Improving image-retrieval performance of foundation models in gastrointestinal endoscopic images
These findings demonstrate that the proposed dual-backbone framework offers an accurate and automated tool for assessing the procedural quality of gastrointestinal endoscopy and may facilitate more reliable quality control in clinical practice.
Authors
- Youngbae Hwang (ORCID: https://orcid.org/0000-0002-3400-0493)
- Junseok Park (ORCID: https://orcid.org/0000-0001-5607-1041)
- Kangsan Kim (ORCID: https://orcid.org/0000-0002-5283-8644)
- Sang Hyun Kim (ORCID: https://orcid.org/0000-0002-5668-6502)
Institutions
- Chungbuk National University (KR)
- Soonchunhyang University (KR)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-12-18
- DOI
- https://doi.org/10.3389/fmed.2025.1727884
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research Foundation
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion
- Division of Human Resource Development