QUANTITATIVE AND EXPLAINABLE ARTIFICIAL INTELLIGENCE (AI)-POWERED APPROACHES TO PREDICT ULCERATIVE COLITIS DISEASE ACTIVITY FROM HEMATOXYLIN AND EOSIN (H&E)-STAINED WHOLE SLIDE IMAGES (WSI)

• Published in: Inflammatory bowel diseases Vol. 29; no. Supplement_1; pp. S22 - S23
• Main Authors: Sucipto, Kathleen, Khosla, Archit, Drage, Michael, Wang, Yilan, Fahy, Darren, Lin, Mary, Resnick, Murray, Montalto, Mike, Beck, Andrew, Wapinski, Ilan, Hennek, Stephanie, Jayson, Christina, Najdawi, Fedaa
• Format: Journal Article
• Language: English
• Published: US Oxford University Press 01.02.2023
• Subjects: Artificial intelligence; Inflammatory bowel disease; Neural networks; Remission (Medicine)

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