Image partitioning method, device, equipment and readable storage medium

Abstract

The present application discloses an image partitioning method, device, equipment and readable storage medium. Obtain a biological tissue section staining image to be partitioned; determine the image blocks to be processed in the biological tissue section staining image; perform feature extraction on each image block to be processed to obtain a tissue morphology feature vector for each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to the response intensity of a tissue morphology feature in the image block to be processed; cluster each image block to be processed based on the tissue morphology feature vector of each image block to be processed to obtain a clustering result of each image block to be processed; partition the biological tissue section staining image based on the clustering result of each image block to be processed. Using the above scheme, the biological tissue section staining image can be partitioned based on clustering, without the need for supervised training of a biological tissue section staining image partitioning model.

Description

Technical Field

[0001] The present application relates to the technical field of computer-aided biological tissue section staining image analysis, and more specifically, to an image partitioning method, device, equipment and readable storage medium. Background Art

[0002] With the digitization of biological tissue section staining images and the rapid growth of computer computing power, computer-assisted biological tissue section staining image analysis technology has gradually attracted the attention of researchers and clinical pathologists. Among them, the partitioning of biological tissue section staining images is an important branch of computer-assisted biological tissue section staining image analysis. The partitioning of biological tissue section staining images can divide biological tissue section staining images into regions corresponding to different tissue types, which helps to assist pathologists in reading films and assist computer diagnosis.

[0003] The current biological tissue section staining image partitioning scheme generally obtains the biological tissue section staining image partitioning model through supervised training, and uses the biological tissue section staining image partitioning model to partition the biological tissue section staining image. However, the biological tissue section staining image partitioning model obtained through supervised training has poor versatility and can only partition the biological tissue section staining images covered by the training data set. It cannot process the biological tissue section staining images not covered by the training data set. Moreover, the supervised training of the biological tissue section staining image partitioning model requires a large number of accurately annotated training data sets. However, since the annotation of biological tissue section staining images requires a deep histopathology background, there are very few accurately annotated data sets.

[0004] Therefore, how to provide a partitioning scheme for biological tissue section staining images without the need for supervised training of biological tissue section staining image partitioning models has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0005] In view of the above problems, the present application proposes an image partitioning method, device, equipment and readable storage medium to provide a partitioning scheme for biological tissue section staining images without the need for supervised training of biological tissue section staining image partitioning models. The specific scheme is as follows:

[0006] A method for image partitioning, the method comprising:

[0007] Acquire a stained image of a biological tissue section to be partitioned;

[0008] Determining an image block to be processed in the biological tissue section staining image;

[0009] Performing feature extraction on each image block to be processed to obtain a tissue morphology feature vector of each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed;

[0010] Based on the tissue morphology feature vectors of each image block to be processed, clustering each image block to be processed to obtain a clustering result of each image block to be processed;

[0011] Based on the clustering results of each image block to be processed, the biological tissue section staining image is partitioned.

[0012] Optionally, the determining of the image block to be processed in the biological tissue section staining image includes:

[0013] Using a tissue detection algorithm to determine the tissue area and background area of ​​the biological tissue section staining image;

[0014] Segmenting the biological tissue section staining image into image blocks of equal size;

[0015] For each image block, calculating the tissue area ratio in the image block according to the tissue area and background area of ​​the image block;

[0016] The image blocks whose tissue area ratios meet the preset conditions are determined as the image blocks to be processed.

[0017] Optionally, the extracting features of each image block to be processed to obtain a tissue morphology feature vector of each image block to be processed includes:

[0018] A feature extraction network is used to extract features from each image block to be processed, thereby obtaining a tissue morphology feature vector for each image block to be processed. The feature extraction network is obtained by pre-training a convolutional neural network using a natural image data set.

