MRI-based Radiomics:Associations With The Recurrence-free Survival Of Patients With Hepatocellular Carcinoma Treated With Conventional Transcatheter Arterial Chemoembolization

Objectives: Preoperative estimation of hepatocellular carcinoma(HCC)recurrence after conventional transcatheter arterial chemoembolization(TACE)is crucial for subsequent follow-up and therapy decisions.To evaluate the associations of radiomics models based on pretreatment contrast-enhanced magnetic resonance imaging(MRI),a clinicalradiological model and a combined model with the recurrence-free survival(RFS)of patients with HCC after TACE and to develop a radiomics nomogram for individual RFS estimations and risk stratification.Methods: A total of 184 consecutive HCC patients were enrolled and randomly divided into the training(n=110)and validation datasets(n=74).Radiomics signatures capturing intratumoral and peritumoral expansion(1,3,and 5 mm)were constructed,and the radiomics models were set up using least absolute shrinkage and selection operator(LASSO)Cox regression.Clinical-radiological features were identified by univariate and multivariate Cox regression.The clinical-radiological model and the combined model fusioning the radiomics signature with the clinical-radiological risk factors,were developed by multivariate Cox proportional hazard model.The performance of each model was evaluated using the concordance index(Cindex)and Kaplan-Meier analysis was used for risk stratification,and independent validation datasets were used for verification.A radiomics nomogram derived from the combined model was established.Results: The intratumoral portal venous phase model(C-index,0.727)was superior to the arterial phase(C-index,0.644)and the clinicalradiological models(C-index,0.692).Among the different peritumoral expansion models,only the 3-mm peritumoral expansion model showed a comparable predictive performance(P = 0.4087)to that of the portal venous phase intratumoral model,and the C-index of the model was 0.714 in the validation cohort.The combined model showed the best predictive performance(C-index,0.802).Kaplan-Meier analysis showed that the cutoff values of the combined model relative to a median value(1.7426)perfectly stratified these patients into high-risk and low-risk subgroups in the training and validation cohorts.Conclusions: The combined model is more valuable than the clinicalradiological model or radiomics model alone for evaluating the RFS of HCC patients after TACE,and the radiomics nomogram can be used to preoperatively and individually estimate RFS.