Histological images segmentation of mucous glands

TL;DR

This paper reviews current trends in histological image segmentation and introduces a new convolutional neural network designed specifically for segmenting mucous glands, aiding in more accurate diagnosis of colon polyps.

Contribution

The paper presents a novel convolutional neural network tailored for mucous gland segmentation in histology images, enhancing diagnostic accuracy.

Findings

Designed a new CNN architecture for gland segmentation

Improved accuracy in mucous gland detection

Facilitated better quantitative diagnostic methods

Abstract

Mucous glands lesions analysis and assessing of malignant potential of colon polyps are very important tasks of surgical pathology. However, differential diagnosis of colon polyps often seems impossible by classical methods and it is necessary to involve computer methods capable of assessing minimal differences to extend the capabilities of the classical pathology examination. Accurate segmentation of mucous glands from histology images is a crucial step to obtain reliable morphometric criteria for quantitative diagnostic methods. We review major trends in histological images segmentation and design a new convolutional neural network for mucous gland segmentation.