Fig. 6

Decision curve analysis (DCA). The y axis represents the net benefit, which was determined by calculating the difference between the expected benefit and the expected harm associated with each proposed model [net benefit = true-positive rate (TPR) – (false-positive rate (FPR)× weighting factor), where the weighting factor = threshold probability/ (1-threshold probability)]. The gray line represents the assumption that all tumors were histopathological high-grade (the treat-all scheme). The black line represents the assumption that all tumors were histopathological low-grade expression (the treat-none scheme). A DCA in the training cohort. For threshold probabilities from 4 to 90%, using the nomogram to predict the histopathological grade added more benefit than using the radiomics model. B DCA in the validation cohort. for threshold probabilities ranging from 8–64% and greater than 75%, using the nomogram to predict the histopathological grade added more benefit than using the TM-PTV model