Mask image-based nasal polyp pathological image cutting method, device and equipment and storage medium

Abstract

This disclosure provides a method, device, and storage medium for cutting nasal polyp pathological images based on mask images, relating to the field of data processing technology. The implementation scheme is as follows: The nasal polyp pathological slide is reduced in size based on a preset reduction ratio; the reduced nasal polyp pathological slide is segmented into nasal polyp tissue and background to obtain a masked pathological image; the masked pathological image is cut to obtain multiple first sub-masked pathological images; an integral operation is performed on each first sub-masked pathological image; based on the integral results of each first sub-masked pathological image, multiple second sub-masked pathological images are selected from the multiple first sub-masked pathological images; based on the coordinates of each second sub-masked pathological image in the masked pathological image, the mapping coordinates of each second sub-masked pathological image on the nasal polyp pathological slide are determined; based on the mapping coordinates of each second sub-masked pathological image on the nasal polyp pathological slide, the nasal polyp pathological slide is cut to obtain the target nasal polyp pathological slide. This improves the cutting efficiency of nasal polyp pathological slides.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology. Specifically, it relates to methods, apparatus, devices, and storage media for cutting nasal polyp pathological images based on mask diagrams. Background Technology

[0002] When processing nasal polyp pathology slides, the images are typically segmented into multiple sub-images, and cell identification is performed on each sub-image. However, current techniques for pathological images use a fixed-size, cyclically segmented approach within a pre-defined rectangular area. This results in some sub-images containing little or no valid pathological region, necessitating further filtering. While manual filtering is commonly used, it cannot guarantee data consistency. Therefore, existing image segmentation and filtering methods have certain limitations. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and storage medium for cutting nasal polyp pathological images based on mask diagrams.

[0004] According to one aspect of this disclosure, a method for segmenting nasal polyp pathological images based on mask diagrams is provided, comprising: The nasal polyp pathology slides are reduced in size based on a preset reduction ratio; The reduced nasal polyp pathological slide was segmented into nasal polyp tissue and background to obtain a masked pathological image. The masked pathological image is segmented to obtain multiple first sub-masked pathological images; Perform integration on each of the first sub-mask pathological images; Based on the integration results of each of the first sub-mask pathological images, a plurality of second sub-mask pathological images are selected from the plurality of first sub-mask pathological images; Based on the coordinates of each second sub-mask pathological image in the mask pathological image, the mapping coordinates of each second sub-mask pathological image in the nasal polyp pathological slide are determined; Based on the mapping coordinates of each of the second sub-mask pathological images on the nasal polyp pathological slide, the nasal polyp pathological slide is cut to obtain the target nasal polyp pathological slide.

[0005] According to one aspect of this disclosure, a cutting device for nasal polyp pathology images based on mask diagrams is provided, comprising: The image reduction module is used to reduce the size of nasal polyp pathological slides based on a preset reduction ratio; The image masking module is used to segment the nasal polyp tissue and background on the reduced nasal polyp pathological slide to obtain a masked pathological image; The first image cutting module is used to cut the masked pathological image to obtain multiple first sub-masked pathological images; The integration module is used to perform integration operations on each of the first sub-mask pathological images; An image filtering module is used to select multiple second sub-mask pathological images from the multiple first sub-mask pathological images based on the integration results of each of the first sub-mask pathological images. The coordinate mapping module is used to determine the mapping coordinates of each second sub-mask pathological image in the nasal polyp pathological slide based on the coordinates of each second sub-mask pathological image in the mask pathological image. The second image cutting module is used to cut the nasal polyp pathological slide based on the mapping coordinates of each of the second sub-mask pathological images on the nasal polyp pathological slide to obtain the target nasal polyp pathological slide.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and The memory is communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the mask-based nasal polyp pathology images in the embodiments of this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform a cutting method of a nasal polyp pathology image based on a mask image according to any embodiment of this disclosure.

