Preoperative 3D morphological phenotyping of hepatocellular carcinoma via a foundation model: a non-invasive biomarker for recurrence risk stratification.
10 affiliations
- 1China-Singapore Belt and Road Joint Laboratory on Liver Disease Research, The First Hospital of Jilin University, Changchun, Jilin, China.
- 2Department of Hepatobiliary and Pancreatic Surgery, General Surgery Center, The First Hospital of Jilin University, Changchun, Jilin, China.
- 3Department of Radiology, The First Hospital of Jilin University, Changchun, Jilin, China.
- 4Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- 5Department of Radiology, Medical Imaging Institute of Tianjin, Tianjin First Central Hospital, School of Medicine, Nankai University, Tianjin, China.
- 6Department of Gastroenterology, Tonghua Second People's Hospital, Tonghua, Jilin, China.
- 7Division of Hepatobiliary & Pancreatic Surgery, Department of Surgery, National University of Singapore, Singapore.
- 8Department of Surgery, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
- 9Division of Surgical Oncology, National University Cancer Institute Singapore (NCIS), National University Health System, Singapore.
- 10National University Digestive Center (NUCD), National University Health System Singapore, Singapore.
Abstract
Background
Imaging features play a central role in hepatocellular carcinoma (HCC) staging, but current systems remain limited in prognostic precision and treatment guidance. Pathological gross classification, which categorises HCC into four subtypes based on tumour margin morphology, represents a morphological surrogate of aggressive tumour behaviour encompassing histological and molecular features and has demonstrated value in predicting prognosis and guiding adjuvant locoregional therapy selection. Importantly, gross classification is assessable through imaging, but its evaluation utterly depends on postoperative pathology and remains subjective, time-consuming and poorly reproducible. We aimed to develop a three-dimensional (3D) Foundation Model-driven system to automatically perform non-invasive morphological phenotyping and to evaluate its prognostic utility.Methods
A cohort of 551 patients who underwent hepatectomy after gadoxetic acid-enhanced MRI from two medical centres was retrospectively analysed. Pathological gross classification served as the reference standard. The 3D MorphStratify Model was built to automatically phenotype 3D gross classification with a dedicated 3D Foundation Model encoder and a channel-aware fusion module. A combined model integrating 3D MorphStratify and Conventional Imaging Predictors (Morph-CIP) was constructed and validated for recurrence risk stratification. The biological rationale linking imaging morphological phenotyping to underlying biology was preliminarily explored.Results
Eligible patients were divided into a development dataset (n=291), a validation dataset (n=192) and an external test set (n=68). The 3D MorphStratify Model achieved a micro-averaged area under the receiver operating characteristic curve (AUC) of 0.932, significantly outperforming senior radiologists (AUC 0.825) with about 40-fold improved efficiency. The imaging-based 3D morphological phenotyping (3D MorphStratify) independently predicted poor recurrence-free survival (RFS, HR 2.16, 95% CI 1.20 to 3.87, p=0.010). The Morph-CIP Model enables risk stratification through training set (AUC 0.836, 0.768, 0.765 for 1-year, 2-year, 3-year RFS), internal test set (AUC 0.816, 0.690, 0.711) and external test set (AUC 0.737, 0.709, 0.702). The high-risk group is characterised by the enrichment of glycolysis and hypoxia signalling pathways.Conclusion
3D MorphStratify is the first automated 3D morphological phenotyping system for HCC, transforming subjective pathological gross classification into an objective, non-invasive imaging biomarker. The integration of 3D MorphStratify with conventional imaging predictors enables recurrence risk stratification, potentially providing complementary information for prognostic evaluation.
Related
- Foundation Model-Enabled Pathology-Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study.
