Cell screening method, device, electronic equipment and computer program product

Abstract

The application discloses a cell screening method and device, electronic equipment and computer program product. The method comprises the following steps: acquiring a first image and a second image; determining a first reference cell corresponding to each of one or more to-be-screened cells from one or more reference cells based on the first image and the second image, and determining a first distance between each of the one or more to-be-screened cells and the corresponding first reference cell; screening one or more target cells from the one or more to-be-screened cells based on the determined one or more first distances, generating a third image, and outputting the third image to a cell cutting system; and the third image represents a mask image for displaying a cell contour of the one or more target cells.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a cell screening method, apparatus, electronic device, and computer program product. Background Technology

[0002] With the development of image processing technology, researchers are able to analyze biological tissues based on the processing of imaging images, enabling further life science research and clinical diagnosis. In practical applications, target cells to be analyzed can be first screened from the cells contained in the imaging image, then the target cells can be cut out using a cell cutting system, and finally the cut target cells can be analyzed to achieve the analysis of biological tissues.

[0003] In related technologies, during the screening of target cells, the spatial relationship between each cell to be screened and other cells in the imaging image is manually labeled. Then, the spatial relationship corresponding to each cell to be screened is matched with fixed screening conditions to perform cell screening based on the matching results. However, manual labeling is cumbersome, and the imaging image often contains a large number of cells to be screened, resulting in low screening efficiency and thus affecting the efficiency of biological tissue analysis. Summary of the Invention

[0004] To address the related technical issues, embodiments of this application provide a cell screening method, apparatus, electronic device, and computer program product.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides a cell screening method, the method comprising:

[0007] Acquire a first image and a second image; the first image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more cells to be screened in the target tissue; the second image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more reference cells in the target tissue; the reference cells are used to provide spatial relationship reference for the cells to be screened.

[0008] Based on the first image and the second image, a first reference cell corresponding to each cell to be screened in the one or more reference cells is determined, and a first distance between each cell to be screened and its corresponding first reference cell is determined.

[0009] Based on one or more determined first distances, one or more target cells are selected from the one or more cells to be screened to generate a third image and output the third image to the cell cutting system; the third image represents a mask image used to display the cell outlines of the one or more target cells.

[0010] This application also provides a cell screening device, including:

[0011] An acquisition unit is used to acquire a first image and a second image; the first image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more cells to be screened in the target tissue; the second image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more reference cells in the target tissue; the reference cells are used to provide spatial relationship reference for the cells to be screened.

[0012] The determining unit is configured to, based on the first image and the second image, determine the first reference cell corresponding to each cell to be screened in the one or more reference cells, and determine the first distance between each cell to be screened and the corresponding first reference cell in the one or more cells to be screened;

[0013] A screening unit is configured to screen one or more target cells from the one or more cells to be screened based on one or more determined first distances, to generate a third image and output the third image to a cell cutting system; the third image represents a mask image used to display the cell outlines of the one or more target cells.

[0014] This application also provides an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor.

[0015] When the processor runs the computer program, it performs the steps described in the above method.

[0016] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps described in the above method.

[0017] In this embodiment, a first image and a second image are acquired. The first image represents a mask image output by the cell imaging system after recognizing the cell contours of one or more cells to be screened in the target tissue. The second image represents a mask image output by the cell imaging system after recognizing the cell contours of one or more reference cells in the target tissue. The reference cells are used to provide spatial relationship references for the cells to be screened. Then, based on the first image and the second image, a first reference cell corresponding to each cell to be screened in one or more cells to be screened is determined from the one or more reference cells, and a first distance between each cell to be screened and its corresponding first reference cell is determined. Afterward, based on the determined one or more first distances, one or more target cells are screened from the one or more cells to be screened to generate a third image and output the third image to the cell cutting system. The third image represents a mask image used to display the cell contours of one or more target cells. In the above scheme, based on the mask image output by the cell imaging system, the first distance between each cell to be screened and the corresponding first reference cell is automatically determined. Therefore, compared with related technologies, the spatial relationship between the cells to be screened and the corresponding reference cells can be determined without manual annotation. Based on this, target cells are screened from one or more cells to be screened according to the determined first distance, realizing automatic batch screening of cells in the target tissue and improving screening efficiency. Furthermore, after screening the target cells, the scheme of this application generates the corresponding mask image and outputs the mask image to the cell cutting system, thereby improving cell cutting efficiency and mitigating the adverse effects of related technologies on the analysis efficiency of biological tissues. Attached Figure Description

[0018] Figure 1 A schematic diagram illustrating the implementation process of cell screening provided in an embodiment of this application;

[0019] Figure 2 A schematic diagram of a first image provided for an embodiment of this application;

[0020] Figure 3 A schematic diagram of a third image provided for an embodiment of this application;

[0021] Figure 4 A schematic diagram of a fourth image provided for an embodiment of this application;

[0022] Figure 5 A schematic diagram of a sixth image provided for an embodiment of this application;

[0023] Figure 6 A schematic diagram of a first interface provided in an embodiment of this application;

[0024] Figure 7This is a schematic diagram of the structure of a cell screening device provided in an embodiment of this application;

[0025] Figure 8 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0026] With the development of image processing technology, researchers are able to analyze biological tissues based on the processing of imaging images, enabling further life science research and clinical diagnosis. In practical applications, target cells to be analyzed can be first screened from the cells contained in the imaging image, then the target cells can be cut out using a cell cutting system, and finally the cut target cells can be analyzed to achieve the analysis of biological tissues.

[0027] In related technologies, during the screening of target cells, the spatial relationship between each cell to be screened and other cells in the imaging image is manually labeled. Then, the spatial relationship corresponding to each cell to be screened is matched with fixed screening conditions to perform cell screening based on the matching results. However, manual labeling is cumbersome, and the imaging image often contains a large number of cells to be screened, resulting in low screening efficiency and thus affecting the efficiency of biological tissue analysis.

[0028] Based on this, in this embodiment, a first image and a second image are acquired; wherein, the first image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more cells to be screened in the target tissue, and the second image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more reference cells in the target tissue, the reference cells being used to provide spatial relationship references for the cells to be screened; then, based on the first image and the second image, a first reference cell corresponding to each cell to be screened in one or more cells to be screened is determined from the one or more reference cells, and a first distance between each cell to be screened and its corresponding first reference cell is determined; subsequently, based on the determined one or more first distances, one or more target cells are screened from the one or more cells to be screened to generate a third image and output the third image to the cell cutting system, wherein, the third image represents a mask image used to display the cell contours of one or more target cells. In the above scheme, based on the mask image output by the cell imaging system, the first distance between each cell to be screened and the corresponding first reference cell is automatically determined. Therefore, compared with related technologies, the spatial relationship between the cells to be screened and the corresponding reference cells can be determined without manual annotation. Based on this, target cells are screened from one or more cells to be screened according to the determined first distance, realizing automatic batch screening of cells in the target tissue and improving screening efficiency. Furthermore, after screening the target cells, the scheme of this application generates the corresponding mask image and outputs the mask image to the cell cutting system, thereby improving cell cutting efficiency and mitigating the adverse effects of related technologies on the analysis efficiency of biological tissues.

