Quantitative and explainable AI-powered approaches to predict ulcerative colitis disease activity from hematoxylin and eosin (H&E)-stained whole slide images (WSI)

Study Background

Microscopic inflammation has been shown to be an important indicator of disease activity in ulcerative colitis (UC) ¹. However, manual histologic scoring is semi-quantitative and subject to interobserver variation, and AI-based solutions often lack interpretability ².

Here we report two distinct quantitative approaches to predict disease activity scores and histological remission using AI-powered digital pathology. Both the random forest classifier (RFC) and graph neural network (GNN) further provide explainability and biological insight by identifying histological features informing model predictions.

¹ Gonzalez-Partida, I. et al. Eur J Gastroenterol Hepatol. 2021; 33:e796-e802.
² Romkens, TH. et al. J Crohns Colitis. 2018; 12:425-431

Kathleen Sucipto ¹, Archit Khosla ¹, Michael G. Drage ¹, Yilan Wang ¹, Darren Fahy ¹, Mary Lin ¹, Murray B. Resnick ¹, Michael Montalto ¹, Andrew Beck ¹, Ilan Wapinski1, Stephanie Hennek ¹, Christina K.B. Jayson ¹, & Fedaa Najdawi ¹

¹ PathAI, Boston, Massachusetts

View Poster

Quantitative and explainable AI-powered approaches to predict ulcerative colitis disease activity from hematoxylin and eosin (H&E)-stained whole slide images (WSI)

Study Background

Get In Touch