Related Experiment Video
Updated: May 26, 2026
A Three-Dimensional Digital Model for Early Diagnosis of Hepatic Fibrosis Based on Magnetic Resonance Elastography
Published on: July 21, 2023
Construction of a classification model for liver fibrosis in MAFLD based on multiparametric MRI radiomics and machine
Xing Xia1, Jian He1, Yong Wen1
1Department of Radiology, Affiliated Hospital of Guizhou Medical University, Guiyang, Guizhou, China.
Background:
Liver fibrosis (LF) severity is an important factor in the clinical management and prognosis of patients with metabolic dysfunction-associated fatty liver disease (MAFLD). Conventional imaging modalities and routine clinical parameters may lack sufficient precision for accurate fibrosis staging. Multiparametric magnetic resonance imaging (mpMRI) provides a noninvasive, quantitative approach that may improve fibrosis assessment.
Objectives:
This study aimed to develop and validate a machine learning-based classification model for staging LF severity in MAFLD using mpMRI radiomics in a rat model.
Materials And Methods:
A prospective mpMRI study was conducted on 160 male Sprague-Dawley rats with histologically confirmed LF of varying severity, including healthy controls. Imaging was performed using T2-weighted fat-suppressed (T2-FS) and IDEAL-IQ sequences to derive proton density fat fraction, in-phase, and out-of-phase images. Radiomic features were extracted and screened to identify the most discriminative subset, which were then integrated with six machine learning classifiers-logistic regression (LR), decision tree (DT), support vector machine (SVM), random forest (RF), LightGBM, and AdaBoost, using a 7:3 training-to-validation split. Three models were constructed: conventional, deep learning-based, and hybrid. Diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), net reclassification improvement (NRI), and calibration curves. The optimal model was further assessed with a confusion matrix and benchmarked against the best convolutional neural network (CNN) model. Interpretability was examined via SHapley Additive exPlanations (SHAP) analysis.
Results:
All three models showed good diagnostic performance for staging LF in metabolic dysfunction-associated steatohepatitis (MASH) and outperformed the CNN model. The hybrid model yielded the highest AUC in distinguishing advanced from non-advanced fibrosis (0.982, 95% CI: 0.947-1.000) with an accuracy of 88%. SHAP analysis indicated that deep learning-derived features made the greatest contribution to predictions and were positively associated with increased risk of MASH and fibrosis progression.
Conclusion:
In a rat model of MAFLD, mpMRI-based radiomics combined with machine learning demonstrated promising diagnostic performance for classifying MASH and staging associated LF. This noninvasive approach may help differentiate advanced from non-advanced in MASH, which may provide supportive information and has potential to support clinical decision-making.
Insights
Machine learning and multiparametric MRI radiomics accurately stage liver fibrosis in metabolic dysfunction-associated fatty liver disease (MAFLD) rats. This noninvasive method aids in differentiating advanced fibrosis, supporting clinical decisions for MAFLD patients.
Area of Science:
- Radiology
- Machine Learning
- Hepatology
Background:
- Liver fibrosis (LF) severity is crucial for managing metabolic dysfunction-associated fatty liver disease (MAFLD).
- Current imaging and clinical methods lack precision for accurate LF staging.
- Multiparametric magnetic resonance imaging (mpMRI) offers a noninvasive, quantitative approach for fibrosis assessment.
Purpose of the Study:
- To develop and validate a machine learning (ML) model for LF staging in MAFLD using mpMRI radiomics.
- To assess the model's diagnostic performance in a rat model.
Main Methods:
- 160 male Sprague-Dawley rats with varying LF severity underwent mpMRI (T2-FS, IDEAL-IQ).
- Radiomic features were extracted and screened; ML classifiers (LR, DT, SVM, RF, LightGBM, AdaBoost) were trained and validated.
- Three models (conventional, deep learning, hybrid) were constructed and evaluated using AUC, DCA, NRI, and calibration curves.
Main Results:
- All developed models demonstrated good diagnostic performance for LF staging in MAFLD, outperforming a CNN model.
- The hybrid model achieved the highest AUC (0.982) for distinguishing advanced from non-advanced fibrosis with 88% accuracy.
- SHAP analysis revealed deep learning features significantly contributed to predictions, correlating with MASH and fibrosis progression risk.
Conclusions:
- mpMRI-based radiomics combined with ML shows promise for noninvasively classifying MASH and staging LF in MAFLD.
- This approach can help differentiate advanced from non-advanced fibrosis in MASH.
- The findings have potential to support clinical decision-making in MAFLD management.