[0019] Optionally, clustering each image block to be processed based on the tissue morphological feature vector of each image block to be processed to obtain a clustering result of each image block to be processed includes:

[0020] Acquiring position information of each image block to be processed in the biological tissue slice staining image;

[0021] Generate a morphological feature data set based on the position information of each image block to be processed in the biological tissue section staining image and the tissue morphological feature vector of each image block to be processed;

[0022] Based on the morphological feature data set, a tissue morphological feature spatial distribution map is generated, wherein each spatial position point in the tissue morphological feature spatial distribution map corresponds to a tissue morphological feature spectrum;

[0023] Performing dimension reduction on each tissue morphology characteristic spectrum to obtain a reduced-dimensional tissue morphology characteristic spectrum;

[0024] A clustering algorithm is used to cluster the tissue morphology characteristic spectra after dimensionality reduction to obtain multiple clusters. Each cluster corresponds to an image block to be processed with similar tissue morphology characteristic spectra, and different clusters correspond to image blocks to be processed with different tissue morphology characteristic spectra.

[0025] Optionally, partitioning the biological tissue section staining image based on the clustering results of each image block to be processed includes:

[0026] The regions corresponding to the image blocks to be processed in the biological tissue section staining image are colored according to the color information corresponding to the cluster where the image blocks to be processed are located, so as to realize the partitioning of the biological tissue section staining image.

[0027] Optionally, the dimensionality reduction of each tissue morphology characteristic spectrum to obtain a reduced-dimensional tissue morphology characteristic spectrum includes:

[0028] A nonlinear dimensionality reduction algorithm or a linear dimensionality reduction algorithm is used to reduce the dimension of each tissue morphology characteristic spectrum to obtain a reduced-dimensional tissue morphology characteristic spectrum.

[0029] Optionally, the clustering algorithm includes:

[0030] Any of Kmeans, hierarchical clustering, density-based clustering methods, maximum expectation clustering with Gaussian mixture models, graph group detection, mean shift clustering.

[0031] An image partitioning device, the device comprising:

[0032] An acquisition unit, used for acquiring a stained image of a biological tissue section to be partitioned;

[0033] A determination unit, used to determine an image block to be processed in the biological tissue section staining image;

[0034] A feature extraction unit, used to extract features from each image block to be processed to obtain a tissue morphology feature vector for each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed;

[0035] A clustering unit, used for clustering each image block to be processed based on the tissue morphology feature vector of each image block to be processed, so as to obtain a clustering result of each image block to be processed;

[0036] The partitioning unit is used to partition the biological tissue section staining image based on the clustering results of each image block to be processed.

[0037] An image partitioning device comprises a memory and a processor;

[0038] The memory is used to store programs;

[0039] The processor is used to execute the program to implement the various steps of the image partitioning method described above.

[0040] A readable storage medium stores a computer program, and when the computer program is executed by a processor, each step of the image partitioning method described above is implemented.

[0041] By means of the above technical scheme, the present application discloses an image partitioning method, device, equipment and readable storage medium. Obtain a biological tissue section staining image to be partitioned; determine the image block to be processed in the biological tissue section staining image; perform feature extraction on each image block to be processed to obtain a tissue morphology feature vector for each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to the response intensity of a tissue morphology feature in the image block to be processed; based on the tissue morphology feature vectors of each image block to be processed, cluster each image block to be processed to obtain a clustering result of each image block to be processed; based on the clustering result of each image block to be processed, partition the biological tissue section staining image. By adopting the above scheme, the biological tissue section staining image can be partitioned based on clustering, without the need for supervised training of a biological tissue section staining image partitioning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0043] Figure 1 A schematic diagram of a flow chart of an image partitioning method disclosed in an embodiment of the present application;

[0044] Figure 2 A schematic flow chart of a method disclosed in an embodiment of the present application for clustering each image block to be processed based on the tissue morphological feature vector of each image block to be processed to obtain the clustering results of each image block to be processed;

[0045] Figure 3 This is an example diagram of an image partitioning method disclosed in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the structure of an image partitioning device disclosed in an embodiment of the present application;

[0047] Figure 5 This is a hardware structure block diagram of an image partitioning device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] Next, the image partitioning method provided by the present application is introduced through the following embodiments.

