Machine learning modeling to predict HCC locations in cirrhotic patients undergoing MRI - a proof-of-concept study.
Authors:
- 13 July 2026
- journal article
- Published by Springer Nature in Abdominal Radiology
Abstract
Current hepatocellular carcinoma (HCC) surveillance guidelines rely on manually defined LI-RADS (Liver Imaging Reporting and Data System) features rather than imaging data analysis. This study evaluates the feasibility of machine-learning (ML)-based image analysis frameworks to identify and localize hepatic parenchyma at elevated risk for HCC. In this retrospective study, cirrhotic patients with HCC diagnosis undergoing MRI between 2008 and 2023 were included. The analysis included negative screening MRI preceding a positive screening MRI confirming a LR-5 lesion within 18 months. Volume-of-interest (VOI) annotations of 'non-malignant' and 'malignant' liver tissue on the screening MRI were manually or automatically placed, mapped from future HCC lesion on positive screening MRI. Radiomics were extracted from these VOIs using PyRadiomics. Logistic regression (LR), random forest (RF), and eXtreme Gradient Boosting (XGB) models were trained and validated across four manual/automatic annotation combinations. Exploratory voxel-level heatmaps were generated to visualize high-risk HCC areas. Model performance was summarized using median values and 95% non-parametric confidence intervals. 121 patients (65 ± 9.56; 99 men) were included. The best model performances for LR, RF, and XGB were achieved when training and validating on manual annotations: (AUC [95% CI]: 0.75 [0.72-0.78]; 0.80 [0.78-0.81]; 0.79 [0.77-0.81], respectively). Predictions from LR-3 lesions outperformed regions without visible precursor territory (RF AUC [95% CI]: 0.86 [0.84-0.88] vs. 0.66 [0.63-0.70]). In 36 out of 121 patients (30%), heatmaps showed visually increased probability signals in the region where HCC subsequently became visible on follow-up imaging. The results demonstrate the feasibility of ML-based MRI analysis for identifying liver regions at increased risk for HCC development prior to radiologic diagnosis, particularly in the presence of precursor lesions.Keywords
Funding Information
- Deutscher Akademischer Austauschdienst
- Rolf W. Günther Stiftung für Radiologische Wissenschaften
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
- NIH (NIH P30 DK034989)
This publication has 21 references indexed in Scilit:
- Accuracy of Various Forms of Contrast-Enhanced MRI for Diagnosing Hepatocellular Carcinoma: A Systematic Review and Meta-AnalysisFrontiers in Oncology, 2021
- New insights into the pathophysiology and clinical care of rare primary liver cancersJHEP Reports, 2021
- Hepatocellular carcinomaNature Reviews Disease Primers, 2021
- Deep learning–assisted differentiation of pathologically proven atypical and typical hepatocellular carcinoma (HCC) versus non-HCC on contrast-enhanced MRI of the liverEuropean Radiology, 2021
- New Arterial Phase Enhancing Nodules on MRI of Cirrhotic Liver: Risk of Progression to Hepatocellular Carcinoma and Implications for LI-RADS ClassificationAmerican Journal of Roentgenology, 2020
- Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRIEuropean Radiology, 2019
- Liver Imaging Reporting and Data System (LI-RADS) Version 2018: Imaging of Hepatocellular Carcinoma in At-Risk PatientsRadiology, 2018
- Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary StudyRadiology, 2018
- MRI With Liver-Specific Contrast for Surveillance of Patients With Cirrhosis at High Risk of Hepatocellular CarcinomaJAMA Oncology, 2017
- Early Detection, Curative Treatment, and Survival Rates for Hepatocellular Carcinoma Surveillance in Patients with Cirrhosis: A Meta-analysisPLOS Medicine, 2014