[0029] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0030] This application provides a cell screening method. In practical applications, this method can be applied to an image processing system other than a cell imaging system and a cell cutting system. This image processing system can be used as a plug-in between the cell imaging system and the cell cutting system.

[0031] In practical applications, an image processing system can receive images from a cell imaging system based on the target tissue, perform corresponding image processing (e.g., cell screening), and then output the file to a cell cutting system so that the cell cutting system can cut the cells in the target tissue. Thus, when the output of the cell imaging system is incompatible with the input required by the cell cutting system, the image processing system can convert them through relevant processing, improving the flexibility and efficiency of cell cutting, and thereby improving the flexibility and efficiency of the analysis of the target tissue.

[0032] This image processing system can have a cell screening function. To highlight the cell screening function of the image processing system, it can also be called a cell screening system.

[0033] See Figure 1 The cell screening method provided in this application includes:

[0034] Step 101: Obtain the first image and the second image.

[0035] The first image represents a mask image output by the cell imaging system after recognizing the cell contours of one or more cells to be screened in the target tissue; the second image represents a mask image output by the cell imaging system after recognizing the cell contours of one or more reference cells in the target tissue; the reference cells are used to provide spatial relationship references for the cells to be screened.

[0036] Here, the target tissue can be understood as the biological tissue that the user needs to analyze. For example, the user can include researchers, and the biological tissue can include pathological tissue. The user can perform analyses such as tumor microenvironment or spatial proteomics based on the target tissue.

[0037] In practical applications, cell imaging systems can perform microscopic imaging of cells in target tissues, generating scanned images. After generating the scanned images, the cell imaging system can directly output them, or it can optimize the scanned images and output optimized scanned images, which can also be called analytical images. For example, optimization can include at least one or more of the following: saturation adjustment and brightness adjustment. For ease of description, the image output by the cell imaging system after cell imaging processing of the target tissue is referred to as an imaging image. That is, both the scanned image and the analytical image are referred to as imaging images. An imaging image may contain one or more imaged cells.

[0038] In practical applications, cell imaging systems can identify the contours of cells in a target tissue and then output a mask image based on the identified cell contours.

[0039] A mask image can be represented as a binary image, that is, each pixel in the mask image has only two values. Each pixel can be used to operate on pixels in the same position in the imaging image to indicate the target region where the cell is located in the imaging image. The contour of this region can be regarded as the cell contour.

[0040] For example, the value of each pixel in the mask image can include either 0 or 1. A pixel with a value of 0 represents a black pixel, which can be used to convert pixels at the same position in the image to a dark color, effectively weakening the image content at the same pixel position in the image. A pixel with a value of 1 represents a white pixel, which can be used to maintain the color of pixels at the same position in the image, effectively preserving the content at the same pixel position in the image. White areas in the mask image can represent the image area where the cell is located. It should be noted that the values ​​0 or 1 are merely examples. In practical applications, the pixel value can also be set to 0 or 255, where a pixel with a value of 0 represents a black pixel and a value of 255 represents a white pixel. The specific value method is not limited here.

[0041] In practical applications, the mask image and the imaging image can be directly superimposed to obtain a superimposed image. This superimposed image can contain only the cells indicated by the mask image, allowing the user to observe the image content corresponding to the cells indicated by the mask image without being disturbed by other image content. Alternatively, the mask image can be superimposed on the imaging image with a set transparency. In this superimposed image, the color brightness of the image content corresponding to the cells indicated by the mask image can be higher than that of other image content in the superimposed image. This allows the user to observe the entire image content while intuitively and quickly observing the image content corresponding to the cells indicated by the mask image.

[0042] In practical applications, a cell imaging system can identify cells for contour recognition and / or imaging based on user-inputted cell selection instructions, and output the corresponding mask image and / or imaging image. For example, the cell selection instructions input by the user into the cell imaging system can instruct the system to process astrocytes. Based on these instructions, the system can perform contour recognition and / or imaging of one or more astrocytes in the target tissue, and output the corresponding mask image and / or imaging image.

[0043] In practical applications, the cells in the first and second images can be determined by the cell imaging system based on different cell selection instructions input by the user.

[0044] Users can select cells in the target tissue as cells to be screened or reference cells based on their own needs, and then input a first cell selection instruction into the cell imaging system to make the cell imaging system output a first image, and input a second cell selection instruction into the cell imaging system to make the cell imaging system output a second image.

[0045] One or more cells to be screened in the target tissue may contain one or more cells to be analyzed for user intent analysis. Reference cells in the target tissue can provide spatial relationship references for the cells to be screened, so that the execution subject of the method in this embodiment can screen out the cells to be analyzed, that is, the target cells, from one or more cells to be screened.

[0046] It should be noted that when identifying cells, users may not know the exact location of the cells in the target tissue. For example, users may only need to determine the cell types corresponding to the cells to be screened and the reference cells.

[0047] For example, when a user intends to analyze astrocytes that are close to cancer cells, the user can identify astrocytes as cells to be screened and cancer cells as reference cells. Then, the user can input a first cell selection instruction into the cell imaging system so that the cell imaging system can perform cell contour recognition on the astrocytes and output a first image. The user can also input a second cell selection instruction into the cell imaging system so that the cell imaging system can perform cell contour recognition on the cancer cells and output a second image.

[0048] Step 102: Based on the first image and the second image, determine the first reference cell corresponding to each cell to be screened in one or more reference cells, and determine the first distance between each cell to be screened and the corresponding first reference cell in one or more cells to be screened.

[0049] In practical applications, the spatial relationship of each cell to be screened can be determined by referring to a specific reference cell, that is, by referring to the corresponding first reference cell. The first reference cell can be the reference cell among one or more reference cells that has the shortest center distance to the corresponding cell to be screened. The center distance can be understood as the geometric center distance.

[0050] In practical applications, the first distance can be used to describe the spatial relationship between the cell to be screened and the first reference cell. Compared with the center-to-center distance between the cell to be screened and the first reference cell, the first distance can more accurately describe the spatial relationship between the cell to be screened and the first reference cell.

