Table 2.
Comparison of the performance of networks on the private dataset
| Methods | Acc | Sen | Spe | F1 | AUC |
|---|---|---|---|---|---|
| DenseNet121 | 0.667 | 0.722 | 0.943 | 0.664 | 0.889 |
| ResNet101 | 0.662 | 0.726 | 0.950 | 0.673 | 0.889 |
| ViT-B | 0.594 | 0.623 | 0.935 | 0.587 | 0.850 |
| Swin-B | 0.693 | 0.736 | 0.966 | 0.695 | 0.918 |
| NesT-B | 0.750 | 0.746 | 0.968 | 0.716 | 0.944 |
The bold values represent the best results in the metrics. This can make more readable and make it easier to compare the results of different methods. This also highlights the effectiveness of the proposed method