Tissue segmentation method, system and equipment of sample image and medium

Abstract

The invention discloses a tissue segmentation method, system and device for a sample image of an image, and a medium, and the tissue segmentation method comprises the steps: obtaining the gene expression quantity of a to-be-segmented target tissue in the sample image, determining a gene expression matrix of the sample image, and enabling the gene expression matrix to carry out the arrangement of the gene expression quantity according to the pixel position; assigning a gene expression quantity of each pixel position in the gene expression matrix to a corresponding pixel position in a sample image to determine image data; performing image processing on the image data to determine foreground pixel points of the image data; according to the method, the connected region of the image data is marked according to the foreground pixel points to obtain the target tissue segmentation image, and the connected region is determined by determining the foreground pixel points, so that the interference of the pixel values of the background pixel points on the segmentation result is reduced, the segmentation result is more complete, and artifacts are reduced.

Description

Method, system, device and medium for tissue segmentation of sample images Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a tissue segmentation method, system, device and medium for sample images. Background Art

[0002] Tissue segmentation in medical images is a core component of medical image processing, a multidisciplinary technique involving digital image processing, pattern recognition, computer vision, and biomedicine. This technique can highlight tissue regions of interest while simplifying post-processing computational complexity, facilitating subsequent analysis.

[0003] When segmenting target tissues using existing tissue segmentation methods, smaller tissues require imaging with a high-quality microscope. However, when the image quality is poor, the segmentation effect of the target tissue in the image is poor.

[0004] Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the defect in the prior art that when the image quality is poor, the segmentation effect of the target tissue in the image is poor, and to provide a tissue segmentation method, system, device and medium for a sample image.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] In a first aspect, a tissue segmentation method for a sample image is provided, the tissue segmentation method comprising:

[0008] Obtaining gene expression levels of a target tissue to be segmented in a sample image and determining a gene expression matrix of the sample image, wherein the gene expression matrix arranges the gene expression levels according to pixel positions;

[0009] Determining image data by assigning the gene expression amount at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image;

[0010] performing image processing on the image data to determine foreground pixels of the image data;

[0011] The connected areas of the image data are marked according to the foreground pixels to obtain a target tissue segmentation image.

[0012] Optionally, determining the image data by assigning the gene expression value at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image includes:

[0013] determining an image matrix having the same size as the gene expression matrix;

[0014] The gene expression amount of each pixel position in the gene expression matrix is ​​assigned to the corresponding pixel position in the image matrix and all pixel positions are normalized to obtain image data of the sample image.

[0015] Optionally, performing image processing on the image data to determine foreground pixels of the image data includes:

[0016] Sequentially dividing the image data into foreground pixels and background pixels by using each pixel value as a pixel threshold;

[0017] Calculating the foreground average pixel value of the foreground pixel point and the background average pixel value of the background pixel point under each pixel threshold condition, and determining the variance of the foreground pixel point and the background pixel point under each pixel threshold condition based on the foreground average pixel value and the background average pixel value;

[0018] Traversing all pixel thresholds, and determining the pixel threshold corresponding to the maximum variance as the target threshold;

[0019] The foreground pixels of the image data are determined according to the target threshold value and the pixel values ​​of the foreground pixels are unified.

[0020] Optionally, the tissue segmentation method further includes:

[0021] The background pixels of the image data are determined according to the target threshold value and the pixel values ​​of the background pixels are unified.

[0022] Optionally, the tissue segmentation method further includes:

[0023] performing convolution on the image data to extract low-level features of the image data;

[0024] The determining of foreground pixels of the image data by performing image processing on the image data includes:

[0025] The foreground pixels of the image data are determined by image processing on the image data after convolution.

[0026] Optionally, the step of marking the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image includes:

[0027] performing a morphological opening operation on the image data for connected region marking to smooth edges of the connected regions of the image data;

[0028] and / or,

[0029] performing a morphological closing operation on the image data for connected region marking to eliminate small holes in the connected regions of the image data;

[0030] and / or,

[0031] Holes are filled in the image data for which connected area marking is performed.

[0032] Optionally, the step of marking the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image includes:

[0033] Foreground pixels with an adjacency relationship are determined as pixels in the same connected area.

[0034] Optionally, after determining the foreground pixels having an adjacency relationship as pixels of the same connected region, the method further includes:

[0035] Calculating the area of ​​each connected region respectively, and calculating the standard deviation and mean of all connected regions;

[0036] Determine whether the area of ​​each of the connected regions is between the standard deviation and the mean;

[0037] If so, retain the connected area;

[0038] If not, the connected region is discarded.