[0051] Step 103: Based on the determined first distance, select one or more target cells from one or more cells to be screened to generate a third image and output the third image to the cell cutting system.

[0052] The third image represents a mask image used to display the cell outlines of one or more target cells.

[0053] In practical applications, a first distance can be determined for each cell to be screened based on set conditions, and the determination result can be used to determine whether the cell to be screened is identified as a target cell, so as to screen one or more target cells from one or more cells to be screened. For example, the set conditions may include: the first distance is within a set distance range.

[0054] After identifying one or more target cells, the image content in the first image related to these target cells can be processed to generate a third image. For example, the image region in the first image containing these target cells can be saved as the third image.

[0055] here, Figure 2 An example of a first image is provided, in which the white areas can be understood as image regions containing one or more cells to be screened. The method of this application embodiment can be derived from... Figure 2 One or more target cells are selected from one or more cells to be screened, thereby generating a third image. For example, the generated third image can be as follows: Figure 3 As shown, Figure 3 The white area in the image shown can be interpreted as the image region where the target cell is located.

[0056] After obtaining the third image, it can be directly output to the cell cutting system. After receiving the third image, the cell cutting system can cut out the cell entities in the target tissue. The cut-out cell entities correspond to the target cells, so that the user can perform further analysis on the target tissue.

[0057] After obtaining the third image, it can be adjusted and then output to the cell cutting system to enable the cell cutting system to cut out the target cells more accurately. For example, the adjustment process may include expanding the cell outline in the third image outward by a predetermined number of pixels, so that the image region related to the indicated cell in the third image can contain cells with complete morphology, thereby ensuring the integrity of the cells cut by the cell cutting system and improving the accuracy and efficiency of target tissue analysis.

[0058] After obtaining the third image, it can be superimposed on the imaging image corresponding to the target tissue, allowing users to intuitively observe the screening results.

[0059] In one embodiment, after generating the third image, the cell screening method provided in this application further includes:

[0060] The third image is superimposed on the fourth image with a set transparency to obtain the fifth image, and the fifth image is output; the fourth image represents the image output by the cell imaging system after performing cell imaging processing on the target tissue.

[0061] Here, the fourth image can be understood as the imaging image corresponding to the target tissue.

[0062] In practical applications, a predefined first function instruction can be called to process the third and fourth images, overlaying the third image onto the fourth image with a set transparency. For example, the first function instruction could include "cv2.addWeighted", with a set transparency of 0.5.

[0063] In the fifth image, the color brightness of the target cell indicated by the third image can be higher than that of the non-target cell corresponding image content in the fifth image. In this way, the user can observe the target cell corresponding image content intuitively and quickly while observing the entire image content of the fifth image, without having to frequently switch images to observe the third and fifth images separately. This allows for convenient review of the screening results and improves the accuracy and efficiency of the analysis of the target tissue.

[0064] In practical applications, after obtaining the third image, the cell area of ​​each target cell in the third image can be statistically analyzed, and the statistical data can be saved as a first file, which is then output as the first file. For example, the first file can be a comma-separated values ​​(CSV) file. In this way, users can analyze the cell area of ​​each target cell based on the first file, improving the accuracy and efficiency of the analysis of the target tissue.

[0065] In this embodiment, based on the mask image output by the cell imaging system, the first distance between each cell to be screened and the corresponding first reference cell is automatically determined. Compared with related technologies, this method does not require manual annotation to determine the spatial relationship between the cells to be screened and the corresponding reference cells. Based on this, target cells are screened from one or more cells to be screened according to the determined first distance, realizing automatic batch screening of cells in the target tissue and improving screening efficiency. Furthermore, after screening the target cells, this solution generates a corresponding mask image and outputs the mask image to the cell cutting system, thereby improving cell cutting efficiency and mitigating the adverse effects of related technologies on the analysis efficiency of biological tissues.

[0066] The method for determining the first distance will be further explained below.

[0067] In one embodiment, based on a first image and a second image, determining a first reference cell corresponding to each of the one or more cells to be screened from one or more reference cells, and determining a first distance between each cell to be screened and its corresponding first reference cell, includes:

[0068] For each cell to be screened, based on the first image and the second image, a second distance is determined between the cell to be screened and each reference cell in one or more reference cells, and a first reference cell corresponding to the cell to be screened is determined based on the obtained one or more second distances; the first reference cell represents the reference cell corresponding to the smallest second distance among one or more second distances;

[0069] The second distance corresponding to the first reference cell is compared with the first radius of the first covering circle of the first reference cell, and the first distance between the corresponding cell to be screened and the first reference cell is determined based on the comparison result; the center of the first covering circle of the first reference cell is characterized as the geometric center of the first reference cell, and the first covering circle of the first reference cell covers the first reference cell.

[0070] In practical applications, a predefined second function instruction can be called to process the first and second images respectively, in order to determine the geometric center of each cell to be screened in the first image and the geometric center of each reference cell in the second image. For example, the predefined second function instruction may include "cv2.connectedComponentsWithStats".

[0071] In practical applications, the second distance can characterize the distance between the geometric center of the corresponding cell to be screened and the geometric center of the corresponding reference cell. In this case, the second distance can be understood as the center distance between the cell to be screened and the reference cell.

[0072] In practical applications, before determining the second distance corresponding to each cell to be screened, some reference cells can be screened from one or more reference cells. Then, when determining the second distance, only the second distance between each cell to be screened and the screened reference cells is determined. Based on these second distances, the first reference cell is determined, thereby reducing the amount of computation and improving the efficiency of cell screening.

[0073] In one embodiment, before determining the second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image, the cell screening method provided in this application further includes:

[0074] One or more second reference cells are selected from one or more reference cells; the cell area of ​​the second reference cells is located within a set area range.

[0075] Correspondingly, based on the first image and the second image, a second distance is determined between the cell to be screened and each of the one or more reference cells, including:

[0076] Based on the first image and the second image, a second distance is determined between the cell to be screened and each of the one or more second reference cells.

[0077] In practical applications, a set third function instruction can be invoked to process the second image in order to determine the cell area of ​​each reference cell in the second image. For example, the set third function instruction may include: "cv2.connectedComponentsWithStats".

[0078] After determining the cell area of ​​each reference cell, reference cells whose cell area falls within a set area range can be selected from one or more reference cells, that is, one or more second reference cells can be selected.

[0079] In practical applications, the endpoints of the set area range can be determined based on the user's input in the first interface of the cell screening system. Thus, the embodiments of this application can dynamically determine the area range for cell screening based on the user's input, thereby improving the accuracy and flexibility of cell screening.

[0080] In practical applications, the first covering circle of the first reference cell can be connected to at least one point on the cell outline of the first reference cell.

