Fig. 2From: Added value of CE-CT radiomics to predict high Ki-67 expression in hepatocellular carcinomaFlowchart of tumor segmentation, feature extraction, and model building. Manual segmentation was performed in the multi-phase images, and radiomics features were extracted. Then, LASSO was used for radiomics feature selection and finally, a model was establishment. Receiver operating characteristic (ROC) curve and the DCA curve for predicting Ki-67 status were then developed. LASSO, least absolute shrinkage and selection operator; DCA, Decision curve analysisBack to article page