Table 7. The classification accuracy (%) for the CA and CD features of DWT extracted from different combination of CNNs used in Gastro-CADx using Dataset II.
| Features | CA | CD | ||||
|---|---|---|---|---|---|---|
| Linear | Quadratic | Cubic | Linear | Quadratic | Cubic | |
| ResNet+DarkNet | 98.6 | 98.6 | 98.6 | 98.4 | 98.6 | 98.6 |
| AlexNet+DarkNet | 98.6 | 98.7 | 98.9 | 98.1 | 98.6 | 98.7 |
| DenseNet+DarkNet | 97.1 | 97.3 | 97.3 | 96.5 | 96.7 | 96.7 |
| AlexNet+ResNet | 98.7 | 99 | 99 | 98.6 | 98.9 | 99 |
| AlexNet+DenseNet | 97.7 | 98 | 98.1 | 97.7 | 98 | 98.1 |
| ResNet+DenseNet | 48.8 | 49 | 49.2 | 48.7 | 49 | 49.1 |
| AlexNet+ResNet +DenseNet | 99.6 | 99.6 | 99.7 | 99.5 | 99.6 | 99.5 |
| AlexNet+ResNet+DarkNet | 98.8 | 98.8 | 98.9 | 98.8 | 98.9 | 98.9 |
| AlexNet+DenseNet+DarkNet | 98.7 | 98.7 | 98.8 | 98.6 | 98.8 | 98.8 |
| ResNet+DenseNet+DarkNet | 98.8 | 98.9 | 99 | 98.7 | 99 | 99.1 |
| AlexNet+ResNet+DenseNet+DarkNet | 99.6 | 99.6 | 99.6 | 99.4 | 99.5 | 99.6 |