Fig. 3: ROC curves of three models in predicting the progression of DR.
From: Forecasting the diabetic retinopathy progression using generative adversarial networks
Our DRForecastGAN model outperforms both Pix2Pix and CycleGAN models, achieving the highest AUC values on both internal validation (0.87 vs.0.76 vs.0.75) (a) and external test (0.85 vs.0.70 vs.0.69) (b) datasets.