[0050] Reference Figure 1 , Figure 1 This is a flow chart of an image partitioning method disclosed in an embodiment of the present application. The method may include:

[0051] Step S101: Acquire a stained image of a biological tissue section to be partitioned.

[0052] The biological tissue section staining image to be partitioned may be a biological tissue section staining image with high spatial resolution (pixel resolution less than 1 micron), for example, an H&E stained tissue microscopic image.

[0053] Step S102: determining an image block to be processed in the biological tissue section staining image.

[0054] In the present application, the biological tissue slice staining image can be cut into grid-like image blocks corresponding to smaller tissue areas as image blocks to be processed. The specific implementation will be described in detail through the following embodiments.

[0055] As an implementation method, a tissue detection algorithm can be used to determine the tissue area and background area of ​​the biological tissue section staining image; the biological tissue section staining image is divided into image blocks of equal size; for each image block, the proportion of the tissue area in the image block is calculated according to the tissue area and background area of ​​the image block; and the image block whose tissue area proportion meets the preset conditions is determined as the image block to be processed.

[0056] The method of segmenting the biological tissue section staining image into image blocks of equal size can be determined according to the scene requirements. For example, the biological tissue section staining image to be segmented includes 10 4 ╳10 4The image is divided into square image blocks of equal size in a grid shape, and the size of each image block is 10 2 ╳10 2 pixels, covering about 10 2 ╳10 2 Area in square micrometers.

[0057] The preset condition that the organizational area ratio meets is determined according to the scenario requirements. For example, the organizational area ratio can be determined to meet the preset condition if it exceeds a preset percentage (such as 90%).

[0058] Step S103: extracting features from each image block to be processed to obtain a tissue morphology feature vector for each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed.

[0059] In the present application, the tissue morphological feature vector of each image block to be processed can be various computer vision features, such as grayscale co-occurrence matrix, threshold adjacency statistics, intensity statistical features, features of the intermediate layer output of the neural network model, etc. This application does not impose any limitations on this.

[0060] As an implementable method, a feature extraction network can be used to extract features from each image block to be processed, and a tissue morphology feature vector of each image block to be processed can be obtained. The feature extraction network is obtained by pre-training a convolutional neural network using a natural image data set. For example, a convolutional neural network (such as DenseNet, ResNet, VGG, etc.) pre-trained on a natural image data set (such as ImageNet) is used as a feature extraction network. The image block to be processed is used as input after resizing and normalization preprocessing, and forward propagation is performed in the convolutional neural network. In a pre-selected intermediate layer (such as the conv5_block32 layer of DenseNet201), the 3-channel image block is converted into a three-dimensional array with a large number of channels and a small number of pixels, and each channel corresponds to a visual feature, i.e., a tissue morphology feature. Through a pooling operation (such as average global pooling), the three-dimensional array is reorganized into a tissue morphology feature vector, and each element in the tissue morphology feature vector corresponds to the response intensity of a morphological feature in the image block to be processed.

[0061] Step S104: clustering each image block to be processed based on the tissue morphology feature vector of each image block to be processed to obtain a clustering result of each image block to be processed.

[0062] In this application, the partitioning problem of biological tissue section staining images is transformed into an unsupervised clustering problem. Since unsupervised clustering does not require the construction of annotated datasets for specific tissue sample types, it not only reduces the huge cost of annotating a large number of biological tissue section staining images, but also greatly expands the scope of application of the method, and can solve the partitioning task of biological tissue section staining images with obvious morphological differences of all different tissue types.

[0063] Step S105: partitioning the biological tissue section staining image based on the clustering results of each image block to be processed.

