A Segmentation Method for Poorly Differentiated Glands Based on Internal and External Stress

Abstract

The invention discloses a method for segmenting poorly differentiated glands based on internal and external stress, comprising the following steps: 1) Staining and separating pathological tissue staining images based on the ResUnet architecture to obtain hematoxylin channel and background channel images; 2) based on Improve the variational level set image segmentation algorithm of the symbolic pressure function to segment the lumen area of ​​the gland from the background channel image; 3), use the hematoxylin channel map as the input feature of SC-CNN, and obtain the boundary of the epithelial cell area, that is, the epithelial cell nucleus. 4) The graphic shape description method based on the minimum inertial axis and chain code draws the outline of the gland according to the shape feature of the lumen. The invention makes the information contained in the H&E staining image more independent and easy to identify, so as to deal with the situation of uneven staining intensity and inconspicuous staining difference, develops and combines a new set of features for segmenting gland contours, and clearly proposes a lumen And the expression method of the broad shape feature of the outer ring of the gland.

Description

technical field [0001] The invention relates to the technical field of image information processing, in particular to a method for segmenting poorly differentiated glands based on internal and external stress. Background technique [0002] Adenocarcinoma is a malignant tumor formed by glandular structures in epithelial tissue. It affects the distribution of cells and also changes the structure of the gland. A biopsy is a tissue taken from a suspicious organ in a minimally invasive manner. Pathologists use a microscope to identify biopsy tissues. Pathologists need to be precise and have the ability to detect large amounts of data to detect small abnormalities in biopsies. Taking the digestive system as an example, the histopathological staining images of the colon are the main basis for detecting lesions. Typical histopathological images of colonic glands contain four tissue components: lumen, cytoplasm, epithelial cells, and stroma (connective tissue, blood vessels, neural...

AI Technical Summary

Problems solved by technology

All of the above methods require a large number of manually annotated images, but it is very difficult to annotate a large number of medical images

Images