[0008] According to the technology disclosed herein, the nasal polyp pathological slide is reduced in size based on a preset reduction ratio; the reduced nasal polyp pathological slide is segmented into nasal polyp tissue and background to obtain a masked pathological image; the masked pathological image is cut to obtain multiple first sub-masked pathological images; an integral operation is performed on each first sub-masked pathological image; based on the integral results of each first sub-masked pathological image, multiple second sub-masked pathological images are selected from the multiple first sub-masked pathological images; based on the coordinates of each second sub-masked pathological image in the masked pathological image, the mapping coordinates of each second sub-masked pathological image on the nasal polyp pathological slide are determined; based on the mapping coordinates of each second sub-masked pathological image on the nasal polyp pathological slide, the nasal polyp pathological slide is cut to obtain a target nasal polyp pathological slide. The technical solution of this disclosure involves reducing the original image, masking the reduced image, cutting it into multiple smaller images, then integrating and filtering the smaller images to obtain a target smaller image, mapping the coordinates of the target smaller image back to the original image, and finally cutting the original image. Therefore, by reducing the size of the original image to cut it into smaller images and then filtering the smaller images to obtain the target smaller image, the problem of excessive memory consumption caused by directly cutting and filtering the original image when it is too large can be solved, thereby improving the cutting efficiency.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is a flowchart of a method for cutting nasal polyp pathological images based on a mask image according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram of the entire nasal polyp pathological slide according to an embodiment of the present disclosure; Figure 3 This is a schematic diagram of a masked image of a nasal polyp pathological slide according to an embodiment of this disclosure; Figure 4 This is a schematic diagram of a mask image including a target region bounding box of a nasal polyp pathological slide according to an embodiment of the present disclosure; Figure 5 This is a structural block diagram of a cutting device for nasal polyp pathology images based on a mask image according to an embodiment of the present disclosure. Figure 6 This is a block diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0011] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0012] Figure 1 This is a flowchart of a method for cutting nasal polyp pathological images based on a mask image, according to an embodiment of this disclosure.

[0013] like Figure 1 As shown, the method for segmenting nasal polyp pathological images based on mask diagrams may include: S110, based on a preset reduction ratio, reduces the size of nasal polyp pathological slides; S120, perform nasal polyp tissue and background segmentation on the reduced nasal polyp pathological slide to obtain a masked pathological image; S130, the masked pathological image is segmented to obtain multiple first sub-masked pathological images; S140, perform integral calculations on each first sub-mask pathological image; S150, Based on the integration results of each first sub-mask pathological image, select multiple second sub-mask pathological images from multiple first sub-mask pathological images; S160, Based on the coordinates of each second sub-mask pathological image in the mask pathological image, determine the mapping coordinates of each second sub-mask pathological image in the nasal polyp pathological slide. S170, based on the mapping coordinates of each second sub-mask pathological image on the nasal polyp pathological slide, the nasal polyp pathological slide is cut to obtain the target nasal polyp pathological slide.

[0014] For example, such as Figure 2 As shown, a nasal polyp pathology slide can be a full-size TSA fluorescence pathology slide of nasal polyp tissue. For example, using the OpenSlide open-source library, the pathology slide can be reduced to 1 / 16th the size of the full slide.

[0015] For example, using the Otsu watershed algorithm, the nasal polyp tissue and background in the reduced-size nasal polyp pathological slide are segmented to generate a black-and-white binary image, i.e., a masked pathological image. Figure 3 As shown, it illustrates Figure 2 The pathological image corresponding to the reduced-size masked pathological image of the pathological slide.

[0016] For example, the masked pathological image can be segmented according to a set sub-image size to obtain multiple first sub-masked pathological images. For instance, the sub-image size is 40um*40um, meaning that the size of each first sub-masked pathological image is 40um*40um.

[0017] For example, density analysis of positive immune cells is performed on regions representing nasal polyp tissue in a masked pathological image. Then, if the density of positive immune cells in a region is greater than a preset density threshold, the region is segmented using a first sub-image size; if the density of positive immune cells in a region is less than the preset density threshold, the region is segmented using a second sub-image size, where the first sub-image size is smaller than the second sub-image size. Thus, a smaller size is used to segment the image in high-density areas, and a larger size is used to segment the image in low-density areas, improving the visibility of the segmented images.

[0018] Understandably, positive immune cells refer to a collection of cells that, after TSA multiplex fluorescence staining, are identified in the image as expressing specific immune markers (such as IL-4R, IL-5, and IgE). The YOLO model can automatically identify them, with each type of fluorescent cell corresponding to a specific fluorescence channel, thus serving as a distinguishing feature.

[0019] For example, the entire masked pathological image can be segmented before selecting sub-images. Alternatively, segmenting a specific region within the masked pathological image before selecting sub-images can improve efficiency. For instance, segmenting the smallest region containing all pathological tissue can reduce invalid areas and ensure precise segmentation. Subsequent selection of the resulting sub-images can also reduce the number of invalid sub-images, thereby reducing computational load and improving efficiency.

[0020] For example, the area of ​​the region representing nasal polyp tissue in the first submask pathological image is obtained by performing an area integration algorithm.