[0081] The comparison result between the second distance corresponding to the first reference cell and the first radius of the first covering circle of the first reference cell can be used to describe the position of the geometric center of the first reference cell relative to the outline of the first covering circle, that is, to describe whether the geometric center of the first reference cell is located inside the first covering circle.

[0082] In one embodiment, determining the first distance between the corresponding cell to be screened and the first reference cell based on the comparison result includes:

[0083] If the comparison result indicates that the second distance corresponding to the first reference cell is greater than the first radius, the first difference is determined as the first distance; the first difference is characterized as the difference between the second distance corresponding to the first reference cell and the first radius; and / or,

[0084] If the comparison result indicates that the second distance corresponding to the first reference cell is less than the first radius, a negative value will be set as the first distance; and / or,

[0085] If the comparison result indicates that the second distance corresponding to the first reference cell is equal to the first radius, the first difference or a negative value is determined as the first distance.

[0086] In practical applications, if the comparison result indicates that the second distance corresponding to the first reference cell is greater than the first radius, it can be regarded as the geometric center of the cell to be screened being located outside the first covering circle of the first reference cell. In this case, the second distance can also be regarded as the shortest distance between the geometric center of the cell to be screened and the first covering circle.

[0087] If the comparison result indicates that the second distance corresponding to the first reference cell is less than the first radius, it can be considered that the geometric center of the cell to be screened is located inside the first covering circle of the first reference cell. In this case, setting a negative value can be used to indicate that the geometric center of the cell to be screened is located inside the first covering circle of the first reference cell. That is, it can be used to indicate this situation. For example, the set negative value can include -1.

[0088] If the comparison result indicates that the second distance corresponding to the first reference cell is equal to the first radius, it can be considered that the geometric center of the cell to be screened is located outside the first covering circle of the first reference cell, or it can be considered that the geometric center of the cell to be screened is located inside the first covering circle of the first reference cell. In practical applications, it can be set according to user needs, and there is no restriction here.

[0089] In practical applications, there are differences in cell morphology among different cells. The center-to-center distance between the cell to be screened and the reference cell cannot accurately describe the spatial relationship between the cells to be screened. If the center-to-center distance between the cell to be screened and the reference cell is directly compared with a set threshold, and the target cell is screened based on the comparison result, it is easy to reduce the accuracy of cell screening. For example, assuming the cell to be screened is a microglia and the reference cell is an astrocyte, if the center-to-center distance between a microglia and an astrocyte is greater than the set threshold, the microglia may be close to the synaptic site of the astrocyte because the astrocyte has a longer synapse. In this case, if cell screening is performed based on the comparison result between the center-to-center distance and the set threshold, it will be judged that the microglia is far from the astrocyte, resulting in misjudgment and reducing the accuracy of cell screening.

[0090] In this embodiment, the second distance corresponding to the first reference cell is compared with the first radius of the first covering circle of the first reference cell, and the first distance between the corresponding cell to be screened and the first reference cell is determined based on the comparison result. That is, the solution of this application determines the first distance based on the position of the geometric center of the cell to be screened relative to the first covering circle of the first reference cell. In this way, the first distance can more accurately describe the spatial relationship between the cell to be screened and the first reference cell. On this basis, cell screening is performed based on the determined first distance, which improves the accuracy of cell screening.

[0091] For example, assuming the cells to be screened are microglia and the reference cells are astrocytes, when the center-to-center distance between a microglia and an astrocyte is greater than a set threshold, and the microglia is adjacent to the synaptic site of the astrocyte, the geometric center of the microglia is located inside the first covering circle of the astrocyte. It can be seen that the position of the geometric center of the microglia relative to the first covering circle of the astrocyte can accurately reflect the spatial relationship between the two cells. Thus, the first distance between the microglia and the astrocyte can accurately describe the spatial relationship. Based on this, cell screening based on the determined first distance improves the accuracy of cell screening.

[0092] In one embodiment, screening one or more target cells from one or more cells to be screened based on one or more determined first distances includes:

[0093] For each of one or more first distances, if the first distance is within a set distance interval, the cell to be screened corresponding to the first distance is identified as the target cell.

[0094] In practical applications, the endpoints of the set distance interval can be determined based on the user's input in the first interface of the cell screening system. The left endpoint of the set distance interval can be understood as the minimum value in the distance interval, and the right endpoint of the set distance interval can be understood as the maximum value in the distance interval. In this way, the embodiments of this application can dynamically determine the distance interval for cell screening based on the user's input, thereby improving the accuracy and flexibility of cell screening.

[0095] In practical applications, if the solutions of this application are understood through visualization, the set distance can be regarded as constituting the annular screening interval corresponding to each cell to be screened.

[0096] For example, when both the left and right endpoints of the set distance interval exist, and the value of the left endpoint is not negative, the formed annular screening interval can be understood as an annular circle. The center of the annular circle represents the geometric center of the corresponding cell to be screened. The radius of the large circle of the annular circle is determined based on the right endpoint of the set distance interval, and the radius of the small circle of the annular circle is determined based on the left endpoint of the set distance interval. The geometric center of the target cell screened based on the set distance interval is located within the coverage area of ​​the corresponding annular circle.

[0097] For example, if both the left and right endpoints of the set distance interval exist, and the value of the left endpoint is negative while the value of the right endpoint is not negative, the resulting annular screening interval can be understood as a circle. The center of this circle represents the geometric center of the corresponding cell to be screened. The radius of this circle is determined based on the right endpoint of the set distance interval. The geometric center of the target cell screened based on the set distance interval is located within the coverage area of ​​the corresponding circle.

[0098] For example, if the left endpoint of the set distance interval does not exist, that is, it is infinitesimal, and the right endpoint exists, the annular screening interval can also be understood as a circle. The center of the circle represents the geometric center of the corresponding cell to be screened. The radius of the circle is determined based on the right endpoint of the set distance interval. The geometric center of the target cell screened based on the set distance interval is located inside the corresponding circle.

[0099] For example, if the right endpoint of the set distance interval does not exist, that is, it is infinite, and the left endpoint exists, the annular screening interval can also be understood as a circle. The center of the circle represents the geometric center of the corresponding cell to be screened. The radius of the circle is determined based on the left endpoint of the set distance interval. The geometric center of the target cell screened based on the set distance interval is located outside the corresponding circle.

