Methods, apparatus, computer equipment, and storage media for selecting red blood cell detection areas.

Abstract

This application relates to a method, apparatus, computer equipment, and storage medium for selecting red blood cell detection regions. The method involves inputting a cell image into a pre-trained deep neural network to predict cell distribution and generate a first heatmap. Regions with more uniform cell distribution correspond to higher heatmap values. The first heatmap is then filtered using N preset filter boxes of different sizes to obtain N second heatmaps. The coordinates of the highest heatmap value in each second heatmap are extracted, and a selection box of the same size as the corresponding filter box is generated centered on the coordinates of the highest heatmap value on the cell image. Cell edges within each selection box are extracted, and the circular features of cells are detected based on these edges. Cells within the selection boxes are then screened based on these circular features, and the number of red blood cells within each selection box is counted. The selection box with the closest red blood cell count to the target count is selected as the red blood cell detection region, effectively improving the efficiency of red blood cell analysis and detection.

Description

Technical Field

[0001] This application relates to the field of cell detection technology, and in particular to a method, apparatus, computer equipment, and storage medium for selecting red blood cell detection areas. Background Technology

[0002] Red blood cell morphology analysis is an important diagnostic method in medical testing, especially in the diagnosis of hematological diseases and anemia. Doctors need to make diagnoses based on the size, shape, and distribution of red blood cells in cell images. To improve diagnostic efficiency and accuracy, it is usually necessary to detect a target number of red blood cells within a relatively uniformly distributed area; this area is designated as the red blood cell detection area. As a crucial step in red blood cell morphology analysis, selecting the red blood cell detection area is of paramount importance.

[0003] In existing technologies, appropriate red blood cell detection areas are selected by manual observation and counting. However, manual observation and counting are easily affected by the observer's subjective judgment and are time-consuming, resulting in low red blood cell analysis and detection efficiency in existing technologies.

[0004] There is currently no effective solution to the problem of low red blood cell analysis efficiency caused by manually observing and counting to select appropriate red blood cell detection areas in existing technologies. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, and computer-readable storage medium for selecting red blood cell detection areas to address the aforementioned technical problems, thereby solving the problem of low red blood cell analysis and detection efficiency caused by manual observation and counting to select appropriate red blood cell detection areas in related technologies.

[0006] In a first aspect, embodiments of this application provide a method for selecting a red blood cell detection region. The method is used to select a red blood cell detection region from a cell image, and includes the following steps:

[0007] The cell image is input into a pre-trained deep neural network to obtain a prediction result of the cell distribution in the cell image. Based on the prediction result, a first heat map corresponding to the cell image is generated. In the first heat map, the heat value is higher for areas where the cell distribution in the cell image is more uniform.

[0008] The first heatmap is smoothed by mean filtering using N preset filter boxes of different sizes to obtain N second heatmaps after filtering; where N is an integer greater than or equal to 1.

[0009] Extract the coordinates of the position with the largest heat value in each of the second heat maps, and generate a selection box with the same size as the corresponding filter box, centered on the coordinates of the position with the largest heat value on the cell image;

[0010] Extract the cell edges in each of the selected regions and detect the circular features of the cells based on the cell edges;

[0011] Cells within the selected area are filtered based on the detected circular features. The number of red blood cells in each selected area is counted, and the selected area with the red blood cell count closest to the target count is taken as the red blood cell detection area.

[0012] In one embodiment, extracting the cell edges within each selection box includes the following steps:

[0013] The Canny edge detection algorithm is used to extract the cell edges in each selected area.

[0014] In one embodiment, the detection of the circular features of cells based on cell edges includes the following steps:

[0015] The circular features of cells are detected based on cell edges using Hough transform.

[0016] In one embodiment, the pre-trained deep neural network is based on the MobileNetV3 small network model.

[0017] Secondly, this application also provides a red blood cell detection area selection device, the device including a generation module, a filtering module, an extraction module, a detection module and a screening module;

[0018] The generation module is used to input the cell image into a pre-trained deep neural network, obtain a prediction result of the cell distribution in the cell image, and generate a first heat map corresponding to the cell image based on the prediction result. In the first heat map, the heat value is higher for areas where the cell distribution in the cell image is more uniform.

[0019] The filtering module is used to perform mean filtering and smoothing on the first heat map using N preset filter boxes of different sizes to obtain N filtered second heat maps; where N is an integer greater than or equal to 1.