[0064] This embodiment discloses an image partitioning method. Obtain a biological tissue section staining image to be partitioned; determine the image blocks to be processed in the biological tissue section staining image; perform feature extraction on each image block to be processed to obtain a tissue morphology feature vector for each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to the response intensity of a tissue morphology feature in the image block to be processed; cluster each image block to be processed based on the tissue morphology feature vector of each image block to be processed to obtain a clustering result of each image block to be processed; partition the biological tissue section staining image based on the clustering result of each image block to be processed. Using the above scheme, the biological tissue section staining image can be partitioned based on clustering, without the need for supervised training of a biological tissue section staining image partitioning model.

[0065] In another embodiment of the present application, a specific implementation method of clustering each image block to be processed based on the tissue morphological feature vector of each image block to be processed in step S104 to obtain the clustering result of each image block to be processed is described.

[0066] Reference Figure 2 , Figure 2 A flowchart of a method for clustering each image block to be processed based on the tissue morphological feature vector of each image block to be processed to obtain a clustering result of each image block to be processed disclosed in an embodiment of the present application, the method may include:

[0067] Step S201: obtaining position information of each image block to be processed in the biological tissue slice staining image.

[0068] Step S202: generating a morphological feature data set based on the position information of each image block to be processed in the biological tissue section staining image and the tissue morphological feature vector of each image block to be processed.

[0069] Step S203: generating a tissue morphology feature spatial distribution map based on the morphology feature data set, wherein each spatial position point in the tissue morphology feature spatial distribution map corresponds to a tissue morphology feature spectrum.

[0070] Step S204: performing dimension reduction on each tissue morphology characteristic spectrum to obtain a reduced-dimensional tissue morphology characteristic spectrum.

[0071] In this application, the number of morphological features is large, so the sample space is relatively sparse, and clustering will affect the effect. Therefore, based on the similarity between the tissue morphological feature spectra (for example, measured by trigonometric function distance), the feature dimension can be greatly reduced to three dimensions while retaining the structural relationship of the original data to the greatest extent.

[0072] In the present application, a nonlinear dimensionality reduction algorithm or a linear dimensionality reduction algorithm may be used to reduce the dimension of each tissue morphology characteristic spectrum to obtain a tissue morphology characteristic spectrum after dimensionality reduction.

[0073] Nonlinear dimensionality reduction algorithms include t-SNE (t-distributed stochastic neighbor embedding) algorithm, UMAP (Uniform Manifold Approximation and Projection) algorithm, etc.

[0074] Linear dimensionality reduction algorithms include PCA (Principal Component Analysis) algorithm, NMF (Non-negative matrix factorization), ICA (independent component analysis), etc.

[0075] Step S205: clustering each of the tissue morphology characteristic spectra after dimensionality reduction using a clustering algorithm to obtain multiple clusters, each cluster corresponding to an image block to be processed with similar tissue morphology characteristic spectra, and different clusters corresponding to image blocks to be processed with different tissue morphology characteristic spectra.

[0076] In the present application, the clustering algorithm may include: any one of Kmeans, hierarchical clustering, density-based clustering method, maximum expectation clustering using Gaussian mixture model, graph group detection, and mean shift clustering.

[0077] In this application, the histological morphological feature spectra in each cluster are similar to each other, while the clusters are quite different from each other. Based on the assumption that image blocks with similar histological morphological features belong to the same tissue type and images with different histological morphological features belong to different tissue types, the tissue type division at the image block level is achieved.

[0078] It should be noted that after clustering the tissue morphological feature spectra after dimensionality reduction by using a clustering algorithm to obtain multiple clusters, the biological tissue section staining image is partitioned based on the clustering results of each image block to be processed, which can include: coloring the image blocks to be processed according to the color information corresponding to the cluster where the image blocks to be processed are located in the area of ​​the biological tissue section staining image, so as to achieve partitioning of the biological tissue section staining image.