[0100] In one embodiment, before overlaying the third image onto the fourth image with a set transparency to obtain the fifth image, the cell screening method provided in this application further includes:

[0101] Based on a set distance interval, a first bounding box and / or a second bounding box are labeled for each reference cell in one or more reference cells in the fourth image; wherein,

[0102] The defined distance interval is used to screen target cells from one or more cells to be screened based on a first distance; the center of the first frame and the center of the second frame are both represented as the geometric center of the corresponding reference cell, and the radius of the first frame is determined based on a first sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the first endpoint of the defined distance interval; the radius of the second frame is determined based on a second sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the second endpoint of the defined distance interval; the center of the first covering circle is represented as the geometric center of the corresponding reference cell, and the first covering circle covers the corresponding reference cell.

[0103] Here, the first circle can be regarded as a circle marked based on the first endpoint of the set distance interval, and the second circle can be regarded as a circle marked based on the second endpoint of the set distance interval.

[0104] When the first endpoint is represented as the left endpoint, the second endpoint can be represented as the right endpoint; when the first endpoint is represented as the right endpoint, the second endpoint can be represented as the left endpoint.

[0105] In practical applications, when the value at the first endpoint of the set distance interval is negative (i.e., the first sum is less than the radius of the first covering circle of the corresponding reference cell), the radius of the first circle can be represented as the radius of the first covering circle. Similarly, when the value at the second endpoint of the set distance interval is negative (i.e., the second sum is less than the radius of the first covering circle of the corresponding reference cell), the radius of the second circle can be represented as the radius of the first covering circle.

[0106] In practical applications, a predefined fourth function instruction can be invoked to process the fourth image, thereby annotating reference cells with a first and / or second circular frame. For ease of description, the fourth image annotated with the first and / or second circular frames can be referred to as the sixth image. For example, the fourth function instruction may include: "cv2.circle". The outline color of the first and second circular frames can be represented by different colors; for example, the outline color of the first circular frame can be red, and the outline color of the second circular frame can be green. The outline line type of the first and second circular frames can also be represented by different line types; for example, the outline line type of the first circular frame can be a solid line, and the outline line type of the second circular frame can be a dashed line.

[0107] For example, Figure 4 An example of a fourth image is provided, and the sixth image obtained after labeling each reference cell in one or more reference cells with a first bounding box and / or a second bounding box can be found here. Figure 5 As shown, the circular frame with a solid outline corresponds to the first circular frame in the embodiment of this application, and the circular frame with a dashed outline corresponds to the second circular frame in the embodiment of this application.

[0108] In practical applications, after labeling each reference cell in one or more reference cells with a first and / or second bounding box in the fourth image, the third image can be overlaid on the sixth image with a set transparency to obtain the fifth image.

[0109] In practical applications, the first and / or second circular frames corresponding to each cell to be screened can be used to visualize the annular screening interval corresponding to the cell to be screened. In this way, users can intuitively observe the comparison between the set distance interval and the first distance of each cell to be screened. Based on this, users can review the screening results based on the observation results to dynamically adjust the subsequent cell screening, such as dynamically adjusting the set distance interval, thereby improving the efficiency and accuracy of cell screening.

[0110] Based on the above method embodiments, this application also provides an image processing system.

[0111] In practical applications, this image processing system can be characterized as an image processing system separate from cell imaging and cell cutting systems, and can be used as a plug-in between cell imaging and cell cutting systems.

[0112] In practical applications, the image processing system provided in this application embodiment can receive images output by a cell imaging system based on a target tissue, perform corresponding image processing, such as cell screening, and then output the file to a cell cutting system so that the cell cutting system can cut the cells in the target tissue. Thus, when the output of the cell imaging system is incompatible with the input required by the cell cutting system, the image processing system can convert them through relevant processing, thereby improving the flexibility and efficiency of cell cutting and thus improving the flexibility and efficiency of the analysis of the target tissue.

[0113] This image processing system can have a cell screening function. To highlight the cell screening function of the image processing system, it can also be called a cell screening system.

[0114] Here, the image processing system can be used to perform the methods in any of the above embodiments to perform cell screening.

[0115] In practical applications, an image processing system may include a display module. The display module can be used to display a first interface, and the image processing system can acquire and / or determine information for cell screening based on the user's operations on the first interface.

[0116] For example, Figure 6 A schematic diagram of a first interface is provided, which includes the following input items:

[0117] An image file is used by the image processing system to acquire the fourth image in this embodiment. In practical applications, the user can input the storage path of the fourth image by operating the input component corresponding to this input item, so that the image processing system can acquire the fourth image. The input component corresponding to this input item can be represented as a file selector.

[0118] The Mask File is used by the image processing system to acquire the first image. In practical applications, the user can input the storage path of the first image by operating the input component corresponding to this input item, so that the image processing system can acquire the first image. The input component corresponding to this input item can be represented as a file selector.

[0119] The Center File (reference file) is used by the image processing system to acquire the second image. In practical applications, the user can input the storage path of the second image by manipulating the input component corresponding to this input item, thus enabling the image processing system to acquire the second image. In practical applications, the input component corresponding to this input item can be represented as a file selector.

[0120] d_min (minimum distance) is used by the image processing system to determine the left endpoint of a set distance interval, thus defining the set distance interval. In practical applications, the input component corresponding to this input item can be represented as an input box.

[0121] d_max (maximum distance) is used by the image processing system to determine the right endpoint of a defined distance interval, thus defining the specified distance interval. In practical applications, the input component corresponding to this input item can be represented as an input box.

[0122] `area_min` (minimum area) is used by the image processing system to determine the left endpoint of a specified area range, thus defining the defined area range. The input component corresponding to this input item can be represented as an input box.

[0123] `area_max` (maximum area) is used by the image processing system to determine the right endpoint of a specified area range, thus defining the defined area range. In practical applications, the input component corresponding to this input item can be represented as an input box.

[0124] Save Folder is used by the image processing system to determine the output path of the filtered results.

[0125] In practical applications, the input component corresponding to this input item can be represented as a folder selector.

[0126] In practical applications, the filtering results output to this output path may include one or more of the following: the third image, the fifth image, and the first file. After generating the third image, the image processing system can directly output the third image to the cell cutting system, output the third image to this output path, or output the third image to both the cell cutting system and this output path.

[0127] The first interface also includes an Execute button. In practical applications, users can click the Execute button to trigger the image processing system to perform cell screening.

[0128] In this embodiment, the image processing system automatically determines the first distance between each cell to be screened and its corresponding first reference cell based on the mask image output by the cell imaging system. Compared with related technologies, this eliminates the need for manual annotation to determine the spatial relationship between the cells to be screened and their corresponding reference cells. Based on this, target cells are screened from one or more cells to be screened according to the determined first distance, achieving automatic batch screening of cells in the target tissue and improving screening efficiency. Furthermore, after screening out the target cells, the image processing system generates a corresponding mask image and outputs the mask image to the cell cutting system, thereby improving cell cutting efficiency and mitigating the adverse effects of related technologies on the analysis efficiency of biological tissues.