[0039] Optionally, after determining the image data by assigning the gene expression value at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image, the method further comprises:

[0040] downsampling the image data;

[0041] After the connected areas of the image data are marked according to the foreground pixels to obtain the target tissue segmentation image, the method includes:

[0042] The target tissue segmentation image is upsampled.

[0043] In a second aspect, a tissue segmentation system for a sample image is provided, wherein the tissue segmentation system comprises:

[0044] an acquisition module, configured to acquire gene expression levels of a target tissue to be segmented in a sample image and determine a gene expression matrix of the sample image, wherein the gene expression matrix arranges the gene expression levels according to pixel positions;

[0045] An image data determination module, configured to determine image data by assigning the gene expression value at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image;

[0046] a foreground pixel determination module, configured to determine foreground pixels of the image data by performing image processing on the image data;

[0047] The segmentation image determination module is used to mark the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image.

[0048] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the tissue segmentation method of the sample image described in the first aspect when executing the computer program.

[0049] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the method for tissue segmentation of a sample image described in the first aspect is implemented.

[0050] The present invention generates a gene expression matrix by determining the gene expression level at each pixel location and converting the gene expression matrix into image data. This reduces the need for microscopic imaging and correction of tissue images, thereby improving segmentation efficiency. The image data obtained from gene expression levels is more accurate. Connected regions are determined by identifying foreground pixels, reducing the interference of background pixel values ​​in spatial information on the segmentation results, making the segmentation results more complete and reducing artifacts. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] FIG1 is a first flow chart of a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention;

[0052] FIG2 is a flowchart of determining image data in a method for tissue segmentation of a sample image provided by an exemplary embodiment of the present invention;

[0053] FIG3 is a schematic diagram of image data of a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention;

[0054] FIG4 is a schematic diagram of a 2D convolution of a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention;

[0055] FIG5 is a schematic diagram of low-level features of a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention;

[0056] FIG6 is a schematic diagram of a binarization method for tissue segmentation of a sample image provided by an exemplary embodiment of the present invention;

[0057] FIG7 is a schematic diagram of a morphological closing operation of a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention;

[0058] FIG8 is a schematic diagram of a morphological opening operation of a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention;

[0059] FIG9 is a schematic diagram of connected regions of a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention;

[0060] FIG10 is a schematic diagram of hole filling in a tissue segmentation method of a sample image provided by an exemplary embodiment of the present invention;

[0061] FIG11 is a module diagram of a tissue segmentation system for a sample image provided by an exemplary embodiment of the present invention;

[0062] FIG12 is a structural diagram of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0063] The present invention is further described below by way of exemplary embodiments, but the present invention is not limited to the scope of the embodiments.

[0064] An embodiment of the present invention provides a tissue segmentation method for a sample image, and the tissue segmentation methods include the following types: region-based segmentation method, threshold-based segmentation method, clustering-based segmentation method, and manual segmentation method. The region-based segmentation method relies on the intensity uniformity of the image to detect the target boundary of the object area, and this method is prone to over-segmentation of the image; the threshold-based segmentation method compares the intensity value with one or more thresholds to segment the object area, and this method is prone to cause many artifacts in the segmentation of the object area, and the threshold needs to be determined through multiple experiments; the clustering-based segmentation method divides pixels into groups or clusters by using similarity metrics such as distance, connectivity, and intensity. This method does not consider spatial information and is sensitive to noise and grayscale unevenness.

[0065] FIG1 is a tissue segmentation method for a sample image provided by an exemplary embodiment of the present invention. Referring to FIG1 , the tissue segmentation method includes:

[0066] S101 , obtaining gene expression levels of a target tissue to be segmented in a sample image and determining a gene expression matrix of the sample image, wherein the gene expression matrix arranges gene expression levels according to pixel positions.

[0067] In one embodiment, the sample image may preferably be a medical image, which is not specifically limited in this embodiment and may be selected according to actual application scenarios.

[0068] In one embodiment, target tissue can include but not limited to any one or more of sample tissue, biological tissue, muscle tissue, bone tissue, cell tissue.Gene expression matrix characterizes the expression of gene in different positions (row and column position of corresponding gene expression matrix).The data composition of each gene expression amount includes gene identifier, gene coordinates and gene expression amount, characterizes the expression amount of gene in a position.With cell tissue as example, the gene expression amount of cell tissue can be determined by carrying out transcription process to the DNA of cell tissue.In addition, gene expression amount is generally in utf-8 format.

