Multimodal artificial intelligence for subepithelial lesion classification and characterization: a multicenter comparative study (with video)
The ECMAI-WME model demonstrates excellent diagnostic performance and robustness in the multiclass SEL classification and characterization, supporting its potential for real-time deployment to enhance diagnostic consistency and guide clinical decision-making.
Authors
- Qin Zhang (ORCID: https://orcid.org/0000-0002-6121-6513)
- Zhengkui Zhou (ORCID: https://orcid.org/0000-0002-5192-2465)
- Xun Gong (ORCID: https://orcid.org/0000-0002-1494-0955)
- Xiaojuan Jing
- Li Wang (ORCID: https://orcid.org/0000-0001-8357-172X)
- Xiaoxiang Wang (ORCID: https://orcid.org/0009-0006-2653-3982)
- Song He (ORCID: https://orcid.org/0000-0002-4136-6151)
- Xiaobin Sun (ORCID: https://orcid.org/0000-0002-9633-4691)
- Jing Shan (ORCID: https://orcid.org/0000-0002-4343-6870)
- Lin Fan (ORCID: https://orcid.org/0000-0003-1198-9582)
- Jiao Li (ORCID: https://orcid.org/0000-0002-0298-7457)
Institutions
- Dalian Medical University (CN)
- Suizhou Central Hospital (CN)
- Second Affiliated Hospital of Chongqing Medical University (CN)
- Sichuan Mianyang 404 Hospital (CN)
- First Affiliated Hospital of Chengdu Medical College (CN)
- Xiangshan County First People's Hospital (CN)
- Southwest Jiaotong University (CN)
- Chongqing Medical University (CN)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2025-08-14
- DOI
- https://doi.org/10.1186/s12911-025-03147-9
- Primary Topic
- Gastrointestinal Tumor Research and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China