D Fan et al. Clin Gastroenterol Hepatol 2026; 24: 2571-2583. Open Access! INTELCAPE: A Deep Learning-Powered System for Automated, High-Accuracy Crohn’s Disease Diagnosis via Capsule Endoscopy
Methods: In this retrospective, multi-center study with data from 2 Chinese hospitals, the authors developed artificial intelligence, INTELCAPE, for a multi-task deep learning system, to perform small-intestine segmentation, lesion detection, and CD diagnosis from full (capsule endoscopy) CE videos.
Key findings:
- “INTELCAPE achieved state-of-the-art performance across all tasks.”
- “For lesion detection, it achieved area under the curve values of 0.993 (Cohort 1) and 0.980 (Cohort 2), with 99.33% classification accuracy, which was comparable to that of specialists (97.83%) but superior to that of residents (91.05%; P < .001).”
- “For CD diagnosis, INTELCAPE demonstrated robust generalizability, achieving area under the curve values of 0.982 (Cohort 1) and 0.984 (Cohort 2) with 90% diagnostic accuracy, comparable to that of specialists (93.33%) but 10-fold faster (P < .001).”
- “INTELCAPE improved doctors’ diagnostic accuracy (76.7%–94.8%; P < .001), while reducing their interpretation time (67.9–22.5 minutes; P < .001).”
Discussion Points:
- “CE generates thousands of images per examination, imposing a substantial analytical burden on clinicians. Manual analysis is labor-intensive and prone to human error, increasing the risk of missed lesions, particularly those with subtle appearances.”
- “Real-world clinical workflows will require prospective validation on “all-comers” populations, robust handling of poor-quality videos, and device-specific fine-tuning.”
My take: Capsule endoscopy appears to be an ideal target for AI assistance. It has the potential to improve accuracy, reduce time, and augment the performance of less experienced clinicians.
Related blog posts:
