Fig. 2

Validation of the radiomic signature. A–C Kaplan–Meier curves for patients stratified by the Radscore (cutoff = − 0.1026) in the training set (A), internal validation set (B) and external validation set (C). D–F Decision curve analysis (DCA) for radiomic-clinical model nomogram and clinical model nomogram to estimate the OS in the training set (D), internal validation set (E) and external validation set (F). The x-axis represents the threshold probability and the y-axis measures the net benefit. G–J The clinical model nomogram (G) and the radiomic-clinical model nomogram (I) for predicting the 6-, 12-, 18-, and 24-month OS, along with the calibration curves for assessment of the clinical model nomogram (H) and the radiomic-clinical model nomogram (J)