AI-powered three-category Helicobacter pylori diagnosis via magnetic controlled capsule endoscopy: a multicenter validation of a vision-language model
By integrating multimodal image-text data and performing end-to-end analysis, MC-CLIP effectively addresses the fundamental limitations of CNN-based approaches. The model shows strong potential for enhancing the accuracy and reliability of MCCE-based gastric cancer screening programs.
Authors
- Fei Teng
- X. Sun (ORCID: https://orcid.org/0000-0001-9500-7288)
- Hongmei Jiao (ORCID: https://orcid.org/0000-0002-9139-9744)
- Jing Liu (ORCID: https://orcid.org/0000-0002-3311-0818)
- Xiao Chen (ORCID: https://orcid.org/0000-0002-4438-5286)
- Jiaxin Li (ORCID: https://orcid.org/0000-0002-3113-0874)
- Ting Zhang (ORCID: https://orcid.org/0000-0001-8074-8999)
- Peng Jin (ORCID: https://orcid.org/0000-0001-6685-1906)
- Lili Wu (ORCID: https://orcid.org/0000-0002-4108-893X)
- Xiaona Ma (ORCID: https://orcid.org/0000-0002-7194-9550)
- Xin Fan (ORCID: https://orcid.org/0000-0003-0307-1675)
- Shiping Xu
- Hui Su (ORCID: https://orcid.org/0000-0002-5174-8217)
Institutions
- Peking University (CN)
- Chinese PLA General Hospital (CN)
- Peking University First Hospital (CN)
Publication Details
- Journal
- Frontiers in Microbiology
- Published
- 2025-10-13
- DOI
- https://doi.org/10.3389/fmicb.2025.1687021
- Primary Topic
- Helicobacter pylori-related gastroenterology studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00