Deep learning algorithms for automated detection of Crohn’s disease ulcers by video capsule endoscopy

• Published in: Gastrointestinal endoscopy Vol. 91; no. 3; pp. 606 - 613.e2
• Main Authors: Klang, Eyal, Barash, Yiftach, Margalit, Reuma Yehuda, Soffer, Shelly, Shimon, Orit, Albshesh, Ahmad, Ben-Horin, Shomron, Amitai, Marianne Michal, Eliakim, Rami, Kopylov, Uri
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.03.2020
• Subjects: Algorithms; Automation; Capsule Endoscopy - methods; Crohn Disease - complications; Crohn Disease - diagnostic imaging; Deep Learning; Humans; Intestinal Mucosa - diagnostic imaging; Intestine, Small - diagnostic imaging; Neural Networks, Computer; Random Allocation; Reproducibility of Results; Retrospective Studies; Ulcer - diagnostic imaging; Ulcer - etiology; AI; CD; t-SNE; CE; CNN; AUC
• ISSN: 0016-5107; 1097-6779; 1097-6779
• DOI: 10.1016/j.gie.2019.11.012

The aim of our study was to develop and evaluate a deep learning algorithm for the automated detection of small-bowel ulcers in Crohn’s disease (CD) on capsule endoscopy (CE) images of individual patients. We retrospectively collected CE images of known CD patients and control subjects. Each image w...