Blood sample index screening method and device based on cell scatter diagram

Abstract

The invention provides a blood sample index screening method and device based on a cell scatter diagram. The method comprises the following steps: acquiring the cell scatter diagram of a blood sample to be screened; preprocessing the cell scatter diagram by using an expansion algorithm to obtain a preprocessing result; carrying out frame selection by adopting a predetermined target area selection box based on the preprocessing result to obtain a target area; wherein the target area selection box is determined by utilizing massive cell scatter diagram samples with target blood index characteristics; and extracting abnormal character pixel points in the target area, and performing blood sample index screening according to an extraction result to obtain a screening result. The target area of the cell scatter diagram of the blood sample to be screened is extracted through the fixed target area selection box, blood sample index screening is carried out according to the abnormal character pixel points of the target area, training of neural network parameters is not involved, and blood sample index screening low in cost and high in accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method and device for screening blood sample indicators based on cell scattergrams. Background Art

[0002] As a vital medical resource for saving lives, blood safety is paramount, and blood sample index screening is the most critical step in ensuring blood safety. Currently, blood sample index screening is primarily performed using a blood cell analyzer. During the screening process, the analyzer uses a hemolytic agent to disrupt red blood cells, causing slight damage to the white blood cell membrane. Side scattered light (SSC) is then used to determine the complexity of the internal structure of different white blood cells. Fluorescent staining and side fluorescence (SFL) are then used to determine the type and quantity of nucleic acids and organelles in different white blood cells. This allows for the differential counting of each type of white blood cell, and statistical analysis of the measured cells is performed to produce a WDF scatter plot with SSC as the horizontal axis and SFL as the vertical axis. Among them, the statistical types mainly include the following cells: ghost cells / cell fragments (Debris), nucleated red blood cells (NRBC), lymphocytes (LYMPH), abnormal lymphocytes / prolymphocytes (Abnormal lymph Blast), atypical lymphocytes / atypical lymphocytes (Atypically lymph), monocytes (MONO), primitive cells (Blast), neutrophils and basophils (NEUT+BASO), left shift (Left shift), immature granulocytes (IG) and eosinophils (EO), such as Figure 2 shown.

[0003] Scatter plot-based anomaly detection is currently an effective method for screening blood sample indicators. Some studies use neural networks to extract features from images, building end-to-end models or two-stage models (first extracting features, then performing anomaly classification) for this purpose. Such algorithms place high demands on graphics cards, which are difficult to achieve with lightweight medical devices, especially microscopes. Some studies have added graphics cards to the blood analyzers they are developing, which increases the burden on the machine's portability and cost. Furthermore, scatter plot data naturally lacks semantic information, making it difficult to obtain meaningful features during feature extraction using the aforementioned deep learning methods, resulting in low accuracy.

[0004] In summary, the existing technology has the problems of high equipment cost and low result accuracy. Summary of the Invention

[0005] The present invention provides a method and device for screening blood sample indicators based on cell scattergrams, which are used to solve the defects of high equipment cost and low result accuracy in the existing technology, and realize low-cost and high-accuracy blood sample indicator screening.

[0006] The present invention provides a blood sample index screening method based on cell scattergram, comprising:

[0007] Obtaining a cell scatter plot of the blood sample to be screened;

[0008] Preprocessing the cell scattergram using an expansion algorithm to obtain a preprocessing result;

[0009] Based on the preprocessing result, a predetermined target region selection frame is used to select a target region, where the target region selection frame is determined using a large number of cell scatter plot samples having target blood indicator characteristics;

[0010] Abnormal characteristic pixel points in the target area are extracted, and blood sample index screening is performed based on the extraction results to obtain screening results.

[0011] According to the present invention, a blood sample index screening method based on cell scatter plots is provided, which uses a large number of cell scatter plot samples with target blood index characteristics to determine a target area selection frame, specifically including:

[0012] Obtain a large number of cell scatter plot samples with target blood indicator characteristics;

[0013] Using a mix-up algorithm to fuse the cell scatter plot samples to obtain a fusion result;

[0014] The pixels with abnormal distribution in the fusion result are selected to obtain a target area selection box.

