Artificial Intelligence in Small Bowel Capsule Endoscopy Hiroaki Saito 1 , Masato Nakahori 1 , Dai Hirasawa 1 , Tomonori Aoki 2 , Atsuo Yamada 2 , Akiyoshi Tsuboi 3 , Shiro Oka 3 , Tomohiro Tada 4 , Tomoki Matsuda 1 1Department of Gastroenterology, Sendai Kousei Hospital, Sendai, Japan 2Department of Gastroenterology, Graduate School of Medicine, the University of Tokyo, Tokyo 3Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan 4AI Medical Service Inc., Tokyo Keyword: カプセル内視鏡 , ディープラーニング , CNN , 検出 , 機械学習 pp.443-450
Published Date 2021/4/25
DOI https://doi.org/10.11477/mf.1403202300
  • Abstract
  • Look Inside
  • Reference

 The use of AI(artificial intelligence)in small bowel capsule endoscopy has been widely discussed. Developments of imaging technology and reading equipment have been the factors responsible for the clinical application of small bowel capsule endoscopy thereby improving its diagnosis. Therefore, improving these technologies by AI can be considered as inevitable. Even before the emergence of deep learning, efforts had been made to use machine learning in the field of small bowel capsule endoscopy for image diagnosis. Since the advent of deep learning technology in 2012, research on the diagnostic imaging of small bowel capsule endoscopy using AI has gained popularity, and several studies have reported it till date. In this paper, we present an up-to-date review of the research that has been reported in this field. Research with increased clinical relevance and comprehension has been emerging recently, and is dealing with large amounts of data. It is anticipated that this is an area that will continue to attract attention. Finally, we summarize future research topics and issues related to clinical implementation.

Copyright © 2021, Igaku-Shoin Ltd. All rights reserved.


電子版ISSN 1882-1219 印刷版ISSN 0536-2180 医学書院