Masashi Misawa1, Shin-Ei Kudo1, Yuichi Mori2, Kinichi Hotta3, Kazuo Ohtsuka4, Takahisa Matsuda5, Shoichi Saito6, Toyoki Kudo1, Toshiyuki Baba1, Fumio Ishida1, Hayato Itoh7, Masahiro Oda7, Kensaku Mori7. 1. Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan. 2. Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan; Clinical Effectiveness Research Group, Institute of Health and Society, University of Oslo, Oslo, Norway. 3. Division of Endoscopy, Shizuoka Cancer Center, Shizuoka, Japan. 4. Department of Endoscopy, Tokyo Medical and Dental University, Tokyo, Japan. 5. Cancer Screening Center, National Cancer Center Hospital, Tokyo, Japan; Division of Screening Technology, Center for Public Health Sciences, National Cancer Center, Tokyo, Japan; Endoscopy Division, National Cancer Center Hospital, Tokyo, Japan. 6. Department of Gastroenterology, The Cancer Institute Hospital, Tokyo, Japan. 7. Graduate School of Informatics, Nagoya University, Nagoya, Japan.
Abstract
BACKGROUND AND AIMS: Artificial intelligence (AI)-assisted polyp detection systems for colonoscopic use are currently attracting attention because they may reduce the possibility of missed adenomas. However, few systems have the necessary regulatory approval for use in clinical practice. We aimed to develop an AI-assisted polyp detection system and to validate its performance using a large colonoscopy video database designed to be publicly accessible. METHODS: To develop the deep learning-based AI system, 56,668 independent colonoscopy images were obtained from 5 centers for use as training images. To validate the trained AI system, consecutive colonoscopy videos taken at a university hospital between October 2018 and January 2019 were searched to construct a database containing polyps with unbiased variance. All images were annotated by endoscopists according to the presence or absence of polyps and the polyps' locations with bounding boxes. RESULTS: A total of 1405 videos acquired during the study period were identified for the validation database, 797 of which contained at least 1 polyp. Of these, 100 videos containing 100 independent polyps and 13 videos negative for polyps were randomly extracted, resulting in 152,560 frames (49,799 positive frames and 102,761 negative frames) for the database. The AI showed 90.5% sensitivity and 93.7% specificity for frame-based analysis. The per-polyp sensitivities for all, diminutive, protruded, and flat polyps were 98.0%, 98.3%, 98.5%, and 97.0%, respectively. CONCLUSIONS: Our trained AI system was validated with a new large publicly accessible colonoscopy database and could identify colorectal lesions with high sensitivity and specificity. (Clinical trial registration number: UMIN 000037064.).
BACKGROUND AND AIMS: Artificial intelligence (AI)-assisted polyp detection systems for colonoscopic use are currently attracting attention because they may reduce the possibility of missed adenomas. However, few systems have the necessary regulatory approval for use in clinical practice. We aimed to develop an AI-assisted polyp detection system and to validate its performance using a large colonoscopy video database designed to be publicly accessible. METHODS: To develop the deep learning-based AI system, 56,668 independent colonoscopy images were obtained from 5 centers for use as training images. To validate the trained AI system, consecutive colonoscopy videos taken at a university hospital between October 2018 and January 2019 were searched to construct a database containing polyps with unbiased variance. All images were annotated by endoscopists according to the presence or absence of polyps and the polyps' locations with bounding boxes. RESULTS: A total of 1405 videos acquired during the study period were identified for the validation database, 797 of which contained at least 1 polyp. Of these, 100 videos containing 100 independent polyps and 13 videos negative for polyps were randomly extracted, resulting in 152,560 frames (49,799 positive frames and 102,761 negative frames) for the database. The AI showed 90.5% sensitivity and 93.7% specificity for frame-based analysis. The per-polyp sensitivities for all, diminutive, protruded, and flat polyps were 98.0%, 98.3%, 98.5%, and 97.0%, respectively. CONCLUSIONS: Our trained AI system was validated with a new large publicly accessible colonoscopy database and could identify colorectal lesions with high sensitivity and specificity. (Clinical trial registration number: UMIN 000037064.).
Authors: Steven A Hicks; Inga Strümke; Vajira Thambawita; Malek Hammou; Michael A Riegler; Pål Halvorsen; Sravanthi Parasa Journal: Sci Rep Date: 2022-04-08 Impact factor: 4.379