CN-114332854-B - Image processing method, device, equipment and storage medium

CN114332854BCN 114332854 BCN114332854 BCN 114332854BCN-114332854-B

Abstract

The application relates to an image processing method, an image processing device, image processing equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining an identification image of a target cell nucleus based on a medical microscopic image, wherein the identification image is a multi-channel image formed by a target image block and a mask image, carrying out cell type identification based on the identification image, and obtaining the cell type of a cell corresponding to the target cell nucleus.

Inventors

ZHANG WENHUA
ZHANG JUN
HAN XIAO

Assignees

腾讯科技（深圳）有限公司

Dates

Publication Date: 20260505
Application Date: 20211216

Claims (8)

1. An image processing method, the method comprising: acquiring a medical microscopy image, the medical microscopy image comprising at least one nucleus; Based on the position information of the target cell nucleus in the at least one cell nucleus in the medical microscopic image, intercepting at least two target image blocks from the medical microscopic image; generating at least two mask images based on the position information of the target cell nuclei in at least two target image blocks, combining the at least two target image blocks with the mask images of the at least two target image blocks respectively, and generating at least two identification images, wherein the identification images are multichannel images composed of the target image blocks and the mask images; Performing cell type recognition based on the recognition image to obtain a classification probability distribution of the target cell nucleus, wherein the classification probability distribution is used for indicating the probability that cells corresponding to the target cell nucleus belong to various cell types; and obtaining the cell type of the cell corresponding to the target cell nucleus based on the classification probability distribution of the target cell nucleus.
2. The method of claim 1, wherein said capturing at least two of said target image tiles from said medical microscope image based on positional information of said target nuclei in said medical microscope image comprises: at least two target image blocks are randomly intercepted from the medical microscope image based on the position information of the target cell nuclei in the medical microscope image.
3. The method of claim 1, wherein said capturing at least two of said target image tiles from said medical microscope image based on positional information of said target nuclei in said medical microscope image comprises: based on the position information of the target cell nucleus in the medical microscopic image and at least two position limiting conditions, intercepting at least two target image blocks from the medical microscopic image; wherein the position constraint is used to limit a distance between a position of the target nucleus in the target image block and an edge of the target image block.
4. The method of claim 1, wherein the obtaining the cell type to which the cell corresponding to the target cell nucleus belongs based on the classification probability distribution of the target cell nucleus comprises: Fusing the classification probability distribution of each of at least two identification images to obtain fused classification probability distribution; And acquiring the cell type of the cell corresponding to the target cell nucleus based on the fusion classification probability distribution.
5. An image processing apparatus, characterized in that the apparatus comprises: a microscopic image acquisition module for acquiring a medical microscopic image, the medical microscopic image comprising at least one cell nucleus; The device comprises a medical microscopic image acquisition module, an identification image acquisition module, a generation module and a display module, wherein the medical microscopic image acquisition module is used for acquiring at least two target image blocks from the medical microscopic image based on the position information of target cell nuclei in the at least one cell nucleus in the medical microscopic image, wherein the positions of the target cell nuclei in different target image blocks are different; The probability distribution acquisition module is used for carrying out cell type identification based on the identification image to obtain the classification probability distribution of the target cell nucleus, wherein the classification probability distribution is used for indicating the probability that the cells corresponding to the target cell nucleus belong to various cell types; And the cell type acquisition module is used for acquiring the cell type of the cell corresponding to the target cell nucleus based on the classification probability distribution of the target cell nucleus.
6. A computer device comprising a processor and a memory having stored therein at least one computer instruction that is loaded and executed by the processor to implement the image processing method of any of claims 1 to 4.
7. A computer readable storage medium having stored therein at least one computer instruction that is loaded and executed by a processor to implement the image processing method of any of claims 1 to 4.
8. A computer program product, characterized in that the computer program product comprises computer instructions that are read and executed by a processor of a computer device, so that the computer device performs the image processing method according to any of claims 1 to 4.

Description

Image processing method, device, equipment and storage medium Technical Field The present application relates to the field of artificial intelligence, and in particular, to an image processing method, apparatus, device, and storage medium. Background With the continued development of the use of artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) in the medical field, cells in medical microscopy images can now be classified by AI to assist medical personnel in making medical-related decisions. In the related art, microscopic images containing cells can be processed through a deep neural network to obtain cell types to which the cells belong, for example, a developer can train an image recognition model in advance through a model training device, and in the application process, the microscopic images containing the cells are input into the image recognition model by the computer device, and the cell types of the cells are output from the image recognition model. However, the image recognition model in the related art has poor ability to extract characteristics related to cell classification from an input microscopic image, resulting in low accuracy of classification of cells. Disclosure of Invention The embodiment of the application provides an image processing method, an image processing device, image processing equipment and a storage medium, which can improve the accuracy of classifying cells in a microscopic image. In one aspect, there is provided an image processing method, the method including: acquiring a medical microscopy image, the medical microscopy image comprising at least one nucleus; Acquiring an identification image of a target cell nucleus in the at least one cell nucleus based on the medical microscopic image, wherein the identification image is a multi-channel image composed of a target image block and a mask image, the target image block is an image block containing the target cell nucleus in the medical microscopic image, and the mask image is used for indicating the position of the target cell nucleus in the target image block; Performing cell type recognition based on the recognition image to obtain a classification probability distribution of the target cell nucleus, wherein the classification probability distribution is used for indicating the probability that cells corresponding to the target cell nucleus belong to various cell types; and obtaining the cell type of the cell corresponding to the target cell nucleus based on the classification probability distribution of the target cell nucleus. In still another aspect, there is provided an image processing apparatus including: a microscopic image acquisition module for acquiring a medical microscopic image, the medical microscopic image comprising at least one cell nucleus; The device comprises a medical microscopic image acquisition module, an identification image acquisition module and a mask image acquisition module, wherein the medical microscopic image is used for acquiring an identification image of a target cell nucleus in at least one cell nucleus, the identification image is a multi-channel image composed of a target image block and the mask image, the target image block is an image block containing the target cell nucleus in the medical microscopic image, and the mask image is used for indicating the position of the target cell nucleus in the target image block; The probability distribution acquisition module is used for carrying out cell type identification based on the identification image to obtain the classification probability distribution of the target cell nucleus, wherein the classification probability distribution is used for indicating the probability that the cells corresponding to the target cell nucleus belong to various cell types; And the cell type acquisition module is used for acquiring the cell type of the cell corresponding to the target cell nucleus based on the classification probability distribution of the target cell nucleus. In one possible implementation, the identification image acquisition module is configured to, in response to a user input, Performing cell nucleus position identification on the medical microscopic image to obtain the position information of the target cell nucleus in the medical microscopic image; Based on the position information of the target cell nucleus in the medical microscopic image, intercepting the target image block from the medical microscopic image; generating the mask image based on the position information of the target cell nuclei in the target image block; and combining the target image block and the mask image to generate the identification image. In one possible implementation, the identification image acquisition module is configured to, in response to a user input, Based on the position information of the target cell nucleus in the medical microscopic image, at least two target image blocks are intercepted from the medical microscopic image, wherein the posi