[0020] The extraction module is used to extract the coordinate position of the largest heat value in each of the second heat maps, and generate a selection box with the same size as the corresponding filter box, centered on the coordinate position of the largest heat value on the cell image.

[0021] The detection module is used to extract the cell edges in each selected area and detect the circular features of the cells based on the cell edges;

[0022] The filtering module is used to filter cells within the selection box based on the detected circular features, count the number of red blood cells in each selection box, and select the selection box whose red blood cell count is closest to the target count as the red blood cell detection area.

[0023] Thirdly, this embodiment provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0024] Fourthly, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect above.

[0025] The aforementioned red blood cell detection region selection method, apparatus, computer equipment, and computer-readable storage medium are used to select red blood cell detection regions from cell images. The method involves inputting the cell image into a pre-trained deep neural network to obtain a prediction result of the cell distribution in the cell image. Based on the prediction result, a first heatmap corresponding to the cell image is generated. In the first heatmap, the more uniform the cell distribution in the cell image, the higher the heat value. The first heatmap is smoothed by mean filtering using N preset filter boxes of different sizes to obtain N filtered second heatmaps, where N is an integer greater than or equal to 1. The coordinates of the maximum heat value in each second heatmap are extracted, and a selection box of the same size as the corresponding filter box is generated centered on the coordinates of the maximum heat value in the cell image. Cell edges in each selection box are extracted, and circular features of the cells are detected based on the cell edges. Cells within the selection boxes are filtered based on the detected circular features, and the number of red blood cells in each selection box is counted. The selection box with the closest red blood cell count to the target count is selected as the red blood cell detection region. This application introduces artificial intelligence technology into medical image analysis. By using deep learning algorithms to extract features and segment regions of red blood cell images, it can quickly and efficiently select red blood cell detection areas, effectively improving the efficiency of red blood cell analysis and detection. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0027] Figure 1This is an application scenario diagram of the red blood cell detection area selection method provided in the embodiments of this application;

[0028] Figure 2 This is a flowchart of a red blood cell detection region selection method provided in the embodiments of this application;

[0029] Figure 3 This is a schematic diagram of the first heatmap obtained by processing a cell image using a pre-trained deep neural network in the red blood cell detection region selection method provided in the embodiments of this application.

[0030] Figure 4 This is a schematic diagram illustrating the effect of the red blood cell detection region selection method based on cell edge detection of the circular features of cells according to the embodiments of this application;

[0031] Figure 5 A schematic diagram of the structure of the red blood cell detection area selection device provided in the embodiments of this application;

[0032] Figure 6 A schematic diagram of the structure of a computer device provided in the embodiments of this application. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to 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. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0034] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0035] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0036] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0037] Figure 1 This diagram illustrates an application scenario for a red blood cell detection region selection method provided in one embodiment of this application. Figure 1As shown, data transmission between server 101 and mobile terminal 102 can be performed via network. Mobile terminal 102 is used to acquire cell images and transmit them to server 101. After receiving the cell images, server 101 inputs them into a pre-trained deep neural network to obtain a prediction result of the cell distribution in the cell images. Based on the prediction result, a first heatmap corresponding to the cell images is generated. In the first heatmap, the more uniform the cell distribution in the cell image, the higher the heat value. Server 101 uses N preset filter boxes of different sizes to perform mean filtering and smoothing on the first heatmap, obtaining N filtered second heatmaps. Where N is an integer greater than or equal to 1; server 101 then extracts the coordinates of the maximum heat value in each second heatmap, and generates a selection box with the same size as the corresponding filter box, centered on the coordinates of the maximum heat value on the cell image; then server 101 extracts the cell edges in each selection box and detects the circular features of cells based on the cell edges; finally, server 101 filters the cells in the selection boxes based on the detected circular features, counts the number of red blood cells in each selection box, and takes the selection box with the closest number of red blood cells to the target number as the red blood cell detection area. Server 101 can be implemented by a standalone server or a server cluster composed of multiple servers, and mobile terminal 102 can be any type of image acquisition device.

[0038] This application provides a method for selecting red blood cell detection regions from a cell image, such as... Figure 2 As shown, the method includes the following steps:

[0039] Step S210: Input the cell image into a pre-trained deep neural network to obtain the prediction result of the cell distribution in the cell image. Based on the prediction result, generate a first heat map corresponding to the cell image. In the first heat map, the heat value is higher for areas with more uniform cell distribution in the cell image.

