Vendor‐Agnostic Vision Transformer‐Based Artificial Intelligence for Peroral Cholangioscopy: Diagnostic Performance in Biliary Strictures Compared With Convolutional Neural Networks and Endoscopists
The novel ViT-based AI model demonstrated high vendor-agnostic diagnostic accuracy across multiple POCS systems, achieving performance comparable to conventional CNNs and endoscopists evaluated in this study.
Authors
- Yoshiro Kawahara (ORCID: https://orcid.org/0000-0002-0509-251X)
- Koichiro Tsutsumi (ORCID: https://orcid.org/0000-0001-5728-6538)
- Shinji Kajitani
- Kentaro Oki (ORCID: https://orcid.org/0000-0002-9498-6653)
- Akihiro Matsumi (ORCID: https://orcid.org/0000-0003-0923-6143)
- Kazuya Miyamoto (ORCID: https://orcid.org/0000-0003-0464-0833)
- Masahiro Tomiya
- Daisuke Uchida (ORCID: https://orcid.org/0000-0002-2809-2707)
- Yuki Fujii
- Shigeru Horiguchi
- Kazuyuki Matsumoto (ORCID: https://orcid.org/0000-0002-5102-7452)
- Tatsuya Kikuchi (ORCID: https://orcid.org/0000-0002-2811-4371)
- Ryosuke Sato (ORCID: https://orcid.org/0000-0002-5368-6347)
- Akimitsu Ohto
- Motoyuki Otsuka (ORCID: https://orcid.org/0000-0003-2869-2881)
- Takayoshi Tanimoto
Institutions
- Ryoka Systems (Japan) (JP)
- Okayama University Hospital (JP)
Publication Details
- Journal
- Digestive Endoscopy
- Published
- 2025-09-03
- DOI
- https://doi.org/10.1111/den.70028
- Primary Topic
- Gallbladder and Bile Duct Disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Japan Agency for Medical Research and Development