Objectives: To evaluate the value of a CT-based radiomics signature in pre-operatively predicting the early recurrence(<1 year)of hepatocellular carcinoma(HCC).Methods: A total of 215 HCC patients who underwent resection between 2004 and 2015 were enrolled in this retrospective study.Radiomics features were extractedfrom arterial-and portal venous phase CTimages,and aradiomics signature was builtusinga least absolute shrinkage and selectionoperator(LASSO)logistic regression model.Pre-operative clinical factors associated with early recurrence were evaluated.A radiomics signature,clinical model and combined model were built,and the area under the curve(AUC)of operating characteristics(ROC)was used to explore their performance to discriminate early recurrence.Results: Twenty-one radiomics features were chosen from 300 candidate features to build a radiomics signaturethatwas significantly associated with early recurrence(P<0.001)and presented good performance in the discrimination ofearly recurrence alone with an AUC of 0.817(95%CI: 0.758─0.866),sensitivity of 0.794 and specificity of 0.699.The AUCs of the clinicaland combined model were0.781(95%CI: 0.719─0.834)and 0.836(95%CI: 0.779─0.883),respectively,with the sensitivity being 0.784 and 0.824 and the specificity being 0.619 and 0.708.Adding a radiomics signature into conventional clinical variables can significantly improve the accuracy of the pre-operative model in predicting early recurrence(P=0.01).Conclusions: The radiomics signature was a significant predictor for early recurrence in HCC.Incorporating a radiomics signature into conventional clinical factors may help clinicians better stratify patients for treatmentand adopt anindividualized monitoring protocol to improve clinicaloutcomes,which need to be validated in future studies.