[0129] The present application will be further described in detail below with reference to application examples.

[0130] This application provides a cell screening system, which is equivalent to the image processing system in this application.

[0131] In practical applications, cell screening systems are based on Figure 6 The process for cell screening using the interface shown can be mainly divided into the following steps:

[0132] Step 1: Based on the user-input Mask File, obtain Mask A (mask image A), and based on the user-input Center File, obtain Mask B (mask image B).

[0133] In practical applications, Mask A can represent the mask image output by the cell imaging system after recognizing the cell contours of one or more cells a in the target tissue, and Mask B can represent the mask image output by the cell imaging system after recognizing the cell contours of one or more cells b in the target tissue.

[0134] Here, Mask A corresponds to the first image in this embodiment, cell a corresponds to the cell to be screened in this embodiment, and Mask B corresponds to the second image in this embodiment. Cell b corresponds to the reference cell in this embodiment.

[0135] Step 2: Based on the user-inputted area_min and area_max, perform cell area filtering on one or more cells b.

[0136] In practical applications, the cell screening system can determine the geometric center and cell area of ​​cells in Mask A based on Mask A and Mask B.

[0137] In practical applications, the cell screening system can determine a set area range based on area_min and / or area_max input by the user. Exemplarily, the set area range can be expressed as [area_min, area_max]; then, the cell screening system can screen out cells b with cell areas within the set area range from one or more cells b, obtaining one or more cells b after cell area screening.

[0138] Here, one or more cells b after cell area screening are equivalent to one or more second reference cells in the embodiments of the present application.

[0139] Step 3: Determine the specific cell b corresponding to each cell a.

[0140] In practical applications, for each cell a, the cell screening system can respectively determine the center distance between the cell a and each cell b among one or more cells b after cell area screening, and determine the cell b corresponding to the minimum center distance as the specific cell b corresponding to the cell a. Among them, the center distance is equivalent to the second distance in the embodiments of the present application. For the convenience of expression, the center distance can be expressed as d.

[0141] Step 4: Determine the screening distance between each cell a and the corresponding specific cell b.

[0142] Here, the screening distance is equivalent to the first distance in the embodiments of the present application. For the convenience of expression, the center distance can be expressed as D.

[0143] In practical applications, the center distance between the cell a and the corresponding specific cell b can be compared with the radius of the first covering circle of the specific cell b to obtain a comparison result, and the screening distance can be determined based on the comparison result. For the convenience of expression, the radius of the first covering circle of the specific cell b can be expressed as r.

[0144] When the comparison result indicates d < r, the screening distance D can be represented as a set negative value. Exemplarily, the set negative value can be -1; in this case, it can be considered that the geometric center of the cell a is inside the first covering circle.

[0145] When the comparison result indicates d ≥ r, the screening distance D can be represented as d - r; in this case, it can be considered that the geometric center of the cell a is outside or on the contour of the first covering circle.

[0146] Step 5: Screen out target cells from one or more cells a based on the screening distance corresponding to each cell a.

[0147] In practical applications, the cell screening system can determine a set distance interval based on the user-inputted d_min and / or d_max. For example, the set distance interval can be represented as [d_min, d_max). Then, the cell screening system can determine the cell a corresponding to the screening distance within the set distance interval as the target cell.

[0148] Step 6: Output the filtering results.

[0149] In practical applications, the cell screening system can generate a target mask image based on one or more screened target cells and output the target mask image to the cell cutting system. For example, the cell screening system can save the image region where one or more target cells are located in Mask A as a target mask image, which is equivalent to the third image in the embodiments of this application.

[0150] The cell screening system can also count the cell area of ​​each target cell in the target mask image and save the statistical results as a statistical file, which is equivalent to the first file in the embodiments of this application.

[0151] The cell screening system can also obtain an imaging image based on the user-input Image File. This imaging image is equivalent to the fourth image in the embodiments of this application. Then, a first and / or second circular frame is marked for each cell b in the imaging image. Subsequently, the target mask image is superimposed on the imaging image after the circular frame is marked with a set transparency to obtain the superimposed image.

[0152] In practical applications, the cell screening system can output the target mask image and / or statistical file and / or the superimposed image to the output path corresponding to the Save Folder.

[0153] In the application embodiments of this application, the cell screening system automatically determines the screening distance between each cell a to be screened and its corresponding specific cell b based on the mask image output by the cell imaging system. Thus, compared with related technologies, it can determine the spatial relationship between cell a and its corresponding specific cell b without manual annotation. Based on this, target cells are screened from one or more cells a according to the determined screening distance, realizing automatic batch screening of cells in the target tissue and improving screening efficiency. Furthermore, after screening the target cells, the solution of this application generates a corresponding mask image and outputs the mask image to the cell cutting system, thereby improving cell cutting efficiency and mitigating the adverse effects of related technologies on the analysis efficiency of biological tissues.

[0154] Based on the embodiments described above, this application also provides a cell screening device, see [link to previous document]. Figure 7 The cell screening device includes:

[0155] The acquisition unit 71 is used to acquire a first image and a second image; the first image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more cells to be screened in the target tissue; the second image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more reference cells in the target tissue; the reference cells are used to provide spatial relationship reference for the cells to be screened.

[0156] The determining unit 72 is configured to, based on the first image and the second image, determine the first reference cell corresponding to each cell to be screened in the one or more reference cells, and determine the first distance between each cell to be screened and the corresponding first reference cell in the one or more cells to be screened;

[0157] The screening unit 73 is configured to screen one or more target cells from the one or more cells to be screened based on one or more determined first distances, so as to generate a third image and output the third image to the cell cutting system; the third image represents a mask image for displaying the cell outlines of the one or more target cells.

[0158] In one embodiment, the determining unit 72, based on the first image and the second image, determines a first reference cell corresponding to each of the one or more cells to be screened from the one or more reference cells, and determines a first distance between each cell to be screened and its corresponding first reference cell, including:

[0159] For each cell to be screened, based on the first image and the second image, a second distance is determined between the cell to be screened and each reference cell in the one or more reference cells, and a first reference cell corresponding to the cell to be screened is determined based on the obtained one or more second distances; the first reference cell represents the reference cell corresponding to the smallest second distance among the one or more second distances;

[0160] The second distance corresponding to the first reference cell is compared with the first radius of the first covering circle of the first reference cell, and the first distance between the corresponding cell to be screened and the first reference cell is determined based on the comparison result; the center of the first covering circle of the first reference cell is characterized as the geometric center of the first reference cell, and the first covering circle of the first reference cell covers the first reference cell.

