Figure 4. Training and validation process of 3D-VGGNet (A, C, E) and 3D-ResNet (B, D, F).

The epoch numbers for VGGNet and ResNet were 50 and 80, respectively. (A, B): Training and validation loss plot; (C, D): Validation accuracy plot; (E, F): AUC plot. In the training process, the performance 3D-VGGNet and 3D-ResNet classifiers constantly improved and then plateaued after the 50th epoch and 80th epoch, respectively.