[0079] For easier understanding, see Figure 3 , Figure 3 This is an example diagram of an image partitioning method disclosed in an embodiment of the present application. Figure 3 As shown in the figure, after the stained tissue microscopic image is divided into image blocks, the tissue morphological features of the image blocks are extracted using a deep convolutional neural network, and then a morphological feature data set is generated based on the position information of each image block. A tissue morphological feature spatial distribution map is generated based on the morphological feature data set. Each spatial point in the tissue morphological feature spatial distribution map corresponds to a tissue morphological feature spectrum, and then dimensionality reduction and clustering are performed based on each tissue morphological feature spectrum to finally obtain the partition of the stained tissue microscopic image.

[0080] The image partitioning device disclosed in the embodiment of the present application is described below. The image partitioning device described below and the image partitioning method described above can be referenced to each other.

[0081] Reference Figure 4 , Figure 4 FIG. 1 is a schematic diagram of the structure of an image partitioning device disclosed in an embodiment of the present application. Figure 4 As shown, the image partitioning device may include:

[0082] An acquisition unit 11 is used to acquire a stained image of a biological tissue section to be partitioned;

[0083] A determination unit 12, configured to determine an image block to be processed in the biological tissue section staining image;

[0084] A feature extraction unit 13 is used to extract features from each image block to be processed to obtain a tissue morphology feature vector of each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed;

[0085] A clustering unit 14 is used to cluster each image block to be processed based on the tissue morphology feature vector of each image block to be processed, so as to obtain a clustering result of each image block to be processed;

[0086] The partitioning unit 15 is used to partition the biological tissue section staining image based on the clustering results of each image block to be processed.

[0087] Reference Figure 5 , Figure 5 The hardware structure block diagram of the image partitioning device provided in the embodiment of the present application is shown in FIG. Figure 5 ,The hardware structure of the image partitioning device may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0088] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0089] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0090] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0091] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:

[0092] Acquire a stained image of a biological tissue section to be partitioned;

[0093] Determining an image block to be processed in the biological tissue section staining image;

[0094] Performing feature extraction on each image block to be processed to obtain a tissue morphology feature vector of each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed;

[0095] Based on the tissue morphology feature vectors of each image block to be processed, clustering each image block to be processed to obtain a clustering result of each image block to be processed;

[0096] Based on the clustering results of each image block to be processed, the biological tissue section staining image is partitioned.

[0097] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0098] The embodiment of the present application further provides a readable storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0099] Acquire a stained image of a biological tissue section to be partitioned;

[0100] Determining an image block to be processed in the biological tissue section staining image;

[0101] Performing feature extraction on each image block to be processed to obtain a tissue morphology feature vector of each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed;

[0102] Based on the tissue morphology feature vectors of each image block to be processed, clustering each image block to be processed to obtain a clustering result of each image block to be processed;

[0103] Based on the clustering results of each image block to be processed, the biological tissue section staining image is partitioned.

[0104] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0105] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0106] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0107] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An image partitioning method, characterized in that: The method comprises: Acquire a stained image of a biological tissue section to be partitioned; Determining an image block to be processed in the biological tissue section staining image; Performing feature extraction on each image block to be processed to obtain a tissue morphology feature vector of each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed; Based on the tissue morphology feature vectors of each image block to be processed, clustering each image block to be processed to obtain a clustering result of each image block to be processed; Partitioning the biological tissue section staining image based on the clustering results of each image block to be processed; The clustering of each image block to be processed based on the tissue morphology feature vector of each image block to be processed to obtain the clustering result of each image block to be processed includes: Acquiring position information of each image block to be processed in the biological tissue slice staining image; Generate a morphological feature data set based on the position information of each image block to be processed in the biological tissue section staining image and the tissue morphological feature vector of each image block to be processed; Based on the morphological feature data set, a tissue morphological feature spatial distribution map is generated, wherein each spatial position point in the tissue morphological feature spatial distribution map corresponds to a tissue morphological feature spectrum; Performing dimension reduction on each tissue morphology characteristic spectrum to obtain a reduced-dimensional tissue morphology characteristic spectrum; A clustering algorithm is used to cluster the tissue morphology characteristic spectra after dimensionality reduction to obtain multiple clusters. Each cluster corresponds to an image block to be processed with similar tissue morphology characteristic spectra, and different clusters correspond to image blocks to be processed with different tissue morphology characteristic spectra.