[0021] For example, the first sub-mask pathological image whose black area meets the condition is used as the second sub-mask pathological image, that is, the sub-image is obtained by filtering.

[0022] For example, by magnifying the coordinates of the sub-image in the masked pathological image by 16 times, the mapped coordinates of the sub-image in the original image can be obtained.

[0023] For example, using the OpenSlide open-source library, the nasal polyp pathological slide, i.e. the original image, is cut based on the mapping coordinates of each sub-image in the original image to obtain the target nasal polyp pathological slide.

[0024] According to the above implementation method, by reducing the size of the original image, masking the reduced image, and cutting it into multiple smaller images, then integrating and filtering the smaller images to obtain the target smaller image, mapping the coordinates of the target smaller image back to the original image, and finally cutting the original image. This solves the problem of excessive memory usage due to an overly large original image and improves cutting efficiency.

[0025] In one embodiment, the process of segmenting the nasal polyp pathological slide into nasal polyp tissue and background to obtain a masked pathological image includes: denoising the nasal polyp pathological slide; and segmenting the nasal polyp tissue and background on the denoised and reduced nasal polyp pathological slide to obtain a masked pathological image.

[0026] In this example, the reduced nasal polyp pathological slide is first denoised, and then the slide is binarized to improve the clarity of the pathological image and improve the accuracy of subsequent cutting of the original slide.

[0027] In one embodiment, segmenting a masked pathological image to obtain multiple first sub-masked pathological images includes: performing contour recognition on the masked pathological image to obtain the boundary coordinates of each of the multiple contours; determining a minimum region comprising the multiple contours based on the coordinate boundaries of each contour to obtain a target region, wherein the boundary of the target region is tangent to the boundary of at least one of the multiple contours; and segmenting the target region in the masked pathological image to obtain multiple first sub-masked pathological images.

[0028] For example, using the CV2 contour recognition algorithm, closed contours in a masked pathological image can be identified, resulting in multiple contours. Then, based on the coordinate boundaries of each contour, a minimum region encompassing all contours can be determined, for example... Figure 4 As shown.

[0029] In this example, by filtering the largest contour in the masked pathological image, the smallest region containing all pathological tissue can be determined, reducing invalid areas and ensuring precise positioning of the target cutting area. Subsequent filtering of the resulting smaller images after cutting can reduce the number of invalid smaller images, thereby reducing computational load and improving efficiency.

[0030] In one embodiment, an integral operation is performed on each of the first sub-mask pathological images, including: performing an integral operation on the black regions in the first sub-mask pathological images to obtain the area of ​​the black regions, wherein the black regions are used to represent nasal polyp tissue.

[0031] In one implementation, multiple second sub-mask pathological images are selected from multiple first sub-mask pathological images based on the integration results of each first sub-mask pathological image, including: if the area of ​​the black region of the first sub-mask pathological image is greater than a preset area threshold, the first sub-mask pathological image is used as the second sub-mask pathological image.

[0032] For example, the area of ​​the black region can be normalized, that is, the ratio of the area of ​​the black region to the area of ​​the first sub-mask pathological image can be used as the normalized value of the area of ​​the black region, so that the value ranges between 0 and 1.

[0033] For example, if the normalized value of the area of ​​the black region is greater than 0.7, the first sub-mask pathological image is used as the second sub-mask pathological image, meaning that the image is considered to contain more than 70% nasal polyp tissue. If the normalized value of the area of ​​the black region is less than 0.7, it is considered that the cut sub-image does not contain nasal polyp tissue or that the nasal polyp tissue contained at the boundary is too small, and the image can be cut.

[0034] In this example, the algorithm performs integral operations on each sub-image of the mask image to determine the size of the integral result, and excludes sub-images that are less than a certain proportion, i.e., sub-images that contain too small an effective area or do not contain an effective area, thereby reducing the cost of manual screening and improving the efficiency of subsequent cutting of the original image.

[0035] In one embodiment, determining the mapping coordinates of each second sub-masked pathological image in the nasal polyp pathological slide based on the coordinates of each second sub-masked pathological image in the masked pathological image includes: magnifying the coordinates of the second sub-masked pathological image in the masked pathological image based on the magnification ratio corresponding to the reduction ratio to obtain the mapping coordinates of the second sub-masked pathological image in the nasal polyp pathological slide.

[0036] For example, a reduction ratio of 1 / 16 corresponds to a magnification ratio of 16 times. Alternatively, a reduction ratio of 1 / 32 corresponds to a magnification ratio of 32 times.