[0069] In this embodiment, the gene expression level at each pixel position in the sample image is obtained and arranged according to the row and column coordinates of the pixel position to obtain a gene expression matrix. The gene expression matrix is ​​consistent with the size of the sample image. When the gene expression level at each pixel position is 0, it indicates that the gene of the target tissue is not present at that pixel position. The gene expression level at each pixel position in the gene expression matrix can represent the gene expression level of one or more genes. If the gene expression matrix is ​​inconsistent with the size of the sample image, both images or one of the images can be scaled.

[0070] S102 : Determine image data by assigning the gene expression value at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image.

[0071] In one embodiment, step S102 specifically includes:

[0072] determining an image matrix having the same size as the gene expression matrix;

[0073] The gene expression amount of each pixel position in the gene expression matrix is ​​assigned to the corresponding pixel position in the image matrix and all pixel positions are normalized to obtain image data of the sample image.

[0074] Referring to FIG2 , the gene expression amount at each pixel position in the gene expression matrix is ​​stored in a dictionary with the row and column coordinates of each pixel position as the key and the gene expression amount as the value. An all-zero image matrix of the same size as the gene expression matrix is ​​created, and the row and column coordinates of the gene expression amount stored in the dictionary are assigned to the same position in the image matrix, that is, the gene expression amount at the same pixel position in the image matrix is ​​the same as the gene expression amount at the same pixel position in the gene expression matrix. The assigned image matrix is ​​normalized so that the pixel value of each pixel position is within the interval [0, 255], thereby obtaining image data that is more accurate relative to the sample image and reducing the impact on subsequent tissue segmentation images. The image data is shown in FIG3 . The format of the image data is preferably TIFF format, but can also be JPG format, etc. It is not limited to a specific form of expression and can be selected according to actual conditions.

[0075] In this embodiment, a gene expression matrix is ​​generated by obtaining the gene expression amount at each pixel position, and the gene expression matrix is ​​converted into image data, thereby reducing the process of repeatedly photographing and correcting tissue images through the original microscope, improving segmentation efficiency, and making the image data more accurate in displaying the target tissue compared to the initial sample image, which can improve the accuracy of subsequent target tissue determination and thus improve the accuracy of target tissue segmentation.

[0076] S103, performing image processing on the image data to determine foreground pixels of the image data;

[0077] In one embodiment, before step S103, the tissue segmentation method further includes:

[0078] As shown in Figure 4 , the image data is convolved to extract low-level features. A preferred convolution method is 2D convolution. Alternatively, dilated convolution, depthwise separable convolution, and other convolution methods can be used to improve computational accuracy and expand the field of view. The image data after convolution is shown in Figure 5 .

[0079] The foreground pixels of the image data are determined by image processing on the convolved image data.

[0080] In one embodiment, step S103 specifically includes:

[0081] Each pixel value is used as a pixel threshold to separate foreground pixels and background pixels from the image data. The pixel value is in the interval [0, 255]. Taking pixel value T0 as an example, pixels with a pixel value less than T0 are foreground pixels, and pixels with a pixel value greater than T0 are background pixels.

[0082] Calculate the foreground average pixel value of the foreground pixels and the background average pixel value of the background pixels under each pixel threshold condition.

[0083] The variance between the foreground pixel and the background pixel under each pixel threshold condition is determined according to the foreground average pixel value and the background average pixel value.

[0084] Traverse all pixel thresholds and determine the pixel threshold corresponding to the maximum variance as the target threshold;

[0085] The foreground pixels of the image data are determined according to the target threshold and the pixel values ​​of the foreground pixels are unified to 255, and the pixel values ​​of the background pixels are unified to 0 to obtain the binarized image data, as shown in FIG6 .

[0086] Optionally, foreground pixels and background pixels may be converted to each other by image inversion.

[0087] S104 , marking the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image.

[0088] In one embodiment, the connected region refers to an image region composed of foreground pixels having the same pixel value and adjacent positions in the image data, that is, a segmented region of the target tissue.

[0089] In one embodiment, step S104 specifically includes:

[0090] Foreground pixels with an adjacency relationship are determined as pixels in the same connected area.

[0091] Among them, connected region analysis methods such as the two-pass method and the seed-filling method can be used.

