Segmentation of Muscularis Propria in Colon Histopathology Images Using Vision Transformers for Hirschsprung's Disease

TL;DR

This paper demonstrates that Vision Transformers outperform CNNs and traditional methods in segmenting muscularis propria in colon histopathology images, aiding diagnosis of Hirschsprung's disease.

Contribution

It introduces the application of Vision Transformers for muscularis propria segmentation, showing superior performance over CNNs and shallow methods in histopathology image analysis.

Findings

ViT achieved a DICE score of 89.9%

ViT had a Plexus Inclusion Rate of 100%

ViTs outperform CNNs and k-means clustering in segmentation accuracy

Abstract

Hirschsprung's disease (HD) is a congenital birth defect diagnosed by identifying the lack of ganglion cells within the colon's muscularis propria, specifically within the myenteric plexus regions. There may be advantages for quantitative assessments of histopathology images of the colon, such as counting the ganglion and assessing their spatial distribution; however, this would be time-intensive for pathologists, costly, and subject to inter- and intra-rater variability. Previous research has demonstrated the potential for deep learning approaches to automate histopathology image analysis, including segmentation of the muscularis propria using convolutional neural networks (CNNs). Recently, Vision Transformers (ViTs) have emerged as a powerful deep learning approach due to their self-attention. This study explores the application of ViTs for muscularis propria segmentation in calretinin-stained histopathology images and compares their performance to CNNs and shallow learning methods. The ViT model achieved a DICE score of 89.9% and Plexus Inclusion Rate (PIR) of 100%, surpassing the CNN (DICE score of 89.2%; PIR of 96.0%) and k-means clustering method (DICE score of 80.7%; PIR 77.4%). Results assert that ViTs are a promising tool for advancing HD-related image analysis.