[0015] According to a blood sample index screening method based on a cell scattergram provided by the present invention, the cell scattergram is preprocessed using an expansion algorithm to obtain a preprocessing result, specifically comprising:

[0016] Performing grayscale processing on the cell scattergram to obtain a grayscale image;

[0017] Binarization is performed on the grayscale image to obtain a preprocessing result.

[0018] According to a blood sample index screening method based on a cell scattergram provided by the present invention, abnormal characteristic pixel points in the target area are extracted, and blood sample index screening is performed based on the extraction results to obtain screening results, specifically comprising:

[0019] Extracting abnormal pixel points in the target area to obtain an extraction result;

[0020] Counting the number of abnormal pixel points in the extraction result to obtain a target number;

[0021] The screening result is obtained based on the target quantity and the preset quantity threshold.

[0022] According to a blood sample index screening method based on a cell scattergram provided by the present invention, a screening result is obtained according to the target number and a preset number threshold, specifically comprising:

[0023] When the target number is greater than the preset number threshold, determining that the screening result is a sample abnormality;

[0024] When the target number is less than or equal to the preset number threshold, the screening result is determined to be a normal sample.

[0025] According to a blood sample index screening method based on a cell scattergram provided by the present invention, the abnormal trait pixel point is a pixel point with a pixel value of 0.

[0026] The present invention also provides a blood sample index screening device based on a cell scattergram, comprising:

[0027] an acquisition unit, used for acquiring a cell scattergram of a blood sample to be screened;

[0028] a preprocessing unit, configured to preprocess the cell scattergram using an expansion algorithm to obtain a preprocessing result;

[0029] A region unit, configured to select a target region using a predetermined target region selection frame based on the preprocessing result to obtain a target region; wherein the target region selection frame is determined using a large number of cell scatter plot samples having target blood indicator characteristics;

[0030] The screening unit is used to extract abnormal characteristic pixel points in the target area, and screen the blood sample indicators according to the extraction results to obtain the screening results.

[0031] The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the blood sample index screening method based on the cell scattergram as described above is implemented.

[0032] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the blood sample index screening method based on the cell scattergram as described above is implemented.

[0033] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned blood sample index screening methods based on cell scattergrams.

[0034] The present invention provides a method and device for screening blood sample indicators based on a cell scatter plot, which comprises obtaining a cell scatter plot of a blood sample to be screened; preprocessing the cell scatter plot using an expansion algorithm to obtain a preprocessing result; selecting a target area using a predetermined target area selection frame based on the preprocessing result to obtain a target area; wherein the target area selection frame is determined using a large number of cell scatter plot samples having target blood indicator characteristics; extracting abnormal trait pixels in the target area, and performing blood sample indicator screening based on the extraction result to obtain a screening result. The present invention extracts the target area of the cell scatter plot of the blood sample to be screened using a fixed target area selection frame, and performs blood sample indicator screening based on the abnormal trait pixels in the target area. The present invention does not involve the training of neural network parameters, and achieves low-cost and high-accuracy blood sample indicator screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 1 is a flow chart of a method for screening blood sample indicators based on cell scattergram provided by the present invention;

[0037] Figure 2 It is a scatter plot of the prior art provided by the present invention;

[0038] Figure 3 This is an overview of five types of data of abnormal samples and normal samples in the blood sample index screening method based on cell scattergram provided by the present invention; wherein, Figure 3 (a) is an overview of the five types of data for abnormal samples (M3 leukemia). Figure 3 Middle (b) is an overview of the five types of data for normal samples;

[0039] Figure 4 : is a schematic diagram of the effect of the expansion algorithm processing of the blood sample index screening method based on the cell scattergram provided by the present invention; wherein, Figure 4 (a) is the original image of a cell scatter plot. Figure 4 (b) is the image after the image dilation operation in (a). Figure 4 (c) is the original image of another cell scatter plot. Figure 4 (d) is the image after the image in (c) is expanded;

[0040] Figure 52. Schematic diagram of target area selection box for the blood sample index screening method based on cell scattergram provided by the present invention;

[0041] Figure 6 It is a schematic structural diagram of a blood sample index screening device based on cell scattergram provided by the present invention;

[0042] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] The following combination Figure 1-Figure 5 Describe the blood sample index screening method based on cell scattergram of the present invention, Figure 1 Schematic diagram of the process of the blood sample index screening method based on cell scattergram provided by the present invention, such as Figure 1 As shown, the method includes the following steps:

[0045] Step 110: Obtain a cell scattergram of the blood sample to be screened.

