Cell adhesion segmentation method and device based on confidence score

Abstract

The invention relates to a cell adhesion segmentation method and device based on confidence score. The method comprises the following steps: processing an original image through a neural network model to obtain a prediction map based on confidence score; binarizing the prediction image according to a first threshold value to obtain a binary image; the binary image is optimized, and all connected domains in the optimized binary image are extracted; screening the connected domains according to a preset area threshold to obtain a connected domain image; calculating a distance map based on the binary image, and determining a segmentation boundary line according to the distance map; and integrating the connected domain image and the segmentation boundary to obtain a segmentation result of cell adhesion. According to the method, the confidence score of the original image is predicted through the convolutional neural network segmentation model, the intersection region at the boundary of each connected domain is obtained through the binarized image, dual confirmation is performed on the segmentation of the adhesion cells, and wrong adhesion segmentation caused by a problem of one result is avoided.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a method and device for cell adhesion segmentation based on confidence score. Background technique [0002] In daily pathological diagnosis, pathologists need to count cells in pathological images when interpreting some types of immunohistochemical indicators, such as breast cancer immunohistochemical Ki67, ER, PR, etc., according to the requirements of pathological guidelines. Classification and statistical analysis. In recent years, with the rapid development of big data and artificial intelligence, intelligent diagnosis systems based on image processing and deep learning have gradually entered the field of medical diagnosis. The intelligent diagnosis system can automatically segment or evaluate tissues and cells in digital pathological images. , to assist pathologists in diagnosis. [0003] In the related art, in the process of cell segmentation, du...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, in the process of cell segmentation, due to the adhesion of the cells themselves during imaging, it is difficult for the cell segmentation algorithm to automatically separate the adherent cells, which affects the inaccurate evaluation results related to the number such as counting, and ultimately affects intelligent diagnosis. the accuracy of

Images