Segmentation method, device and terminal for epithelial cell nucleus in prostate cancer pathological image

Abstract

The embodiment of the invention discloses a segmentation method, device and terminal for epithelial cell nucleuses in a prostate cancer pathological image, and the method comprises the steps: carryingout the color space conversion of an obtained pathological staining image, and carrying out the cell nucleus segmentation based on a single-channel image of a converted color image; performing regionsegmentation on the initial size image and the scaled image of each cell nucleus in each single-channel image of the cell nucleus segmentation color image to obtain a single-channel region image, andperforming feature extraction on each single-channel region image; inputting the obtained single-channel image features and multi-channel image features of the cell nucleus into a cell nucleus classification model for cell nucleus classification, and determining epithelial cell nucleuses in the pathological staining image according to a classification result. According to the technical scheme, the problem that epithelial cell nucleuses in the prostate are difficult to accurately segment in the prior art can be well solved, so the accuracy of judgment on pathological diagnosis, severity and the like of the prostate cancer is improved.

Description

technical field [0001] The present invention relates to the technical field of pathological image processing, in particular to a method, device and terminal for segmenting epithelial cell nuclei in pathological images of prostate cancer. Background technique [0002] The prostate is an important organ of the male genitourinary system. A normal prostate gland is composed of lumens and epithelial cells surrounding the lumens. The area between the glands is composed of stroma and stromal cells. Prostate cancer mainly occurs in epithelial cells. The malignant expansion of epithelial cells will cause the cavity of the prostate to shrink or even be completely blocked, seriously affecting various functions of the prostate, seriously threatening the health and quality of life of men, and even the lives of patients. [0003] Prostate cancer is a malignant tumor of epithelial origin. In its clinical diagnosis, pathological diagnosis is the "gold standard", and pathological images play...

AI Technical Summary

Problems solved by technology

However, since both epithelial cell nuclei and stromal cell nuclei contain nucleic acid substances, there is no significant difference in color after being specifically combined with a stain, and it is difficult to classify epithelial cell nuclei and stromal cell nuclei using traditional image segmentation algorithms

In addition, the adjacency and overlapping phenomena between nuclei make the accuracy of nucleus segmentation still have a lot of room for improvement.

Images