Prediction of Ki-67 expression in hepatocellular carcinoma with machine learning models based on intratumoral and peritumoral radiomic features

Figure 6 The receiver operating characteristic curve shows the performance of the different models in predicting Ki-67 expression. A: Receiver operating characteristic curve comparison of the training group for the three models; B: Receiver operating characteristic curve comparison of the validation group for the three models. AUC: Area under the receiver operating characteristic curve; CI: Confidence interval.