[0046] It should be noted that the cell scatter plot obtained is of the blood sample to be screened, which includes but is not limited to a WDF scatter plot. It should be noted that the cell scatter plot of the blood sample to be screened can be obtained using a blood cell analyzer or other detection instruments, and the present invention is not limited thereto. The present invention can screen any image input that meets the requirements of the software system and has high applicability.

[0047] In some embodiments, the cell scatter plot obtained in the embodiments of the present invention includes five categories: Debris (ghost cells / cell debris); NRBC (nucleated red blood cells); LYMPH (lymphocytes); Abnormal lymph blast (abnormal lymph blast); and Atypical lymph (atypical lymphocytes). Each color represents a specific cell component. Furthermore, each of the five categories of statistical cells is analyzed independently. For each category, side scattered light (SSC) is used to obtain the differences in the complexity of the internal structure of different white blood cells. Side fluorescence (SFL) is used to obtain the differences in the types and number of nucleic acids and organelles of different white blood cells. The SSC is used as the horizontal axis and the SFL is used as the vertical axis for differential counting to construct a cell scatter plot.

[0048] It should be noted that, through research, it is found that the scatter plot data naturally has a Gaussian distribution prior, that is, most of the points are near the mean, and only a few points have a large variance. Each cell type can be regarded as an independent Gaussian distribution, such as Figure 3 As shown, Figure 3 (a) is an overview of the five types of data for abnormal samples (M3 leukemia). Figure 3 (b) is an overview of the five types of data for normal samples.

[0049] In addition, the abnormal cell environment will be significantly different from the normal cell environment in the scatter plot. Based on this, the present invention aims to find problems in the scatter plot of blood routine results as soon as possible, thereby greatly saving the analysis and review time of the results and improving work efficiency.

[0050] Step 120: pre-processing the cell scattergram using an expansion algorithm to obtain a pre-processing result.

[0051] To enhance the distinction between the abnormal sample's cell scatter plot image and the normal sample's cell scatter plot image, and to better distinguish the two, the cell scatter plot image is pre-processed using a dilation algorithm in step 120. Based on this, if the abnormal sample's cell scatter plot image has a large number of positive pixels (i.e., abnormal), the dilation algorithm can also be used to further increase the number of positive pixels, thereby widening the gap between the abnormal sample's cell scatter plot image and the normal image, making screening easier.

[0052] Step 130: Based on the preprocessing result, a predetermined target area selection frame is used to select a target area, where the target area selection frame is determined using a large number of cell scatter plot samples having target blood indicator characteristics.

[0053] In step 130 , it should be emphasized that the present invention does not analyze the entire image. Instead, it is necessary to find the effective target area of interest in the pre-processing results for subsequent screening.

[0054] Research has found that cell scatter plots of specific blood markers exhibit specific regional characteristics. For example, a prominent feature of M3 leukemia in a scatter plot is a right triangle with the hypotenuse facing left in the center of the image. Based on this, different target area selection boxes can be set for different blood marker characteristics to accurately locate the target area.

[0055] Step 140: extracting abnormal characteristic pixel points in the target area, and performing blood sample index screening based on the extraction results to obtain screening results.

[0056] After obtaining the target area, the abnormal characteristic pixels are extracted in the target area through the prior knowledge of the target blood indicator characteristics. The blood sample indicators are screened based on the abnormal characteristic pixels to determine whether the blood sample to be screened is a normal sample, thereby obtaining the screening result.

[0057] Based on the above embodiment, in some embodiments, the abnormal characteristic pixel point is a pixel point with a pixel value of 0.

