Predicting ulcer in H&E images of inflammatory bowel disease using domain-knowledge-driven graph neural network
This work addresses the need for accurate ulcer prediction in medical imaging to support personalized treatment for inflammatory bowel disease patients, representing an incremental improvement over existing methods.
The paper tackled the problem of identifying ulcer regions in whole slide images of inflammatory bowel disease to aid in biomarker discovery, proposing a weakly-supervised graph neural network that incorporates domain knowledge and outperforms state-of-the-art multiple instance learning methods.
Inflammatory bowel disease (IBD) involves chronic inflammation of the digestive tract, with treatment options often burdened by adverse effects. Identifying biomarkers for personalized treatment is crucial. While immune cells play a key role in IBD, accurately identifying ulcer regions in whole slide images (WSIs) is essential for characterizing these cells and exploring potential therapeutics. Multiple instance learning (MIL) approaches have advanced WSI analysis but they lack spatial context awareness. In this work, we propose a weakly-supervised model called DomainGCN that employs a graph convolution neural network (GCN) and incorporates domain-specific knowledge of ulcer features, specifically, the presence of epithelium, lymphocytes, and debris for WSI-level ulcer prediction in IBD. We demonstrate that DomainGCN outperforms various state-of-the-art (SOTA) MIL methods and show the added value of domain knowledge.