[0040] Specifically, the pre-trained deep neural network in this application can be based on the MobileNetV3 small network model, and trained using a large number of cell images to obtain the pre-trained deep neural network in this application. In this application, assuming the pre-trained neural network model is represented by F(⋅;θ), where θ represents the network parameters; and the cell image is represented by I, then the first heatmap H generated by processing the cell image I using the pre-trained deep neural network F(⋅;θ) is represented as follows:

[0041]

[0042] Deep learning networks are optimized using the maximum entropy loss function, which has the following form:

[0043]

[0044] in, and These are the true labels and predicted values.

[0045] Furthermore, this application utilizes a pre-trained deep neural network to predict cell images, and a schematic diagram of the first heatmap generated based on the prediction results can be found in [reference needed]. Figure 3 ,exist Figure 3 In the diagram, the lighter the color of the area, the higher the heat value, indicating a more uniform cell distribution.

[0046] Step S220: The first heat map is smoothed by mean filtering using N preset filter boxes of different sizes to obtain N second heat maps after filtering; where N is an integer greater than or equal to 1.

[0047] Specifically, the filter box in this application is a rectangular box. Assuming the filter box in this application is represented by K*K, the first heatmap H is smoothed by mean filtering using the filter box to obtain N second heatmaps H', as shown below:

[0048]

[0049] Step S230: Extract the coordinates of the position with the largest thermal value in each second thermal map, and generate a selection box with the same size as the corresponding filter box, centered on the coordinates of the position with the largest thermal value on the cell image.

[0050] Specifically, extract the coordinates (x, y) of the location with the largest thermal value in each second heatmap. k， y k The calculation formula for ) is as follows:

[0051]

[0052] Using the coordinates (x, y) of the cell image corresponding to the location with the highest thermal value k， y k A selection box with the same size as the corresponding filter box is generated centered on B. k Finally, a set of N selection boxes of different sizes {B1, B2, ..., B} is obtained. N},in:

[0053]

[0054] Step S240: Extract the cell edges in each selection box and detect the circular features of the cells based on the cell edges.

[0055] Specifically, the Canny edge detection algorithm can be used to extract the cell edges in each selected area, and the circular features of cells can be detected based on the cell edges using Hough transform. See the schematic diagram illustrating the effect of detecting the circular features of cells based on cell edges. Figure 4 .

[0056] Step S250: Based on the detected circular features, the cells in the selection box are screened, the number of red blood cells in each selection box is counted, and the selection box with the number of red blood cells closest to the target number is taken as the red blood cell detection area.

[0057] In this application, the cell radius can be determined based on the detected circular features. Cells within a selection box are then screened based on whether their radius meets the requirement for red blood cell radius. The number of red blood cells within each selection box is then counted. Finally, the selection box with the closest red blood cell count to the target count is selected as the red blood cell detection area. Specifically, the parametric equation based on the detected circular features is assumed to be:

[0058]

[0059] Assume that red blood cells must satisfy the condition that their radius is within r. min With r max Between these points, the formula for counting the number of red blood cells within each selection box is as follows:

[0060]

[0061] Furthermore, as one implementation method, it is also possible to return the target number N. target The closest selection area B k The error function is defined as follows:

[0062]

[0063] In existing technologies, appropriate red blood cell detection areas are selected by manual observation and counting. However, manual observation and counting are easily affected by the observer's subjective judgment and are time-consuming, resulting in low red blood cell analysis and detection efficiency in existing technologies.

[0064] To address the aforementioned issues, this application provides a method for selecting red blood cell detection regions from cell images. The method involves inputting the cell image into a pre-trained deep neural network to obtain a prediction of the cell distribution. Based on the prediction, a first heatmap corresponding to the cell image is generated. In the first heatmap, regions with more uniform cell distribution correspond to higher heat values. The first heatmap is smoothed using mean filtering with N preset filter boxes of different sizes to obtain N filtered second heatmaps, where N is an integer greater than or equal to 1. The coordinates of the highest heat value in each second heatmap are extracted, and a selection box of the same size as the corresponding filter box is generated centered on the coordinates of the highest heat value in the cell image. Cell edges are extracted from each selection box, and circular features of the cells are detected based on these edges. Cells within the selection boxes are filtered based on the detected circular features, and the number of red blood cells within each selection box is counted. The selection box with the closest red blood cell count to the target count is selected as the red blood cell detection region. This application introduces artificial intelligence technology into medical image analysis. By using deep learning algorithms to extract features and segment regions of red blood cell images, it can quickly and efficiently select red blood cell detection areas, effectively improving the efficiency of red blood cell analysis and detection.