[0058] Specifically, the embodiment of the present invention defines a concept: when the pixel value of the grayscale image is 0, the pixel is considered to exhibit a positive trait, that is, an abnormal trait pixel, or a positive trait pixel.

[0059] It should be noted that the screening method includes counting the number of abnormal trait pixels and making a normal / abnormal judgment based on the number.

[0060] In some embodiments, blood sample indicator screening includes counting the number of abnormal pixels.

[0061] This method uses regional features commonly found in cell scatter plots that reflect target blood markers to extract target regions. It then uses the features of abnormal pixel points to screen blood sample markers. This approach eliminates the need for neural network parameter training, resulting in low cost and high software algorithm robustness and accuracy. Furthermore, direct communication between the user and the terminal facilitates operation, ensuring a consistent field of view while maintaining quality.

[0062] The following further describes the preprocessing performed using the expansion algorithm in step 120. In some embodiments, the cell scattergram is preprocessed using the expansion algorithm to obtain a preprocessing result, specifically including:

[0063] Performing grayscale processing on the cell scattergram to obtain a grayscale image;

[0064] Binarization is performed on the grayscale image to obtain a preprocessing result.

[0065] Specifically, if Figure 4 As shown, Figure 4 (a) is the original image of a cell scatter plot. Figure 4 (b) is the image after the image dilation operation in (a). Figure 4 (c) is the original image of another cell scatter plot. Figure 4 (d) shows the image in (c) after expansion. It should be noted that, in order to highlight the differences between the cell scatter plots of abnormal samples and normal cells from a graphical perspective, the present invention ignores the original concept of scatter plot partitioning. This embodiment of the present invention uses an expansion algorithm to convert the three-channel cell scatter plot image into a grayscale image. A binarization operation is performed on the grayscale image to obtain a preprocessing result. Subsequent blood sample indicator screening is performed based on the preprocessing result.

[0066] In a specific embodiment, the binarization threshold in the grayscale image is set to 50 to perform binarization processing.

[0067] The embodiment of the present invention directly uses the processed grayscale image for screening, which increases the difference between the cell scatter plot image of the abnormal sample and the normal cell scatter plot image, makes the two better distinguishable, and increases the accuracy of the screening result.

[0068] The following further describes the determination of the target region selection box. In some embodiments, the target region selection box is determined using a large number of cell scatter plot samples having target blood indicator characteristics, specifically including:

[0069] Obtain a large number of cell scatter plot samples with target blood indicator characteristics;

[0070] Using a mix-up algorithm to fuse the cell scatter plot samples to obtain a fusion result;

[0071] The pixels with abnormal distribution in the fusion result are selected to obtain a target area selection box.

[0072] Specifically, because the cell scatter plots of a given blood marker feature have specific regional characteristics, embodiments of the present invention use a mix-up algorithm to fuse a large number of acquired cell scatter plot samples with the target blood marker feature to obtain a fused result. The fused image can be used to determine the regional characteristics of the abnormal distribution of the specific region of the target blood marker feature, and the target region selection box can be set based on these regional characteristics.

[0073] More specifically, a geometric shape is used to select all pixels with abnormal distribution, and this shape is the target area selection box.

[0074] In order to further explain the determination of the target area selection frame in more detail, a specific embodiment is given. In this embodiment, the target blood indicator feature is set to M3 leukemia.

[0075] It is important to note that M3 leukemia has a significant impact on human health. Bleeding is the primary symptom, characterized by rapid and profuse bleeding, which can also occur in the brain, lungs, and digestive tract. Patients initially experience massive internal bleeding, which can be life-threatening. Infection is the most common complication, including bacterial, viral, and fungal infections, commonly affecting the mouth, lungs, and skin. Severe cases can develop sepsis and septic shock. Symptoms associated with normal bone marrow hematopoietic function include anemia, bleeding, infection, and fever. Symptoms related to leukemic cell infiltration include enlarged liver, spleen, and lymph nodes, as well as bone pain. Although currently considered the most treatable type of leukemia, with cure rates often reaching 90%, the disease progresses rapidly and has a significant bleeding tendency. Without timely diagnosis and treatment, the mortality rate is extremely high.

