Table 3. Performance comparison between our methods and the state-of-the-art methods.
Method | Accuracy (%) | Total parameters |
---|---|---|
Proposed CNN + GAN | 60.5±2.6 | 55 k |
2D DenseNet | 42.2±5.5 | 116 k |
3D DenseNet | 60.2±4.6 | 405 k |
3D DenseSharp Network | 60.7±5.5 | 599 k |
Italic values indicate the best performance in each column. CNN, convolutional neural network; GAN, generative adversarial network.