[0092] In this embodiment, a two-pass method is preferably adopted. Specifically, during the first scanning process, all pixel points of the image data are traversed from left to right and from top to bottom starting from the first pixel point in the upper left corner of the image data, and a label is assigned to each foreground pixel point. If the pixel point adjacent to the upper or left side of the currently scanned foreground pixel point is 0, the label value of the currently scanned foreground pixel point is increased by one. If the pixel point adjacent to the upper or left side of the currently scanned foreground pixel point is not 0, that is, there is a foreground pixel point adjacent to the currently scanned foreground pixel point, then the label value of the foreground pixel point adjacent to the upper or left side is assigned to the currently scanned foreground pixel point; since the foreground pixels located in the same connected area may have one or more labels with different values ​​during the first scanning process, the labels with different values ​​need to be merged. During the second scanning process, the label values ​​of the foreground pixels with adjacent relationships are unified, that is, assigned the same label, where the label is the minimum value of the label in the same connected area. It should be noted that the starting position of the scan in the two-pass method is not limited to a specific position. The upper left position in this embodiment is only used for illustration. In the process of assigning label values ​​to foreground pixels, the positions of adjacent pixels are also determined according to the direction of scanning, and are not specifically limited to the top or left.

[0093] Calculate the area of ​​each connected region separately, and calculate the standard deviation and mean of all connected regions;

[0094] Determine whether the area of ​​each connected region is between the standard deviation and the mean;

[0095] If so, keep the connected region;

[0096] If not, the connected region is discarded.

[0097] For the retained connected areas, the pixel values ​​of all connected areas are set to 255 to obtain the image data after the connected areas are marked.

[0098] In one embodiment, step S104 specifically includes:

[0099] Referring to FIG7 , a morphological opening operation is performed on the image data for connected region labeling, i.e., the pixels of all connected regions are traversed through the structural element, the pixels of the connected regions are dilated, and then an erosion operation is performed on the dilated connected regions to smooth the edges of the connected regions of the image data.

[0100] Referring to Figure 8, a morphological closing operation is performed on the image data for connected region labeling. This involves traversing all pixels in the connected regions using a structuring element, corroding the pixels, and then dilating the corroded connected regions to eliminate small holes in the connected regions of the image data. The image data after the morphological opening and closing operations are shown in Figure 9.

[0101] In one embodiment, step S104 specifically includes:

[0102] Holes are filled in the image data for connected area marking. Specifically, the image data is copied, and the edges of the connected areas of the copied image data are expanded to prevent incomplete hole filling. The flood filling algorithm is used for filling. The principle is to fill from the first pixel point of the connected area until all the pixels in the connected area are filled with the same pixel value. The copied image data and the image data before copying are image ORed to obtain the image data after hole filling, as shown in Figure 10.

[0103] In one embodiment, the tissue segmentation method further includes downsampling the image data and upsampling the target tissue segmentation image. The downsampling step is performed after step S102 and can employ an interpolation algorithm, preferably a nearest neighbor interpolation method, to reduce the feature dimensionality of the image data, facilitating subsequent operations and reducing computing power. Upsampling is performed after step S104, using a corresponding interpolation algorithm for upsampling and restoring the target tissue segmentation image to the same size as the gene expression matrix.

[0104] An exemplary embodiment of the present invention provides a tissue segmentation system for a sample image. Referring to FIG11 , the tissue segmentation system includes:

[0105] An acquisition module 21 is used to acquire a gene expression matrix of a target tissue, wherein the gene expression matrix includes gene expression levels of the target tissue arranged according to pixel positions;

[0106] An image data determination module 22 determines image data by assigning the gene expression value of each pixel position in the gene expression matrix to the corresponding pixel position in the sample image;

[0107] a foreground pixel determination module 23, configured to determine foreground pixels of the image data by performing image processing on the image data;

[0108] The segmented image determination module 24 is used to mark the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image.

[0109] As for the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The system embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present invention. Those of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0110] FIG12 is a block diagram of an exemplary electronic device 30 suitable for implementing an embodiment of the present invention. FIG12 is merely an example and does not limit the functionality or scope of use of the present invention.

[0111] As shown in FIG3 , electronic device 30 may be a general-purpose computing device, such as a server device. Components of electronic device 30 may include, but are not limited to, at least one processor 31, at least one memory 32, and a bus 33 connecting various system components (including memory 32 and processor 31).

[0112] The bus 33 includes a data bus, an address bus, and a control bus.

[0113] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0114] The memory 32 may also include a program tool 325 (or utility) having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0115] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the method provided in any of the above embodiments.

[0116] The electronic device 30 can also communicate with one or more external devices 34. Such communication can occur via an input / output (I / O) interface 35. Furthermore, the model-generated electronic device 30 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 37. As shown, the network adapter 37 communicates with other modules of the model-generated electronic device 30 via a bus 33. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the model-generated electronic device 30, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0117] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above may be embodied in a single unit / module. Conversely, the features and functions of a single unit / module described above may be further divided and embodied by multiple units / modules.

