Pathological image processing method and device, electronic equipment and storage medium

Abstract

The invention provides a pathological image processing method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining K groups of annotation classification information of a pathological image, wherein the annotation classification information represents an annotation image recording at least one annotation region, and a classification label added to each annotation region, and the annotation area is marked out for the pathological image; evaluating the consistency of the K groups of annotation classification information to obtain evaluation information representing the consistency; and if the consistency represented by the evaluation information is higher than a preset standard, feeding back the annotation classification result to the user with the rechecking permission, wherein the annotation classification result is determined according to the K groups of annotation classification information.

Description

technical field [0001] The invention relates to the field of pathological image processing, in particular to a pathological image processing method, device, electronic equipment and storage medium. Background technique [0002] Due to the development of artificial intelligence technology, using artificial intelligence technology to solve complex medical image recognition problems has great clinical application value. The use of machines to analyze pathological images has high repeatability, can quantitative or semi-quantitative analysis results, and can reduce the repetitive work of pathologists, assisting pathologists to improve the accuracy and reliability of results. Among them, if it is necessary to classify tissues and cells in pathological images through deep learning methods, a large number of labeled images are required as training sets to train deep learning models. [0003] Among them, the work of manual labeling and classification is complicated. In the existing ...

AI Technical Summary

Problems solved by technology

[0003] Among them, the work of manual labeling and classification is complicated. In the existing related technologies, a model for labeling and classification can be trained based on a certain amount of labeling results, and then the trained model can be used to automatically label and classify newly input images.

However, in this process, the accuracy of labeling is difficult to guarantee. At the same time, professional personnel (such as doctors) are still required to participate in a complete and large amount of labeling and classification work, which also leads to a high threshold for participating in labeling and classification work.

Images