Evaluation of Preoperative Microvascular Invasion in Hepatocellular Carcinoma Through Multidimensional Parameter Combination Modeling Based on Gd-EOB-DTPA MRI

Background and Aims: The study established and compared the efficacy of the clinicoradiological model, radiomics model and clinicoradiological-radiomics hybrid model in predicting the microvascular invasion (MVI) of hepatocellular carcinoma (HCC) using gadolinium ethoxybenzyl diethylene triaminepentaacetic acid (Gd-EOB-DTPA) enhanced MRI. Methods: This was a study that enrolled 602 HCC patients from two institutions. Least absolute shrinkage and selection operator (Lasso) method was used to screen for the most important clinicoradiological and radiomics features that predict MVI pre-operatively. Three machine learning algorithms were used to establish the clinicoradiological, radiomics, and clinicoradiological-radiomics hybrid models. Area under the curve (AUC) of receiver operating characteristic (ROC) curves and Delong's test were used to compare and quantify the predictive performance of the models. Results: The AUCs of the clinicoradiological model in training and validation cohorts were 0.793 and 0.701, respectively. The radiomics signature of arterial phase (AP) images alone achieved satisfying predictive efficacy for MVI, with AUCs of 0.671 and 0.643 in training and validation cohort, respectively. The combination of clinicoradiological factors and fusion radiomics signature of AP and VP images achieved AUCs of 0.824 and 0.801 in training and validation cohorts, 0.812 and 0.805 in prospective validation and external validation cohorts, respectively. The hybrid model provided the best prediction results. The results of the Delong test revealed that there were statistically significant differences among the clinicoradiological-radiomics hybrid model, clinicoradiological model, and radiomics model (p<0.05). Conclusions: The combination of clinicoradiological factors and fusion radiomics signature of AP and VP images based on Gd-EOB-DTPA-enhanced MRI can effectively predict MVI.