[0076] The early symptoms of M3 leukemia are not obvious and may be confused with other diseases. Routine blood tests cannot clearly distinguish M3 from other diseases, so early M3 is difficult to screen. In addition, the incidence of M3 accounts for 6% to 9% of acute leukemia. Clinically, the main symptoms are fever, infection, anemia, and bleeding, especially intracranial hemorrhage, which is common and one of the causes of death. It is also prone to complications such as disseminated intravascular coagulation (DIC). The mechanism of its occurrence is mainly related to the coarse particles contained in the plasma of leukemic promyelocytes. These particles have been proven to be lysosomes, which contain rich tissue thromboplastin-like procoagulants. During chemotherapy or infection, a large number of leukemic promyelocytes are lysed and destroyed, and their particles are released into the blood circulation, activating the exogenous coagulation system and causing DIC.

[0077] For blood samples with M3 leukemia, abnormal promyelocytes (NEPs) in the bone marrow should be ≥50%, which is generally considered the diagnostic standard for M3. When the percentage is <50% to ≥30%, the promyelocyte / myelocyte ratio should be greater than 3:1. However, current instruments cannot exclude M3 leukemia based on this morphological rule, requiring manual review.

[0078] The embodiment of the present invention uses a mix-up algorithm to fuse all M3 positive scatter plot samples. Through the study of the fused images, it is found that the cell scatter plot of M3 leukemia patients will present a right triangle shape with the right angle side to the right in a specific area. On this basis, for this type of target blood indicator feature, this embodiment uses a right triangle shape to frame all abnormally distributed pixels. The shape of the right triangle is the target area selection box. In this way, through a large number of M3 positive images, we have fixed the target area: the right triangle area, such as Figure 5 shown.

[0079] The following further describes step 140. In some embodiments, extracting abnormal pixel points in the target area and performing blood sample index screening based on the extraction results to obtain screening results specifically includes:

[0080] Extracting abnormal pixel points in the target area to obtain an extraction result;

[0081] Counting the number of abnormal pixel points in the extraction result to obtain a target number;

[0082] The screening result is obtained based on the target quantity and the preset quantity threshold.

[0083] Specifically, after obtaining the target area, the abnormal trait pixels in the target area are extracted, and then the number of positive trait pixels (abnormal trait pixels) is counted according to the extraction results. The target number obtained by statistics is compared with the preset number threshold to obtain the screening result.

[0084] Furthermore, based on the above embodiment, the screening result is obtained according to the target number and the preset number threshold, specifically including:

[0085] When the target number is greater than the preset number threshold, determining that the screening result is a sample abnormality;

[0086] When the target number is less than or equal to the preset number threshold, the screening result is determined to be a normal sample.

[0087] Specifically, for a specific target blood marker characteristic, the preset quantity threshold is different. For example, in one specific embodiment, the target blood marker characteristic is set to M3 leukemia, and the preset quantity threshold is set to 60. If the target quantity exceeds the preset quantity threshold, the blood sample to be screened is considered positive, that is, the screening result is abnormal. Conversely, if the target quantity does not exceed the preset quantity threshold, the blood sample to be screened is considered negative, that is, the screening result is normal.

[0088] It is important to emphasize that the preset threshold is also the lowest critical value obtained by counting abnormal pixel counts within a priori target regions using a large number of cell scatter plot samples with target blood marker characteristics. The specific method is similar to that used to determine the target region selection box and will not be further described in detail in this disclosure.

[0089] The present invention is applicable to the screening of different blood indicators, which can be achieved by setting different target area selection boxes and preset quantity thresholds, and has sufficient openness.

[0090] The present invention provides a method for screening blood sample indicators based on a cell scatter plot, which comprises obtaining a cell scatter plot of a blood sample to be screened; preprocessing the cell scatter plot using an expansion algorithm to obtain a preprocessing result; selecting a target area using a predetermined target area selection box based on the preprocessing result to obtain a target area; wherein the target area selection box is determined using a large number of cell scatter plot samples having target blood indicator characteristics; extracting abnormal trait pixels in the target area, and performing blood sample indicator screening based on the extraction result to obtain a screening result. The present invention extracts the target area of the cell scatter plot of the blood sample to be screened using a fixed target area selection box, and performs blood sample indicator screening based on the abnormal trait pixels in the target area. The present invention does not involve the training of neural network parameters, and achieves low-cost and high-accuracy blood sample indicator screening.

