Biologically interpretable deep learning-derived MRI phenotypes reveal lymph node involvement and neoadjuvant therapy response in intrahepatic cholangiocarcinoma.
Authors
Affiliations (17)
Affiliations (17)
- Department of Radiology, Cancer center, Zhongshan Hospital, Fudan University, Shanghai 200032, China.
- Shanghai Institute of Medical Imaging, Shanghai 200032, China.
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China.
- Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai 200032, China.
- Department of Hepatobiliary Surgery and Liver Transplantation, Liver Cancer Institute and Zhongshan Hospital, Fudan University, Shanghai, China.
- Department of Head and Neck Surgery, Fudan University, Shanghai Cancer Center, Shanghai, China.
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China.
- Department of Interventional Radiology, Zhejiang Cancer Hospital, Hangzhou, Zhejiang 310022, China; Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang 310018, China.
- Department of Radiology, Zhongshan Hospital (Xiamen), Fudan University, Xiamen 361015, China.
- Department of Radiology, Yuncheng Central Hospital affiliated to Shanxi Medical University.
- Graduate School of Changzhi Medical College.
- Department of Radiology, Taizhou First People's Hospital, Taizhou, Zhejiang Province, 318020, China.
- Department of Radiology, Shanghai Xuhui District Central Hospital, Shanghai 200231, China.
- Zhangjiagang TCM Hospital Affiliated to Nanjing University of Chinese Medicine.
- Department of Pathology, National University Hospital, National University Health System, Singapore 119074, Singapore.
- Key Laboratory of Medical Epigenetics and Metabolism, Institutes of Biomedical Sciences, Fudan University, Shanghai 200032, China.
- State Key Laboratory of Genetic Engineering, Fudan University, Shanghai 200433, China.
Abstract
Accurate N-staging of intrahepatic cholangiocarcinoma (iCCA) remains challenging using noninvasive approaches. We aimed to develop a model to refine lymph node (LN) involvement stratification and inform therapeutic consideration. This study enrolled a discovery cohort (n=682), an internal test cohort from the FU-iCCA (n=204) and an external multicenter cohort (n=88) for model development, and a neoadjuvant therapy (NAT) cohort (n=145) for therapeutic evaluation of the model. A SwinU-CliRad framework was constructed by integrating Swin UNEt TRansformers (SwinU)-based magnetic resonance imaging-derived outputs of LN involvement with clinicoradiological features. Correlations between SwinU outputs and tumor multi-omics profiles were explored. The SwinU-CliRad model achieved area under the curves of 0.932, 0.867, and 0.888 in LN risk stratification, and outperformed radiologist-based assessments by correcting more misclassifications than it introduced across the discovery, internal and external test cohorts (18.8% vs. 7.3%, 18.1% vs. 4.9%, and 17.0% vs. 5.7%), respectively. In the NAT cohort, patients classified as high LN-involved risk by the SwinU-CliRad exhibited lower residual viable tumor rates than those with low LN-involved risk, with higher rates of pathological complete response (12.0% vs. 4.2%) and major pathological response (14.0% vs. 8.4%). SwinU outputs were associated with KRAS mutations, MUC5AC overexpression and the large-duct histological subtype. Single-cell RNA sequencing analysis linked LN involvement to an immune-suppressive stroma tumor microenvironment. 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.