Training and validating loss curves of DRUNet-34, 50, 101, and ordinary U-Net when generating synthetic T1WI and T2WI. (A) T1WI; (B) T2WI. DRUNet-X, double ResNet-U-Net with double X convolutional layers; DCNN, deep convolutional neural network; T1WI, T1-weighted images; T2WI, T2-weighted images.