CGH: INTELCAPE for automated, high-accuracy Crohn's disease diagnosis via capsule endoscopy
Mar 19, 2026
·
1 min read
Our team published INTELCAPE in Clinical Gastroenterology and Hepatology, an AI system for automated capsule endoscopy analysis that supports faster and more accurate Crohn’s disease diagnosis.
INTELCAPE combines small-intestine segmentation, lesion detection, and video-level diagnosis in one pipeline. Across multi-center capsule endoscopy cohorts, it achieved specialist-level diagnostic performance while markedly reducing review time and improving clinician performance with AI assistance.
Key points:
- Built and evaluated on 872 capsule endoscopy videos from two Chinese hospitals.
- Reached AUCs of 0.982 and 0.984 for Crohn’s disease diagnosis, with 90% diagnostic accuracy.
- Improved clinicians’ accuracy from 76.7% to 94.8% and cut interpretation time from 67.9 to 22.5 minutes.