- Pathology foundation-model embeddings reveal a morphological landscape of breast lesions beyond diagnostic categories
- Development and Internal Validation of a Preoperative Risk Stratification Model for Difficult Laparoscopic Cholecystectomy in Acute Cholecystitis
- Core needle biopsy washout biomarkers combined with ultrasound for preoperative axillary risk stratification in breast cancer: a retrospective nomogram study with temporal validation
- Preoperative risk stratification for postoperative inflammatory–nutritional deterioration after colorectal cancer surgery: an interpretable machine learning study
BibTeX
@article{wang2026preoperative,
title = {{Preoperative 3D morphological phenotyping of hepatocellular carcinoma via a foundation model: a non-invasive biomarker for recurrence risk stratification.}},
author = {Hongbin Wang and Xiaogen Zhou and Kun Zhang and Kan He and Wenao Ma and Mingyang Li and Han Xue and Ye Sun and Yingzhu Cui and Xiaopeng Wang and Alfred Wei Chieh Kow and Wen Shen and Huimao Zhang and Qi Dou and Lei Zhang and Zhongqi Fan and Guoyue Lv},
journal = {EGastroenterology},
year = {2026},
month = oct,
doi = {10.1136/egastro-2026-100533},
url = {https://europepmc.org/article/MED/42876796},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Preoperative 3D morphological phenotyping of hepatocellular carcinoma via a foundation model: a non-invasive biomarker for recurrence risk stratification.
AU - Hongbin Wang
AU - Xiaogen Zhou
AU - Kun Zhang
AU - Kan He
AU - Wenao Ma
AU - Mingyang Li
AU - Han Xue
AU - Ye Sun
AU - Yingzhu Cui
AU - Xiaopeng Wang
AU - Alfred Wei Chieh Kow
AU - Wen Shen
AU - Huimao Zhang
AU - Qi Dou
AU - Lei Zhang
AU - Zhongqi Fan
AU - Guoyue Lv
PY - 2026
DA - 2026/10/12
JO - EGastroenterology
DO - 10.1136/egastro-2026-100533
UR - https://europepmc.org/article/MED/42876796
AB - Background Imaging features play a central role in hepatocellular carcinoma (HCC) staging, but current systems remain limited in prognostic precision and treatment guidance. Pathological gross classification, which categorises HCC into four subtypes based on tumour margin morphology, represents a morphological surrogate of aggressive tumour behaviour encompassing histological and molecular features and has demonstrated value in predicting prognosis and guiding adjuvant locoregional therapy selection. Importantly, gross classification is assessable through imaging, but its evaluation utterly depends on postoperative pathology and remains subjective, time-consuming and poorly reproducible. We aimed to develop a three-dimensional (3D) Foundation Model-driven system to automatically perform non-invasive morphological phenotyping and to evaluate its prognostic utility.Methods A cohort of 551 patients who underwent hepatectomy after gadoxetic acid-enhanced MRI from two medical centres was retrospectively analysed. Pathological gross classification served as the reference standard. The 3D MorphStratify Model was built to automatically phenotype 3D gross classification with a dedicated 3D Foundation Model encoder and a channel-aware fusion module. A combined model integrating 3D MorphStratify and Conventional Imaging Predictors (Morph-CIP) was constructed and validated for recurrence risk stratification. The biological rationale linking imaging morphological phenotyping to underlying biology was preliminarily explored.Results Eligible patients were divided into a development dataset (n=291), a validation dataset (n=192) and an external test set (n=68). The 3D MorphStratify Model achieved a micro-averaged area under the receiver operating characteristic curve (AUC) of 0.932, significantly outperforming senior radiologists (AUC 0.825) with about 40-fold improved efficiency. The imaging-based 3D morphological phenotyping (3D MorphStratify) independently predicted poor recurrence-free survival (RFS, HR 2.16, 95% CI 1.20 to 3.87, p=0.010). The Morph-CIP Model enables risk stratification through training set (AUC 0.836, 0.768, 0.765 for 1-year, 2-year, 3-year RFS), internal test set (AUC 0.816, 0.690, 0.711) and external test set (AUC 0.737, 0.709, 0.702). The high-risk group is characterised by the enrichment of glycolysis and hypoxia signalling pathways.Conclusion 3D MorphStratify is the first automated 3D morphological phenotyping system for HCC, transforming subjective pathological gross classification into an objective, non-invasive imaging biomarker. The integration of 3D MorphStratify with conventional imaging predictors enables recurrence risk stratification, potentially providing complementary information for prognostic evaluation.
SN - 2766-0125
SN - 2976-7296
ER -