[0161] In one embodiment, the determining unit 72 determines a first distance between the corresponding cell to be screened and the first reference cell based on the comparison result, including:

[0162] If the comparison result indicates that the second distance corresponding to the first reference cell is greater than the first radius, the first difference is determined as the first distance; the first difference is characterized as the difference between the second distance corresponding to the first reference cell and the first radius; and / or,

[0163] If the comparison result indicates that the second distance corresponding to the first reference cell is less than the first radius, a negative value will be set as the first distance; and / or,

[0164] If the comparison result indicates that the second distance corresponding to the first reference cell is equal to the first radius, the first difference or the set negative value is determined as the first distance.

[0165] In one embodiment, before determining the second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image, the determining unit 72 is further configured to:

[0166] One or more second reference cells are selected from the one or more reference cells; the cell area of ​​the second reference cells is located within the set area range;

[0167] Correspondingly, determining the second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image includes:

[0168] Based on the first image and the second image, a second distance is determined between the cell to be screened and each of the one or more second reference cells.

[0169] In one embodiment, the screening unit 73 screens one or more target cells from the one or more cells to be screened based on one or more determined first distances, including:

[0170] For each of the one or more first distances, if the first distance is within a set distance interval, the cell to be screened corresponding to the first distance is determined as the target cell.

[0171] In one embodiment, after generating the third image, the filtering unit 72 is further configured to:

[0172] The third image is superimposed on the fourth image with a set transparency to obtain the fifth image, and the fifth image is output; the fourth image represents the image output by the cell imaging system after performing cell imaging processing on the target tissue.

[0173] In one embodiment, before overlaying the third image onto the fourth image with a set transparency to obtain the fifth image, the filtering unit 73 is further configured to:

[0174] Based on a set distance interval, a first bounding box and / or a second bounding box are labeled for each of the one or more reference cells in the fourth image; wherein,

[0175] The defined distance interval is used to screen target cells from one or more cells to be screened based on a first distance; the center of the first frame and the center of the second frame are both represented as the geometric center of the corresponding reference cell, and the radius of the first frame is determined based on a first sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the first endpoint of the defined distance interval; the radius of the second frame is determined based on a second sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the second endpoint of the defined distance interval; the center of the first covering circle is represented as the geometric center of the corresponding reference cell, and the first covering circle covers the corresponding reference cell.

[0176] In practical applications, the acquisition unit 71, the determination unit 72, and the screening unit 73 can be implemented by the processor in the cell screening device.

[0177] It should be noted that the cell screening device provided in the above embodiments is only illustrated by the division of the above-described program modules. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the cell screening device and the cell screening method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0178] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, this application also provides an electronic device, see [link to relevant documentation]. Figure 8 The electronic device includes:

[0179] Communication interface 1 enables information exchange with other devices;

[0180] Processor 2 is connected to communication interface 1 to enable information interaction with other devices and, when running a computer program, executes the methods provided by one or more technical solutions in the above embodiments. The computer program is stored in memory 3.

[0181] Specifically, the processor 2 is used to acquire a first image and a second image; the first image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more cells to be screened in the target tissue; the second image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more reference cells in the target tissue; the reference cells are used to provide spatial relationship reference for the cells to be screened.

[0182] Based on the first image and the second image, a first reference cell corresponding to each cell to be screened in the one or more reference cells is determined, and a first distance between each cell to be screened and its corresponding first reference cell is determined.

[0183] Based on one or more determined first distances, one or more target cells are selected from the one or more cells to be screened to generate a third image and output the third image to the cell cutting system; the third image represents a mask image used to display the cell outlines of the one or more target cells.

[0184] In one embodiment, the processor 2, based on the first image and the second image, determines a first reference cell corresponding to each of the one or more cells to be screened from the one or more reference cells, and determines a first distance between each cell to be screened and its corresponding first reference cell, including:

[0185] For each cell to be screened, based on the first image and the second image, a second distance is determined between the cell to be screened and each reference cell in the one or more reference cells, and a first reference cell corresponding to the cell to be screened is determined based on the obtained one or more second distances; the first reference cell represents the reference cell corresponding to the smallest second distance among the one or more second distances;

[0186] The second distance corresponding to the first reference cell is compared with the first radius of the first covering circle of the first reference cell, and the first distance between the corresponding cell to be screened and the first reference cell is determined based on the comparison result; the center of the first covering circle of the first reference cell is characterized as the geometric center of the first reference cell, and the first covering circle of the first reference cell covers the first reference cell.

[0187] In one embodiment, the processor 2 determines a first distance between the corresponding cell to be screened and the first reference cell based on the comparison result, including:

[0188] If the comparison result indicates that the second distance corresponding to the first reference cell is greater than the first radius, the first difference is determined as the first distance; the first difference is characterized as the difference between the second distance corresponding to the first reference cell and the first radius; and / or,

[0189] If the comparison result indicates that the second distance corresponding to the first reference cell is less than the first radius, a negative value will be set as the first distance; and / or,

[0190] If the comparison result indicates that the second distance corresponding to the first reference cell is equal to the first radius, the first difference or the set negative value is determined as the first distance.

[0191] In one embodiment, before determining the second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image, the processor 2 is further configured to:

[0192] One or more second reference cells are selected from the one or more reference cells; the cell area of ​​the second reference cells is located within the set area range;

[0193] Correspondingly, determining the second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image includes:

[0194] Based on the first image and the second image, a second distance is determined between the cell to be screened and each of the one or more second reference cells.

[0195] In one embodiment, the processor 2 filters one or more target cells from the one or more cells to be screened based on one or more determined first distances, including:

[0196] For each of the one or more first distances, if the first distance is within a set distance interval, the cell to be screened corresponding to the first distance is determined as the target cell.

[0197] In one embodiment, after generating the third image, the processor 2 is further configured to:

[0198] The third image is superimposed on the fourth image with a set transparency to obtain the fifth image, and the fifth image is output; the fourth image represents the image output by the cell imaging system after performing cell imaging processing on the target tissue.

[0199] In one embodiment, before overlaying the third image onto the fourth image with a set transparency to obtain the fifth image, the processor 2 is further configured to:

[0200] Based on a set distance interval, a first bounding box and / or a second bounding box are labeled for each of the one or more reference cells in the fourth image; wherein,

[0201] The defined distance interval is used to screen target cells from one or more cells to be screened based on a first distance; the center of the first frame and the center of the second frame are both represented as the geometric center of the corresponding reference cell, and the radius of the first frame is determined based on a first sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the first endpoint of the defined distance interval; the radius of the second frame is determined based on a second sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the second endpoint of the defined distance interval; the center of the first covering circle is represented as the geometric center of the corresponding reference cell, and the first covering circle covers the corresponding reference cell.

