Comparison of clinical utility of deep learning-based systems for small-bowel capsule endoscopy reading.

Tomonori AokiAtsuo YamadaShiro OkaMayo TsuboiKen KurokawaDaichi TogoFumiaki TaninoHajime TeshimaHiroaki SaitoRyuta SuzukiJunya AraiSohei AbeRyo KondoAya YamashitaAkiyoshi TsuboiAyako NakadaRyota NiikuraYosuke TsujiYoku HayakawaTomoki MatsudaMasato NakahoriShinji TanakaYusuke KatoTomohiro TadaMitsuhiro Fujishiro

Published in: Journal of gastroenterology and hepatology (2023)

Our novel CNN system significantly reduced endoscopist reading time and psychological stress while maintaining the detectability of abnormalities. CNN performance directly affects clinical utility and should be carefully assessed.

Keyphrases

small bowel
convolutional neural network
deep learning
working memory
artificial intelligence
machine learning
stress induced
sleep quality
depressive symptoms
heat stress
physical activity