[0091] The blood sample index screening device based on cell scattergram provided by the present invention is described below. The blood sample index screening device based on cell scattergram described below and the blood sample index screening method based on cell scattergram described above can be referenced to each other. Figure 6 As shown, the device includes the following modules:

[0092] An acquisition unit 610 is used to acquire a cell scattergram of the blood sample to be screened;

[0093] A preprocessing unit 620 is configured to preprocess the cell scattergram using an expansion algorithm to obtain a preprocessing result;

[0094] A region unit 630 is configured to select a target region using a predetermined target region selection frame based on the preprocessing result to obtain a target region; wherein the target region selection frame is determined using a large number of cell scatter plot samples having target blood indicator characteristics;

[0095] The screening unit 640 is used to extract abnormal characteristic pixel points in the target area, and perform blood sample index screening based on the extraction results to obtain screening results.

[0096] According to the present invention, a blood sample index screening device based on cell scattergram is provided, which uses a large number of cell scattergram samples with target blood index characteristics to determine a target area selection frame, specifically including:

[0097] Obtain a large number of cell scatter plot samples with target blood indicator characteristics;

[0098] Using a mix-up algorithm to fuse the cell scatter plot samples to obtain a fusion result;

[0099] The pixels with abnormal distribution in the fusion result are selected to obtain a target area selection box.

[0100] According to a blood sample index screening device based on a cell scattergram provided by the present invention, the cell scattergram is preprocessed using an expansion algorithm to obtain a preprocessing result, specifically comprising:

[0101] Performing grayscale processing on the cell scattergram to obtain a grayscale image;

[0102] Binarization is performed on the grayscale image to obtain a preprocessing result.

[0103] According to a blood sample index screening device based on a cell scattergram provided by the present invention, abnormal characteristic pixel points in the target area are extracted, and blood sample index screening is performed based on the extraction results to obtain screening results, specifically including:

[0104] Extracting abnormal pixel points in the target area to obtain an extraction result;

[0105] Counting the number of abnormal pixel points in the extraction result to obtain a target number;

[0106] The screening result is obtained based on the target quantity and the preset quantity threshold.

[0107] According to the present invention, a blood sample index screening device based on a cell scattergram is provided, wherein a screening result is obtained according to the target number and a preset number threshold, specifically comprising:

[0108] When the target number is greater than the preset number threshold, determining that the screening result is a sample abnormality;

[0109] When the target number is less than or equal to the preset number threshold, the screening result is determined to be a normal sample.

[0110] According to the blood sample index screening device based on cell scattergram provided by the present invention, the abnormal trait pixel point is a pixel point with a pixel value of 0.

[0111] The blood sample index screening device based on cell scatter plot provided by the present invention is implemented by obtaining a cell scatter plot of a blood sample to be screened; preprocessing the cell scatter plot using an expansion algorithm to obtain a preprocessing result; selecting a target area using a predetermined target area selection frame based on the preprocessing result to obtain a target area; wherein the target area selection frame is determined using a large number of cell scatter plot samples having target blood index characteristics; extracting abnormal trait pixels in the target area, and performing blood sample index screening based on the extraction result to obtain a screening result. The present invention extracts the target area of the cell scatter plot of the blood sample to be screened using a fixed target area selection frame, and performs blood sample index screening based on the abnormal trait pixels in the target area. The present invention does not involve the training of neural network parameters, and achieves low-cost and high-accuracy blood sample index screening.

[0112] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute a blood sample index screening method based on a cell scattergram, the method comprising: obtaining a cell scattergram of a blood sample to be screened; preprocessing the cell scattergram using an expansion algorithm to obtain a preprocessing result; selecting a target area using a predetermined target area selection box based on the preprocessing result to obtain a target area; wherein the target area selection box is determined using a large number of cell scattergram samples having target blood index characteristics; extracting abnormal characteristic pixels in the target area, and screening the blood sample index based on the extraction result to obtain a screening result.