[0065] Figure 5 This is a schematic diagram of a red blood cell detection area selection device according to an embodiment of the present invention, such as... Figure 5 As shown, a red blood cell detection area selection device 30 is provided, which includes a generation module 31, a filtering module 32, an extraction module 33, a detection module 34, and a screening module 35;

[0066] The generation module 31 is used to input the cell image into a pre-trained deep neural network, obtain the prediction result of the cell distribution in the cell image, and generate a first heat map corresponding to the cell image based on the prediction result. In the first heat map, the heat value is higher for the more uniformly distributed cells in the cell image.

[0067] The filtering module 32 is used to perform mean filtering and smoothing on the first heat map using N preset filter boxes of different sizes to obtain N filtered second heat maps; where N is an integer greater than or equal to 1.

[0068] Extraction module 33 is used to extract the coordinate position of the maximum thermal value in each second thermal map, and generate a selection box with the same size as the corresponding filter box, centered on the coordinate position of the maximum thermal value on the cell image;

[0069] The detection module 34 is used to extract the cell edges in each selection box and detect the circular features of the cells based on the cell edges;

[0070] The filtering module 35 is used to filter cells within the selection box based on the detected circular features, count the number of red blood cells in each selection box, and select the selection box with the closest red blood cell count to the target count as the red blood cell detection area.

[0071] The aforementioned red blood cell detection region selection device 30 is used to select red blood cell detection regions from cell images. It inputs the cell image into a pre-trained deep neural network to obtain a prediction result of the cell distribution in the cell image. Based on the prediction result, it generates a first heatmap corresponding to the cell image. In the first heatmap, the more uniform the cell distribution in the cell image, the higher the heat value. The first heatmap is smoothed by mean filtering using N preset filter boxes of different sizes to obtain N filtered second heatmaps, where N is an integer greater than or equal to 1. The coordinates of the maximum heat value in each second heatmap are extracted, and a selection box of the same size as the corresponding filter box is generated centered on the coordinates of the maximum heat value in the cell image. Cell edges in each selection box are extracted, and circular features of the cells are detected based on the cell edges. Cells within the selection boxes are filtered based on the detected circular features, and the number of red blood cells in each selection box is counted. The selection box with the closest red blood cell count to the target count is selected as the red blood cell detection region. This application introduces artificial intelligence technology into medical image analysis. By using deep learning algorithms to extract features and segment regions of red blood cell images, it can quickly and efficiently select red blood cell detection areas, effectively improving the efficiency of red blood cell analysis and detection.

[0072] In one embodiment, the detection module 34 is also used to extract cell edges in each selection box using the Canny edge detection algorithm.

[0073] In one embodiment, the detection module 34 is also used to detect the circular features of cells based on cell edges using Hough transform.

[0074] In one embodiment, the pre-trained deep neural network is modeled after the MobileNetV3 small network model.

[0075] It should be noted that the above modules can be functional modules or program modules, and can be implemented in software or hardware. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or they can be 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.

[0076] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing 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 database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores a set of preset configuration information. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the aforementioned red blood cell detection region selection method.

[0077] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for selecting a red blood cell detection area. The display screen of the computer device may be a liquid crystal display (LCD) or an e-ink display. The input device of the computer device may be a touch layer covering the display screen, or buttons, a trackball, or a touchpad located on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0078] Those skilled in the art will understand that Figure 6 The 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.

[0079] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0080] The cell image is input into a pre-trained deep neural network to obtain the prediction result of the cell distribution in the cell image. Based on the prediction result, a first heat map corresponding to the cell image is generated. In the first heat map, the more uniform the cell distribution in the cell image, the higher the heat value.

[0081] The first heatmap is smoothed by mean filtering using N preset filter boxes of different sizes to obtain N filtered second heatmaps; where N is an integer greater than or equal to 1.

[0082] Extract the coordinates of the maximum heat value in each second heatmap, and generate a selection box with the same size as the corresponding filter box, centered on the coordinates of the maximum heat value on the cell image;

[0083] Extract the cell edges within each selection box and detect the circular features of the cells based on the cell edges;

[0084] Cells within the selected area are filtered based on the detected circular features. The number of red blood cells in each selected area is counted, and the selected area with the closest red blood cell count to the target count is taken as the red blood cell detection area.