[0037] For example, the coordinates of the second sub-mask pathological image within the mask pathological image are magnified by a factor of 16 to obtain the mapped coordinates of the second sub-mask pathological image on the nasal polyp pathological slide. Then, the nasal polyp pathological slide is segmented according to the mapped coordinates of each second sub-mask pathological image on the nasal polyp pathological slide to obtain the target nasal polyp pathological slide. For example, the OpenSlide library can be used to segment the nasal polyp pathological slide to obtain the target nasal polyp pathological slide.

[0038] In this example, the coordinate mapping mechanism makes it easier to process TSA fluorescence pathology slides of nasal polyps. The full pathology slide files are large and require a lot of computer memory, making them difficult to process in one go. By reducing the scale of the original image and then enlarging it back to the original image for cropping, the problem of the excessively large original image file is solved, and a faster and more efficient data processing mechanism is achieved.

[0039] Figure 5 This is a structural block diagram of a cutting device for nasal polyp pathological images based on a mask image, according to an embodiment of the present disclosure.

[0040] like Figure 5 As shown, the cutting device for nasal polyp pathology images based on mask diagrams includes: Image reduction module 510 is used to reduce the size of nasal polyp pathological slides based on a preset reduction ratio; Image masking module 520 is used to segment the nasal polyp tissue and background on the reduced nasal polyp pathological slide to obtain a masked pathological image; The first image cutting module 530 is used to cut the masked pathological image to obtain multiple first sub-masked pathological images; The integration module 540 is used to perform integration operations on each of the first sub-mask pathological images; The image filtering module 550 is used to select a plurality of second sub-mask pathological images from the plurality of first sub-mask pathological images based on the integration results of each of the first sub-mask pathological images. The coordinate mapping module 560 is used to determine the mapping coordinates of each of the second sub-mask pathological images in the nasal polyp pathological slide based on the coordinates of each of the second sub-mask pathological images in the mask pathological image. The second image cutting module 570 is used to cut the nasal polyp pathological slide based on the mapping coordinates of each of the second sub-mask pathological images on the nasal polyp pathological slide to obtain the target nasal polyp pathological slide.

[0041] In one embodiment, the image masking module includes: An image denoising unit is used to denoise the reduced nasal polyp pathological slide; An image masking unit is used to segment the nasal polyp tissue and background on the reduced and denoised nasal polyp pathological slide to obtain a masked pathological image.

[0042] In one embodiment, the first image segmentation module 530 includes: A contour recognition unit is used to perform contour recognition on the masked pathological image to obtain the boundary coordinates of multiple contours. The target region determination unit is used to determine a minimum region including the plurality of contours based on the coordinate boundaries of each of the contours, so as to obtain a target region, wherein the boundary of the target region is tangent to the boundary of at least one of the plurality of contours; An image segmentation unit is used to segment the target region in the masked pathological image to obtain multiple first sub-masked pathological images. In one embodiment, the integration module 540 is specifically used for: The area of ​​the black region in the first submask pathological image is obtained by performing an integral operation, wherein the black region is used to represent nasal polyp tissue.

[0043] In one embodiment, the image filtering module 550 is specifically used for: If the area of ​​the black region in the first sub-masked pathological image is greater than a preset area threshold, the first sub-masked pathological image is used as the second sub-masked pathological image.

[0044] In one embodiment, the coordinate mapping module 560 is specifically used for: Based on the magnification ratio corresponding to the reduction ratio, the coordinates of the second sub-masked pathological image in the masked pathological image are magnified to obtain the mapping coordinates of the second sub-masked pathological image in the nasal polyp pathological slide.

[0045] The specific functions and examples of each module and submodule of the apparatus in this disclosure can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0046] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0047] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0048] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of the present disclosure. Figure 6As shown, the electronic device includes a memory 410 and a processor 420. The memory 410 stores a computer program that can run on the processor 420. There can be one or more memories 410 and processors 420. The memory 410 can store one or more computer programs, which, when executed by the electronic device, cause the electronic device to perform the methods provided in the above-described method embodiments. The electronic device may also include a communication interface 430 for communicating with external devices and performing data exchange and transmission.

[0049] If the memory 410, processor 420, and communication interface 430 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0050] Optionally, in a specific implementation, if the memory 410, processor 420 and communication interface 430 are integrated on a single chip, the memory 410, processor 420 and communication interface 430 can communicate with each other through an internal interface.

[0051] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0052] Further, optionally, the aforementioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct RAMBUS RAM (DR RAM).