2. The method according to claim 1, characterized in that The step of determining the image block to be processed in the biological tissue section staining image comprises: Using a tissue detection algorithm to determine the tissue area and background area of ​​the biological tissue section staining image; Segmenting the biological tissue section staining image into image blocks of equal size; For each image block, calculating the tissue area ratio in the image block according to the tissue area and background area of ​​the image block; The image blocks whose tissue area ratios meet the preset conditions are determined as the image blocks to be processed.

3. The method according to claim 1, characterized in that The step of extracting features from each image block to be processed to obtain a tissue morphology feature vector of each image block to be processed includes: A feature extraction network is used to extract features from each image block to be processed, thereby obtaining a tissue morphology feature vector for each image block to be processed. The feature extraction network is obtained by pre-training a convolutional neural network using a natural image data set.

4. The method according to claim 1, characterized in that: Partitioning the biological tissue section staining image based on the clustering results of each image block to be processed includes: The regions corresponding to the image blocks to be processed in the biological tissue section staining image are colored according to the color information corresponding to the cluster where the image blocks to be processed are located, so as to realize the partitioning of the biological tissue section staining image.

5. The method according to claim 1, characterized in that The dimension reduction of each tissue morphology characteristic spectrum to obtain the reduced tissue morphology characteristic spectrum includes: A nonlinear dimensionality reduction algorithm or a linear dimensionality reduction algorithm is used to reduce the dimension of each tissue morphology characteristic spectrum to obtain a reduced-dimensional tissue morphology characteristic spectrum.

6. The method according to claim 1, characterized in that The clustering algorithm comprises: Any of Kmeans, hierarchical clustering, density-based clustering methods, maximum expectation clustering with Gaussian mixture models, graph group detection, mean shift clustering.

7. An image partitioning device, characterized in that: The device comprises: An acquisition unit, used for acquiring a stained image of a biological tissue section to be partitioned; A determination unit, used to determine an image block to be processed in the biological tissue section staining image; A feature extraction unit, used to extract features from each image block to be processed to obtain a tissue morphology feature vector for each image block to be processed, wherein each element in the tissue morphology feature vector corresponds to a response intensity of a tissue morphology feature in the image block to be processed; A clustering unit, used for clustering each image block to be processed based on the tissue morphology feature vector of each image block to be processed, so as to obtain a clustering result of each image block to be processed; A partitioning unit, used for partitioning the biological tissue section staining image based on the clustering results of each image block to be processed; The clustering unit is specifically used to obtain the position information of each image block to be processed in the biological tissue section staining image; generate a morphological feature data set based on the position information of each image block to be processed in the biological tissue section staining image and the tissue morphological feature vector of each image block to be processed; generate a tissue morphological feature spatial distribution map based on the morphological feature data set, each spatial position point in the tissue morphological feature spatial distribution map corresponds to a tissue morphological feature spectrum; reduce the dimension of each tissue morphological feature spectrum to obtain a reduced-dimensional tissue morphological feature spectrum; use a clustering algorithm to cluster each reduced-dimensional tissue morphological feature spectrum to obtain multiple clusters, each cluster corresponds to an image block to be processed with a similar tissue morphological feature spectrum, and different clusters correspond to image blocks to be processed with different tissue morphological feature spectra.

8. An image partitioning device, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the image partitioning method according to any one of claims 1 to 6.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the image partitioning method according to any one of claims 1 to 6 is implemented.

Images