Predicting the Grade of Prostate Cancer Based on a Biparametric MRI Radiomics Signature

Figure 5

ROC curves of the radiomics signature in the training (a) and test (b) cohorts. ROC curves for the radiomics-based ADC and T2WI model and PI-RADS (c) score performance in distinguishing low- vs. high-grade PCa in the training and test groups. RF, random forest tree; SVM, support vector machine. Predictive ability of the PI-RADS V 2.1 model.

(a)

(b)

(c)