Objective To evaluate the diagnostic performance of radiomics features extracted from diffusion-derived Vessel Density (DDVD) in differentiating hepatocellular carcinoma (HCC) from hepatic hemangioma (HG). Methods This retrospective study enrolled 232 patients (104 with pathologically confirmed HCCs and 128 with clinically diagnosed HGs). The cohort was randomly divided into training and testing sets (7:3 ratio). We generated DDVD maps (subtraction maps of b0-b50 voxel-by-voxel). Features were extracted from b0, b50, b800, ADC, and DDVD maps, respectively. Feature selection was sequentially performed for each type of image using Mann-Whitney U test, Pearson correlation ( |r | 0.8), and LASSO regression. Five Logistic regression models (b0, b50, b800, ADC, and DDVD) were independently constructed to differentiate HCC from HG, with model performance evaluated using receiver operating characteristic analysis, with AUC, sensitivity, specificity, NPV, PPV, and accuracy as primary metrics. Delong test was utilized to evaluate the difference in performance of models. Results From a total of 1,197 features initially extracted, 10 most informative features from each image type were retained. The DDVD-based model demonstrated comparable performance to b0, b50, and ADC models, achieving AUC values of 0.926 (95% CI: 0.914 - 0.929) in the validation cohort and 0.977 (95% CI: 0.948 - 1.000) in the independent test cohort. Comparative analysis revealed that the b0, b50, ADC, and DDVD models significantly outperformed the b800 model in the test cohort (all p 0.05). Conclusions DDVD-based radiomics demonstrates an effective approach for differentiating HCC from HG by quantifying spatial heterogeneity in microvascular characteristics.
Yu et al. (2026) studied this question.