Improved Efficiency and Lesion Detection in Small Bowel Capsule Endoscopy Using the Open‐Source Artificial Intelligence Model SEE‐AI
Satoshi Miyazono, Junji Umeno, Tomohiro Nagasue, Takuto Saiki, Hisamitsu Kaku, Takehiro Torisu, Akihito Yokote, Keisuke Kawasaki, Yutaro Ihara, Yuichi Matsuno, Noriyuki Imazu, Tomohiko Moriyama, Ahmed Nashaat Mohamed, Katsuya Hirakawa, Hajime Yamagata, Yasuharu Okamoto, Koichi Kurahara, Shinichiro Y · 2026
Read Improved Efficiency and Lesion Detection in Small Bowel Capsule Endoscopy Using the Open‐Source Artificial Intelligence Model SEE‐AI by Satoshi Miyazono, Junji Umeno, Tomohiro Nagasue, Takuto Saiki, Hisamitsu Kaku, Takehiro Torisu, Akihito Yokote, Keisuke Kawasaki, Yutaro Ihara, Yuichi Matsuno, Noriyuki Imazu, Tomohiko Moriyama, Ahmed Nashaat Mohamed, Katsuya Hirakawa, Hajime Yamagata, Yasuharu Okamoto, Koichi Kurahara, Shinichiro Y (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13177839.txt.
Description
Satoshi Miyazono and co-authors test an open source artificial intelligence model for capsule endoscopy in this paper. A capsule camera films the small bowel as it passes through. The videos are long, and readers can miss lesions. The model, called SEE-AI, marks likely lesions with boxes on the video.
Records covered 249 capsule exams from six hospitals, done between 2007 and 2022. Two readers each read cases with and without the model help, in a crossover design. A panel settled the final count of 1,550 lesions. AI assisted reading was judged on lesion detection, patient level detection, and reading time. A subgroup covered cases with suspected small bowel bleeding, where finding blood related lesions matters most.
Catalog record
| CREATOR | Satoshi Miyazono, Junji Umeno, Tomohiro Nagasue, Takuto Saiki, Hisamitsu Kaku, Takehiro Torisu, Akihito Yokote, Keisuke Kawasaki, Yutaro Ihara, Yuichi Matsuno, Noriyuki Imazu, Tomohiko Moriyama, Ahmed Nashaat Mohamed, Katsuya Hirakawa, Hajime Yamagata, Yasuharu Okamoto, Koichi Kurahara, Shinichiro Y |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |