Foundation Model-Enabled Pathology-Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study.
10 affiliations
- 1Department of Radiology, Ruijin Hospital, College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- 2Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- 37T Magnetic Resonance Translational Medicine Research Center, Department of Radiology, The First Affiliated Hospital of Army Medical University, Chongqing, China.
- 4Department of Radiology, School of Medicine, Tongji Hospital, Tongji University, Shanghai, China.
- 5Department of Radiology, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai, China.
- 6Department of Radiology, The First People's Hospital of Kashi Prefecture, Kashi, Xinjiang, China.
- 7Faculty of Applied Sciences, Macao Polytechnic University, Macao, China.
- 8Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA.
- 9Department of Pathology, Eastern Hepatobiliary Surgery Hospital, The Third Affiliated Hospital of Naval Medical University, Shanghai, China.
- 10Department of Radiology, Eastern Hepatobiliary Surgery Hospital, The Third Affiliated Hospital of Naval Medical University, Shanghai, China.
Abstract
Vessels encapsulating tumor clusters (VETC) are an aggressive vascular phenotype of hepatocellular carcinoma that is usually determined after surgery. A foundation model-enabled framework for pathology-informed VETC prediction on pretreatment magnetic resonance imaging (MRI), termed PIVOT, uses paired preoperative multiparametric MRI, postoperative hematoxylin and eosin whole-slide images, and CD34 immunohistochemistry during model development, while inference requires only preoperative MRI. PIVOT-MRI uses morphologic and vascular embedding alignment, and PIVOT-Clinical combines the PIVOT-MRI score with tumor size and alpha-fetoprotein. The multicenter retrospective study includes 2052 patients in a training cohort, an internal test cohort, and four external validation cohorts. PIVOT-MRI achieves an area under the receiver operating characteristic curve of 0.887 in the internal test cohort and 0.839-0.861 across external cohorts. PIVOT-Clinical increases the internal-test area under the curve to 0.904 and PIVOT-Clinical-defined groups are associated with different two-year recurrence risks. Removing both histopathologic alignment branches results in the largest ablation-related performance decrease. Exploratory radiotranscriptomic analyses showed that higher PIVOT-MRI scores were associated with angiogenesis-related, endothelial, and proliferative transcriptional programs. PIVOT enables noninvasive preoperative assessment of pathology-defined vascular aggressiveness in resectable hepatocellular carcinoma while preserving an MRI-only clinical inference pathway.
Related
- Preoperative 3D morphological phenotyping of hepatocellular carcinoma via a foundation model: a non-invasive biomarker for recurrence risk stratification.
- Comparative study of niosomal nanoparticles encapsulating Artemisia aucheri and Artemisia sieberi extracts on Michigan Cancer Foundation-7 breast cancer cell proliferation: An in vitro study
- Preoperative ultrasound-estimated uterine weight predicts operative complexity in v-NOTES hysterectomy: A multicenter retrospective study
- The Efficacy and Safety of Combined Locoregional and Systemic Therapy versus Systemic Therapy Alone in Patients with Hepatocellular Carcinoma and Portal Vein Tumor Thrombosis: A Multicenter Real-World Retrospective Cohort Study.
- Atezolizumab plus Bevacizumab with or without Transarterial Chemoembolization as First-Line Treatment for Barcelona Clinic Liver Cancer Stage C Hepatocellular Carcinoma: A Nationwide Multicenter Retrospective Study.
BibTeX
@article{shen2026foundation,
title = {{Foundation Model-Enabled Pathology-Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study.}},
author = {Zhehan Shen and Wanmin Liu and Xiaoming Li and Wenjie Zou and Yiman Li and Jie Yuan and Yasen Yimit and Shihang Wang and Linhao Qu and Hui Dong and Wei Chen and Ningyang Jia and Peijun Wang},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
year = {2026},
month = oct,
doi = {10.1002/advs.78135},
url = {https://europepmc.org/article/MED/42893439},
note = {CC BY},
}
RIS
TY - JOUR
TI - Foundation Model-Enabled Pathology-Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study.
AU - Zhehan Shen
AU - Wanmin Liu
AU - Xiaoming Li
AU - Wenjie Zou
AU - Yiman Li
AU - Jie Yuan
AU - Yasen Yimit
AU - Shihang Wang
AU - Linhao Qu
AU - Hui Dong
AU - Wei Chen
AU - Ningyang Jia
AU - Peijun Wang
PY - 2026
DA - 2026/10/18
JO - Advanced science (Weinheim, Baden-Wurttemberg, Germany)
DO - 10.1002/advs.78135
UR - https://europepmc.org/article/MED/42893439
AB - Vessels encapsulating tumor clusters (VETC) are an aggressive vascular phenotype of hepatocellular carcinoma that is usually determined after surgery. A foundation model-enabled framework for pathology-informed VETC prediction on pretreatment magnetic resonance imaging (MRI), termed PIVOT, uses paired preoperative multiparametric MRI, postoperative hematoxylin and eosin whole-slide images, and CD34 immunohistochemistry during model development, while inference requires only preoperative MRI. PIVOT-MRI uses morphologic and vascular embedding alignment, and PIVOT-Clinical combines the PIVOT-MRI score with tumor size and alpha-fetoprotein. The multicenter retrospective study includes 2052 patients in a training cohort, an internal test cohort, and four external validation cohorts. PIVOT-MRI achieves an area under the receiver operating characteristic curve of 0.887 in the internal test cohort and 0.839-0.861 across external cohorts. PIVOT-Clinical increases the internal-test area under the curve to 0.904 and PIVOT-Clinical-defined groups are associated with different two-year recurrence risks. Removing both histopathologic alignment branches results in the largest ablation-related performance decrease. Exploratory radiotranscriptomic analyses showed that higher PIVOT-MRI scores were associated with angiogenesis-related, endothelial, and proliferative transcriptional programs. PIVOT enables noninvasive preoperative assessment of pathology-defined vascular aggressiveness in resectable hepatocellular carcinoma while preserving an MRI-only clinical inference pathway.
SN - 2198-3844
ER -