[0113] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0114] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the blood sample index screening method based on the cell scatter plot provided by the above methods, the method including: obtaining a cell scatter plot of the blood sample to be screened; preprocessing the cell scatter plot with an expansion algorithm to obtain a preprocessing result; based on the preprocessing result, using a predetermined target area selection box to select a target area; wherein the target area selection box is determined using a large number of cell scatter plot samples with target blood index characteristics; extracting abnormal trait pixels in the target area, and screening the blood sample indicators according to the extraction result to obtain a screening result.

[0115] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the blood sample index screening method based on cell scatter plots provided by the above-mentioned methods, the method comprising: obtaining a cell scatter plot of the blood sample to be screened; preprocessing the cell scatter plot using an expansion algorithm to obtain a preprocessing result; based on the preprocessing result, selecting a target area using a predetermined target area selection box to obtain a target area; wherein the target area selection box is determined using a large number of cell scatter plot samples having target blood index characteristics; extracting abnormal trait pixels in the target area, and screening the blood sample indicators based on the extraction result to obtain a screening result.

[0116] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0117] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A blood sample index screening method based on cell scattergram, characterized in that: include: Obtaining a cell scatter plot of the blood sample to be screened; Preprocessing the cell scattergram using an expansion algorithm to obtain a preprocessing result; Based on the preprocessing result, a predetermined target region selection frame is used to select a target region, where the target region selection frame is determined using a large number of cell scatter plot samples having target blood indicator characteristics; Abnormal trait pixel points in the target area are extracted, and blood sample index screening is performed based on the extraction results to obtain screening results.

2. The blood sample index screening method based on cell scattergram according to claim 1, characterized in that: Utilize a large number of cell scatter plot samples with target blood index characteristics to determine the target area selection frame, including: Obtain a large number of cell scatter plot samples with target blood indicator characteristics; Using a mix-up algorithm to fuse the cell scatter plot samples to obtain a fusion result; The pixels with abnormal distribution in the fusion result are selected to obtain a target area selection box.

3. The blood sample index screening method based on cell scattergram according to claim 1, characterized in that: The cell scatter plot is preprocessed using an expansion algorithm to obtain a preprocessing result, specifically including: Performing grayscale processing on the cell scattergram to obtain a grayscale image; Binarization is performed on the grayscale image to obtain a preprocessing result.

4. The method for screening blood sample indicators based on cell scattergram according to claim 1, characterized in that: Extracting abnormal pixel points in the target area, and screening blood sample indicators based on the extraction results to obtain screening results, specifically including: Extracting abnormal pixel points in the target area to obtain an extraction result; Counting the number of abnormal pixel points in the extraction result to obtain a target number; The screening result is obtained based on the target quantity and the preset quantity threshold.

5. The method for screening blood sample indicators based on cell scattergram according to claim 4, characterized in that: The screening results are obtained based on the target quantity and the preset quantity threshold, including: When the target number is greater than the preset number threshold, determining that the screening result is a sample abnormality; When the target number is less than or equal to the preset number threshold, the screening result is determined to be a normal sample.

6. The method for screening blood sample indicators based on cell scattergram according to claim 1, characterized in that: The abnormal characteristic pixel point is a pixel point with a pixel value of 0.

7. A blood sample index screening device based on cell scattergram, characterized in that: include: an acquisition unit, used for acquiring a cell scattergram of a blood sample to be screened; a preprocessing unit, configured to preprocess the cell scattergram using an expansion algorithm to obtain a preprocessing result; A region unit, configured to select a target region using a predetermined target region selection frame based on the preprocessing result to obtain a target region; wherein the target region selection frame is determined using a large number of cell scatter plot samples having target blood indicator characteristics; The screening unit is used to extract abnormal characteristic pixel points in the target area, and screen the blood sample indicators according to the extraction results to obtain the screening results.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the blood sample index screening method based on cell scattergram according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the blood sample index screening method based on cell scattergram according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the blood sample index screening method based on cell scattergram according to any one of claims 1 to 6 is implemented.

Images