Dynamic contrast-enhanced MRI deep learning model combined with clinical model for noninvasive differentiation of hepatocellular carcinoma from mass-forming intrahepatic cholangiocarcinoma
9 affiliations
- 1Department of Medical Imaging, Xinxiang Central Hospital
- 2Department of Nuclear Medicine, The First Affiliated Hospital of Henan Medical University
- 3Department of Magnetic Resonance, The Second Hospital and Clinical Medical School, Lanzhou University
- 4Gansu Province Clinical Research Center for Functional and Molecular Imaging
- 5Gansu Medical MRI Equipment Application Industry Technology Center
- 6Department of Magnetic Resonance, The First Affiliated Hospital of Henan Medical University
- 7Interventional Diagnostic and Therapeutic Center, Zhongnan Hospital of Wuhan University
- 8Department of Radiology, Huaxi MR Research Center (HMRRC), Institute of Radiology and Medical Imaging, West China Hospital of Sichuan University
- 9Psychoradiology Key Laboratory of Sichuan Province, West China Hospital of Sichuan University
Abstract
Rationale and objectives: This study aims to develop a framework integrating dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-based multi-channel deep learning combined with clinical modeling for the non-invasive preoperative discrimination between hepatocellular carcinoma (HCC) and mass-forming intrahepatic cholangiocarcinoma (MF-ICC).
Methods: The internal development cohort comprised 334 surgically confirmed patients, including 231 patients with HCC and 103 with MF-ICC, and was divided at the patient level into a training cohort ( n = 233) and an internal validation cohort ( n = 101). The independent external validation cohort included 50 patients, comprising 40 with HCC and 10 with MF-ICC. We constructed separate two-dimensional deep learning models based on arterial phase, portal venous phase, and delayed phase images and then developed fusion models (2D model). A multi-channel deep learning model was further developed by directly inputting the three-phase images stacked along the channel dimension. Moreover, a clinical model was built based on independent predictors identified through multivariate analysis, which was ultimately integrated with the best-performing deep learning model. Model performance was evaluated and compared.
Results: Deep learning model directly feeding the three-phase images as a multi-channel input achieved better discrimination (area under the curve [AUC] = 0.814 in the internal validation cohort) than all single-phase and corresponding fusion models. The comprehensive 2D + multi-channel + clinical model showed the best performance for the differentiation of HCC from MF-ICC, achieving an AUC of 0.887 (95% CI, 0.819–0.954) in the internal validation cohort, and generalized well to the external validation cohort (AUC = 0.908; 95% CI, 0.811–1.000). However, no significant differences in AUCs were found among the models after correction for multiple comparisons.
Conclusion: The fusion model integrating clinical predictors with DCE-MRI multi-phase deep learning feature may provide a valuable tool for preoperatively differentiating HCC from MF-ICC.
Related
- Same organ, divergent immunity: T-cell exhaustion versus stromal exclusion in hepatocellular carcinoma and intrahepatic cholangiocarcinoma
- Synchronous hepatocellular carcinoma and IPNB-associated intrahepatic cholangiocarcinoma in a patient with resolved viral hepatitis: a case report of diagnostic pitfall and margin-negative resection
- Early Prognostic Value of the Freiburg Index of Post-Transjugular Intrahepatic Portosystemic Shunt Survival in Patients With Hepatocellular Carcinoma Undergoing Liver Transplantation
- HCC-miR: A Simple, Noninvasive, and Sensitive Model for Early Diagnosis of HCV-Associated Hepatocellular Carcinoma
- RTK–RAS pathway alterations in hepatocellular carcinoma and cholangiocarcinoma: a multicohort genomic and single-cell transcriptomic study
BibTeX
@article{zhang2026dynamic,
title = {{Dynamic contrast-enhanced MRI deep learning model combined with clinical model for noninvasive differentiation of hepatocellular carcinoma from mass-forming intrahepatic cholangiocarcinoma}},
author = {Huijie Zhang and Lijuan Guo and Fei Jia and Wenling Liu and Meng Zhang and Feng Li and Jun Zhou and Baolin Wu},
journal = {Frontiers in Oncology},
year = {2026},
month = oct,
doi = {10.3389/fonc.2026.1936989},
url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1936989/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Dynamic contrast-enhanced MRI deep learning model combined with clinical model for noninvasive differentiation of hepatocellular carcinoma from mass-forming intrahepatic cholangiocarcinoma
AU - Huijie Zhang
AU - Lijuan Guo
AU - Fei Jia
AU - Wenling Liu
AU - Meng Zhang
AU - Feng Li
AU - Jun Zhou
AU - Baolin Wu
PY - 2026
DA - 2026/10/23
JO - Frontiers in Oncology
DO - 10.3389/fonc.2026.1936989
UR - https://www.frontiersin.org/articles/10.3389/fonc.2026.1936989/full
AB - Rationale and objectives: This study aims to develop a framework integrating dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-based multi-channel deep learning combined with clinical modeling for the non-invasive preoperative discrimination between hepatocellular carcinoma (HCC) and mass-forming intrahepatic cholangiocarcinoma (MF-ICC). Methods: The internal development cohort comprised 334 surgically confirmed patients, including 231 patients with HCC and 103 with MF-ICC, and was divided at the patient level into a training cohort ( n = 233) and an internal validation cohort ( n = 101). The independent external validation cohort included 50 patients, comprising 40 with HCC and 10 with MF-ICC. We constructed separate two-dimensional deep learning models based on arterial phase, portal venous phase, and delayed phase images and then developed fusion models (2D model). A multi-channel deep learning model was further developed by directly inputting the three-phase images stacked along the channel dimension. Moreover, a clinical model was built based on independent predictors identified through multivariate analysis, which was ultimately integrated with the best-performing deep learning model. Model performance was evaluated and compared. Results: Deep learning model directly feeding the three-phase images as a multi-channel input achieved better discrimination (area under the curve [AUC] = 0.814 in the internal validation cohort) than all single-phase and corresponding fusion models. The comprehensive 2D + multi-channel + clinical model showed the best performance for the differentiation of HCC from MF-ICC, achieving an AUC of 0.887 (95% CI, 0.819–0.954) in the internal validation cohort, and generalized well to the external validation cohort (AUC = 0.908; 95% CI, 0.811–1.000). However, no significant differences in AUCs were found among the models after correction for multiple comparisons. Conclusion: The fusion model integrating clinical predictors with DCE-MRI multi-phase deep learning feature may provide a valuable tool for preoperatively differentiating HCC from MF-ICC.
SN - 2234-943X
ER -