[0085] In one embodiment, the processor further performs the following steps when executing the computer program:

[0086] The Canny edge detection algorithm is used to extract the cell edges in each selection box.

[0087] In one embodiment, the processor further performs the following steps when executing the computer program:

[0088] The circular features of cells are detected based on cell edges using Hough transform.

[0089] In one embodiment, the processor further performs the following steps when executing the computer program:

[0090] The pre-trained deep neural network is based on the MobileNetV3 small network model.

[0091] The aforementioned storage medium is used to select red blood cell detection regions from cell images. By inputting the cell image into a pre-trained deep neural network, the predicted cell distribution of the cell image is obtained. Based on the prediction results, a first heatmap corresponding to the cell image is generated. In the first heatmap, the more uniform the cell distribution in the cell image, the higher the heat value. The first heatmap is smoothed by mean filtering using N preset filter boxes of different sizes to obtain N filtered second heatmaps, where N is an integer greater than or equal to 1. The coordinate position of the maximum heat value in each second heatmap is extracted, and a selection box of the same size as the corresponding filter box is generated with the coordinate position of the maximum heat value on the cell image as the center. The cell edges in each selection box are extracted, and the circular features of the cells are detected based on the cell edges. Based on the detected circular features, the cells in the selection box are filtered, the number of red blood cells in each selection box is counted, and the selection box with the number of red blood cells closest to the target number is taken as the red blood cell detection region. This application introduces artificial intelligence technology into medical image analysis. By using deep learning algorithms to extract features and segment regions of red blood cell images, it can quickly and efficiently select red blood cell detection areas, effectively improving the efficiency of red blood cell analysis and detection.

[0092] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0093] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0094] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0095] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. 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 scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for selecting a red blood cell detection region, characterized in that, The method is used to select red blood cell detection regions from cell images, and the method includes the following steps: The cell image is input into a pre-trained deep neural network to obtain a prediction result of the cell distribution in the cell image. Based on the prediction result, a first heat map corresponding to the cell image is generated. In the first heat map, the heat value is higher for areas where the cell distribution in the cell image is more uniform. The first heatmap is smoothed by mean filtering using N preset filter boxes of different sizes to obtain N second heatmaps after filtering; where N is an integer greater than or equal to 1. Extract the coordinates of the position with the largest heat value in each of the second heat maps, and generate a selection box with the same size as the corresponding filter box, centered on the coordinates of the position with the largest heat value on the cell image; Extract the cell edges in each of the selected regions and detect the circular features of the cells based on the cell edges; Cells within the selected area are filtered based on the detected circular features. The number of red blood cells in each selected area is counted, and the selected area with the red blood cell count closest to the target count is taken as the red blood cell detection area.

2. The method for selecting the red blood cell detection area according to claim 1, characterized in that, Extracting the cell edges from each of the selected regions includes the following steps: The Canny edge detection algorithm is used to extract the cell edges in each selected area.

3. The method for selecting the red blood cell detection area according to claim 1, characterized in that, The method of detecting the circular features of cells based on cell edges includes the following steps: The circular features of cells are detected based on cell edges using Hough transform.

4. The method for selecting the red blood cell detection area according to claim 1, characterized in that, The pre-trained deep neural network is based on the MobileNetV3 small network model.

5. A red blood cell detection area selection device, characterized in that, The device includes a generation module, a filtering module, an extraction module, a detection module, and a screening module; The generation module is used to input the cell image of claim 1 into a pre-trained deep neural network, obtain a prediction result of the cell distribution of the cell image, and generate a first heat map corresponding to the cell image based on the prediction result. In the first heat map, the heat value of the area with more uniform cell distribution in the cell image is higher. The filtering module is used to perform mean filtering and smoothing on the first heatmap using N preset filter boxes of different sizes to obtain N filtered second heatmaps; where N is an integer greater than or equal to 1. The extraction module is used to extract the coordinate position of the largest heat value in each of the second heat maps, and generate a selection box with the same size as the corresponding filter box, centered on the coordinate position of the largest heat value on the cell image. The detection module is used to extract the cell edges in each selected area and detect the circular features of the cells based on the cell edges; The filtering module is used to filter cells within the selection box based on the detected circular features, count the number of red blood cells in each selection box, and select the selection box whose red blood cell count is closest to the target count as the red blood cell detection area.

6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, 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 4.

7. 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 4.

Images