[0202] It should be noted that the specific processing procedure of communication interface 1 can be understood by referring to the above method.

[0203] Of course, in practical applications, the various components in an electronic device are coupled together through bus system 4. It can be understood that bus system 4 is used to achieve communication and connection between these components. In addition to the data bus, bus system 4 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 8 The general will label all buses as Bus System 4.

[0204] The memory 3 in this embodiment is used to store various types of data to support operation in the electronic device. Examples of such data include any computer program used to operate on the electronic device.

[0205] The methods disclosed in the embodiments of this application can be applied to the processor 2, or implemented by the processor 2. The processor 2 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 2 or by instructions in the form of software. The processor 2 mentioned above may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 2 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the memory 3. The processor 2 reads the information in the memory 3 and combines its hardware to complete the steps of the aforementioned method.

[0206] In an exemplary embodiment, the electronic device may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.

[0207] It is understood that the memory 3 in the embodiments of this application can be volatile memory or non-volatile memory, or both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); the magnetic surface memory can be disk storage or magnetic tape storage. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0208] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as an electronic device including a computer program. The computer program can be executed by the processor 2 of the electronic device to complete the steps described in the aforementioned method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0209] In an exemplary embodiment, this application also provides a computer program product, including a computer program that can be executed by a processor 2 of an electronic device to perform the steps described in any of the foregoing methods.

[0210] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0211] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the term "one or more" in this document refers to any combination of at least two of any one or more elements from a set of A, B, and C. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set of A, B, and C.

[0212] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

Claims

1. A cell screening method, characterized in that, The method includes: Acquire a first image and a second image; the first image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more cells to be screened in the target tissue; the second image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more reference cells in the target tissue; the reference cells are used to provide spatial relationship reference for the cells to be screened. Based on the first image and the second image, a first reference cell corresponding to each of the one or more cells to be screened is determined from the one or more reference cells, and a first distance between each cell to be screened and its corresponding first reference cell is determined; wherein, for each cell to be screened, a second distance between the cell to be screened and each of the one or more reference cells is determined based on the first image and the second image, and a first reference cell corresponding to the cell to be screened is determined based on the obtained one or more second distances; the first reference cell represents the reference cell corresponding to the smallest second distance among the one or more second distances; the second distance corresponding to the first reference cell is compared with the first radius of the first covering circle of the first reference cell, and the first distance between the corresponding cell to be screened and the first reference cell is determined based on the comparison result; the center of the first covering circle of the first reference cell represents the geometric center of the first reference cell, and the first covering circle of the first reference cell covers the first reference cell; Based on one or more determined first distances, one or more target cells are selected from the one or more cells to be screened to generate a third image and output the third image to the cell cutting system; the third image represents a mask image used to display the cell outlines of the one or more target cells.

2. The method according to claim 1, characterized in that, The determination of the first distance between the corresponding cell to be screened and the first reference cell based on the comparison result includes: If the comparison result indicates that the second distance corresponding to the first reference cell is greater than the first radius, the first difference is determined as the first distance; the first difference is characterized as the difference between the second distance corresponding to the first reference cell and the first radius; and / or, If the comparison result indicates that the second distance corresponding to the first reference cell is less than the first radius, a negative value will be set as the first distance; and / or, If the comparison result indicates that the second distance corresponding to the first reference cell is equal to the first radius, the first difference or the set negative value is determined as the first distance.

3. The method according to claim 1, characterized in that, Before determining the second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image, the method further includes: One or more second reference cells are selected from the one or more reference cells; the cell area of ​​the second reference cells is located within a set area range; Correspondingly, determining the second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image includes: Based on the first image and the second image, a second distance is determined between the cell to be screened and each of the one or more second reference cells.

4. The method according to claim 1, characterized in that, The step of selecting one or more target cells from the one or more cells to be screened based on one or more determined first distances includes: For each of the one or more first distances, if the first distance is within a set distance interval, the cell to be screened corresponding to the first distance is determined as the target cell.

5. The method according to claim 1, characterized in that, After generating the third image, the method further includes: The third image is superimposed on the fourth image with a set transparency to obtain the fifth image, and the fifth image is output; the fourth image represents the image output by the cell imaging system after performing cell imaging processing on the target tissue.

6. The method according to claim 5, characterized in that, Before overlaying the third image onto the fourth image with a set transparency to obtain the fifth image, the method further includes: Based on a set distance interval, a first bounding box and / or a second bounding box are labeled for each of the one or more reference cells in the fourth image; wherein, The defined distance interval is used to screen target cells from one or more cells to be screened based on a first distance; the center of the first frame and the center of the second frame are both represented as the geometric center of the corresponding reference cell, and the radius of the first frame is determined based on a first sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the first endpoint of the defined distance interval; the radius of the second frame is determined based on a second sum, which is represented as the sum between the radius of the first covering circle of the corresponding reference cell and the second endpoint of the defined distance interval; the center of the first covering circle is represented as the geometric center of the corresponding reference cell, and the first covering circle covers the corresponding reference cell.

7. A cell screening device, characterized in that, include: The acquisition unit is used to acquire the first image and the second image; The first image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more cells to be screened in the target tissue; the second image represents a mask image output by the cell imaging system after performing cell contour recognition on one or more reference cells in the target tissue; the reference cells are used to provide spatial relationship reference for the cells to be screened. A determining unit is configured to, based on the first image and the second image, determine a first reference cell corresponding to each of the one or more cells to be screened from the one or more reference cells, and determine a first distance between each cell to be screened and its corresponding first reference cell; wherein, for each cell to be screened, the determining unit determines a second distance between the cell to be screened and each of the one or more reference cells based on the first image and the second image, and determines a first reference cell corresponding to the cell to be screened based on the obtained one or more second distances; the first reference cell represents the reference cell corresponding to the smallest second distance among the one or more second distances; the second distance corresponding to the first reference cell is compared with the first radius of the first covering circle of the first reference cell, and the first distance between the corresponding cell to be screened and the first reference cell is determined based on the comparison result; the center of the first covering circle of the first reference cell represents the geometric center of the first reference cell, and the first covering circle of the first reference cell covers the first reference cell; A screening unit is configured to screen one or more target cells from the one or more cells to be screened based on one or more determined first distances, to generate a third image and output the third image to a cell cutting system; the third image represents a mask image used to display the cell outlines of the one or more target cells.

8. An electronic device, characterized in that, include: The processor and the memory used to store computer programs that can run on the processor. When the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 6.

9. 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 6.

Images