[0053] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line, DSL) or wireless (e.g., infrared, Bluetooth, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer, or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)). It is worth noting that the computer-readable storage media mentioned in this disclosure may be non-volatile storage media; in other words, they may be non-transient storage media.

[0054] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0055] In the description of the embodiments of this disclosure, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0056] In the description of the embodiments disclosed herein, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0057] In the description of embodiments of this disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0058] The above description is merely an exemplary embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A method for segmenting nasal polyp pathological images based on mask diagrams, characterized in that, include: The nasal polyp pathology slides are reduced in size based on a preset reduction ratio; The reduced nasal polyp pathological slide was segmented into nasal polyp tissue and background to obtain a masked pathological image. The masked pathological image is segmented to obtain multiple first sub-masked pathological images; Perform integration on each of the first sub-mask pathological images; Based on the integration results of each of the first sub-mask pathological images, a plurality of second sub-mask pathological images are selected from the plurality of first sub-mask pathological images; Based on the coordinates of each second sub-mask pathological image in the mask pathological image, the mapping coordinates of each second sub-mask pathological image in the nasal polyp pathological slide are determined; Based on the mapping coordinates of each of the second sub-mask pathological images on the nasal polyp pathological slide, the nasal polyp pathological slide is cut to obtain the target nasal polyp pathological slide.

2. The method according to claim 1, characterized in that, The process of segmenting the nasal polyp tissue and background on the reduced nasal polyp pathological slide to obtain a masked pathological image includes: The nasal polyp pathological slides were denoised after being reduced in size; The reduced and denoised nasal polyp pathological slides were segmented into nasal polyp tissue and background to obtain masked pathological images.

3. The method according to claim 1, characterized in that, The process of segmenting the masked pathological image to obtain multiple first sub-masked pathological images includes: Contour recognition is performed on the masked pathological image to obtain the boundary coordinates of each of the multiple contours; Based on the coordinate boundaries of each of the contours, a minimum region comprising the multiple contours is determined to obtain a target region, wherein the boundary of the target region is tangent to the boundary of at least one of the multiple contours. The target region in the masked pathological image is segmented to obtain multiple first sub-masked pathological images.

4. The method according to claim 1, characterized in that, The integral operation on each of the first sub-mask pathological images includes: The area of ​​the black region in the first submask pathological image is obtained by performing an integral operation, wherein the black region is used to represent nasal polyp tissue.

5. The method according to claim 4, characterized in that, The method of selecting multiple second sub-masked pathological images from the plurality of first sub-masked pathological images based on the integral results of each of the first sub-masked pathological images includes: If the area of ​​the black region in the first sub-masked pathological image is greater than a preset area threshold, the first sub-masked pathological image is used as the second sub-masked pathological image.

6. The method according to any one of claims 1-5, characterized in that, The step of determining the mapping coordinates of each second sub-masked pathological image in the nasal polyp pathological slide based on the coordinates of each second sub-masked pathological image in the masked pathological image includes: Based on the magnification ratio corresponding to the reduction ratio, the coordinates of the second sub-masked pathological image in the masked pathological image are magnified to obtain the mapping coordinates of the second sub-masked pathological image in the nasal polyp pathological slide.

7. A cutting device for nasal polyp pathological images based on mask diagrams, characterized in that, include: The image reduction module is used to reduce the size of nasal polyp pathological slides based on a preset reduction ratio; The image masking module is used to segment the nasal polyp tissue and background on the reduced nasal polyp pathological slide to obtain a masked pathological image; The first image cutting module is used to cut the masked pathological image to obtain multiple first sub-masked pathological images; The integration module is used to perform integration operations on each of the first sub-mask pathological images; An image filtering module is used to select multiple second sub-mask pathological images from the multiple first sub-mask pathological images based on the integration results of each of the first sub-mask pathological images. The coordinate mapping module is used to determine the mapping coordinates of each second sub-mask pathological image in the nasal polyp pathological slide based on the coordinates of each second sub-mask pathological image in the mask pathological image. The second image cutting module is used to cut the nasal polyp pathological slide based on the mapping coordinates of each of the second sub-mask pathological images on the nasal polyp pathological slide to obtain the target nasal polyp pathological slide.

8. The apparatus according to claim 7, characterized in that, The image masking module includes: An image denoising unit is used to denoise the reduced nasal polyp pathological slide; An image masking unit is used to segment the nasal polyp tissue and background on the reduced and denoised nasal polyp pathological slide to obtain a masked pathological image.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

Images