Diagnostic Value of Radiomics Analysis Based on Multimodal MRI for Advanced Liver Fibrosis in Patients with Hepatitis B

Background: The goal was to explore the value of using radiomics analysis based on multimodal MRI for evaluating the advanced fibrosis in patients with hepatitis B. Methods: One hundred and forty-three patients with hepatitis B fibrosis were randomly divided into training and validation cohorts in a 2:1 ratio. In the training cohort, a clinical model was established with logistic regression, a radiomics signature based on multimodal MRI was established with support vector machine (SVM), and a nomogram integrated the radiomics signature and clinical factors. The value of three models was assessed by ROC analysis in the training and validation cohorts. Results: The nomogram demonstrated the largest area under the ROC curve. The nomogram presented good agreement in the prediction probability of advanced liver fibrosis in two cohorts. Conclusions: Radiomics analysis has good diagnostic value for advanced liver fibrosis and the nomogram can enhance the diagnostic value.