Biologically interpretable deep learning–derived MRI phenotypes reveal lymph node involvement and neoadjuvant therapy response in intrahepatic cholangiocarcinoma
The SwinU-CliRad model can serve as a biologically interpretable tool for LN risk stratification in iCCA surgical candidates, with high-risk patients identified by the model potentially deriving benefit from NAT.
Authors
- Siqi Yin (ORCID: https://orcid.org/0000-0003-0012-0187)
- Danlan Lian (ORCID: https://orcid.org/0009-0007-2650-9357)
- Manning Wang (ORCID: https://orcid.org/0000-0002-9255-3897)
- Wentao Wang (ORCID: https://orcid.org/0009-0004-7556-211X)
- Si-Si Rao
- Xuping Mao (ORCID: https://orcid.org/0009-0005-3615-3062)
- Ruoyu Shi
- Jinjun Wang
- Q Xu
- Dong Liangqing
- Danjun Song
- Danjiang Huang
- Lei Wu
- Wei Sun
- Qiang Gao
- Jiayi Xing
- Kai Zhu
- Xiangge Guo
Institutions
- Yuncheng University (CN)
- Nanjing University of Chinese Medicine (CN)
- Shanghai Medical College of Fudan University (CN)
- Chinese Academy of Sciences (CN)
- Changzhi Medical College (CN)
- Fudan University (CN)
- Fudan University Shanghai Cancer Center (CN)
- Zhejiang Cancer Hospital (CN)
- Shanghai Xuhui Central Hospital (CN)
- Zhongshan Hospital of Xiamen University (CN)
- Zhongshan Hospital (CN)
- Taizhou First People's Hospital (CN)
- National University Hospital (SG)
- Shanghai Institute of Hematology (CN)
- National University Health System (SG)
- Shanghai Institute of Computing Technology (CN)
Publication Details
- Journal
- Hepatology
- Published
- 2026-01-12
- DOI
- https://doi.org/10.1097/hep.0000000000001671
- Citations
- 1
- Primary Topic
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Type
- article
- Field-Weighted Citation Impact
- 39.15