted curve and the first mixed distribution density curve, the fitted distribution density curves of lymphocytes and neutrophils in the forward large angle direction are optimized to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward large angle direction.
6. The method according to claim 1, characterized in that, The process of fitting and decomposing the second mixed distribution density curve to obtain the estimated true distribution curves of lymphocytes and neutrophils in the forward small-angle direction includes: Determine the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction; The second fitting curve is determined by the sum of the fitted distribution density curves of lymphocytes and neutrophils in the forward small-angle direction. With the goal of minimizing the difference between the second fitted curve and the second mixed distribution density curve, the fitted distribution density curves of lymphocytes and neutrophils in the forward small angle direction are optimized to obtain the true distribution estimation curves of lymphocytes and neutrophils in the forward small angle direction.
7. The method according to any one of claims 1 to 6, characterized in that, The target blood sample includes aged blood samples.
8. A blood analyzer, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.