Tomonori Aoki1, Atsuo Yamada1, Yusuke Kato2, Hiroaki Saito3, Akiyoshi Tsuboi4, Ayako Nakada1, Ryota Niikura1, Mitsuhiro Fujishiro5, Shiro Oka4, Soichiro Ishihara6, Tomoki Matsuda3, Masato Nakahori3, Shinji Tanaka4, Kazuhiko Koike1, Tomohiro Tada7. 1. Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan. 2. AI Medical Service Inc, Tokyo, Japan. 3. Sendai Kousei Hospital, Department of Gastroenterology, Miyagi, Japan. 4. Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan. 5. Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya, Japan. 6. Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan; Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan. 7. AI Medical Service Inc, Tokyo, Japan; Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan; Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan.
Abstract
BACKGROUND AND AIMS: A deep convolutional neural network (CNN) system could be a high-level screening tool for capsule endoscopy (CE) reading but has not been established for targeting various abnormalities. We aimed to develop a CNN-based system and compare it with the existing QuickView mode in terms of their ability to detect various abnormalities. METHODS: We trained a CNN system using 66,028 CE images (44,684 images of abnormalities and 21,344 normal images). The detection rate of the CNN for various abnormalities was assessed per patient, using an independent test set of 379 consecutive small-bowel CE videos from 3 institutions. Mucosal breaks, angioectasia, protruding lesions, and blood content were present in 94, 29, 81, and 23 patients, respectively. The detection capability of the CNN was compared with that of QuickView mode. RESULTS: The CNN picked up 1,135,104 images (22.5%) from the 5,050,226 test images, and thus, the sampling rate of QuickView mode was set to 23% in this study. In total, the detection rate of the CNN for abnormalities per patient was significantly higher than that of QuickView mode (99% vs 89%, P < .001). The detection rates of the CNN for mucosal breaks, angioectasia, protruding lesions, and blood content were 100% (94 of 94), 97% (28 of 29), 99% (80 of 81), and 100% (23 of 23), respectively, and those of QuickView mode were 91%, 97%, 80%, and 96%, respectively. CONCLUSIONS: We developed and tested a CNN-based detection system for various abnormalities using multicenter CE videos. This system could serve as an alternative high-level screening tool to QuickView mode.
BACKGROUND AND AIMS: A deep convolutional neural network (CNN) system could be a high-level screening tool for capsule endoscopy (CE) reading but has not been established for targeting various abnormalities. We aimed to develop a CNN-based system and compare it with the existing QuickView mode in terms of their ability to detect various abnormalities. METHODS: We trained a CNN system using 66,028 CE images (44,684 images of abnormalities and 21,344 normal images). The detection rate of the CNN for various abnormalities was assessed per patient, using an independent test set of 379 consecutive small-bowel CE videos from 3 institutions. Mucosal breaks, angioectasia, protruding lesions, and blood content were present in 94, 29, 81, and 23 patients, respectively. The detection capability of the CNN was compared with that of QuickView mode. RESULTS: The CNN picked up 1,135,104 images (22.5%) from the 5,050,226 test images, and thus, the sampling rate of QuickView mode was set to 23% in this study. In total, the detection rate of the CNN for abnormalities per patient was significantly higher than that of QuickView mode (99% vs 89%, P < .001). The detection rates of the CNN for mucosal breaks, angioectasia, protruding lesions, and blood content were 100% (94 of 94), 97% (28 of 29), 99% (80 of 81), and 100% (23 of 23), respectively, and those of QuickView mode were 91%, 97%, 80%, and 96%, respectively. CONCLUSIONS: We developed and tested a CNN-based detection system for various abnormalities using multicenter CE videos. This system could serve as an alternative high-level screening tool to QuickView mode.
Authors: David Chen; Clifton Fulmer; Ilyssa O Gordon; Sana Syed; Ryan W Stidham; Niels Vande Casteele; Yi Qin; Katherine Falloon; Benjamin L Cohen; Robert Wyllie; Florian Rieder Journal: J Crohns Colitis Date: 2022-03-14 Impact factor: 10.020