[0118] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the method provided in any of the above embodiments when the program is executed by a processor.

[0119] The readable storage medium may include, but is not limited to, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0120] In a possible implementation manner, the embodiment of the present invention may also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute a method for implementing any of the above embodiments.

[0121] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0122] Although specific embodiments of the present invention have been described above, those skilled in the art will appreciate that these are merely illustrative and that the scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, and such changes and modifications are intended to fall within the scope of the present invention.

Claims

1. A tissue segmentation method for a sample image, characterized in that: The tissue segmentation method comprises: Obtaining gene expression levels of a target tissue to be segmented in a sample image and determining a gene expression matrix of the sample image, wherein the gene expression matrix arranges the gene expression levels according to pixel positions; Determining image data by assigning the gene expression amount at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image; performing image processing on the image data to determine foreground pixels of the image data; The connected areas of the image data are marked according to the foreground pixels to obtain a target tissue segmentation image.

2. The tissue segmentation method according to claim 1, wherein: The determining of image data by assigning the gene expression amount at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image includes: determining an image matrix having the same size as the gene expression matrix; The gene expression amount of each pixel position in the gene expression matrix is ​​assigned to the corresponding pixel position in the image matrix and all pixel positions are normalized to obtain image data of the sample image.

3. The tissue segmentation method according to claim 1, wherein: The determining of foreground pixels of the image data by performing image processing on the image data includes: Sequentially dividing the image data into foreground pixels and background pixels by using each pixel value as a pixel threshold; Calculating the foreground average pixel value of the foreground pixel point and the background average pixel value of the background pixel point under each pixel threshold condition, and determining the variance of the foreground pixel point and the background pixel point under each pixel threshold condition based on the foreground average pixel value and the background average pixel value; Traversing all pixel thresholds, and determining the pixel threshold corresponding to the maximum variance as the target threshold; The foreground pixels of the image data are determined according to the target threshold value and the pixel values ​​of the foreground pixels are unified.

4. The tissue segmentation method according to claim 3, wherein: The tissue segmentation method further comprises: The background pixels of the image data are determined according to the target threshold value and the pixel values ​​of the background pixels are unified.

5. The tissue segmentation method according to claim 1, wherein: The tissue segmentation method further comprises: performing convolution on the image data to extract low-level features of the image data; The determining of foreground pixels of the image data by performing image processing on the image data includes: The foreground pixels of the image data are determined by image processing on the image data after convolution.

6. The tissue segmentation method according to claim 1, wherein: The step of marking the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image includes: performing a morphological opening operation on the image data for connected region marking to smooth edges of the connected regions of the image data; and / or, performing a morphological closing operation on the image data for connected region marking to eliminate small holes in the connected regions of the image data; and / or, Holes are filled in the image data for which connected area marking is performed.

7. The tissue segmentation method according to claim 1, wherein: The step of marking the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image includes: Foreground pixels with an adjacency relationship are determined as pixels in the same connected area.

8. The tissue segmentation method according to claim 7, wherein: After determining the foreground pixels having an adjacency relationship as pixels of the same connected region, the method includes: Calculating the area of ​​each connected region respectively, and calculating the standard deviation and mean of all connected regions; Determine whether the area of ​​each of the connected regions is between the standard deviation and the mean; If so, retain the connected area; If not, the connected region is discarded.

9. The tissue segmentation method according to claim 1, wherein: After determining the image data by assigning the gene expression amount at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image, the method includes: downsampling the image data; After the connected areas of the image data are marked according to the foreground pixels to obtain the target tissue segmentation image, the method includes: The target tissue segmentation image is upsampled.

10. A tissue segmentation system for a sample image, characterized in that: The tissue segmentation system comprises: an acquisition module, configured to acquire gene expression levels of a target tissue to be segmented in a sample image and determine a gene expression matrix of the sample image, wherein the gene expression matrix arranges the gene expression levels according to pixel positions; An image data determination module, configured to determine image data by assigning the gene expression value at each pixel position in the gene expression matrix to the corresponding pixel position in the sample image; a foreground pixel determination module, configured to determine foreground pixels of the image data by performing image processing on the image data; The segmentation image determination module is used to mark the connected areas of the image data according to the foreground pixels to obtain a target tissue segmentation image.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the tissue segmentation method of the sample image according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for tissue segmentation of a sample image according to any one of claims 1 to 9 is implemented.

Images