Table 4 Classification performance evaluation on the NEH dataset.
From: A novel approach for automatic classification of macular degeneration OCT images
Method | #Param (mil) | Accuracy (%) | Sensitivity (%) | Specificity (%) |
|---|---|---|---|---|
VGG1614 | 28.3 | 91.6 | 91.4 | 95.6 |
ResNet5016 | 23.6 | 86.8 | 86.4 | 93.0 |
DenseNet12117 | 7.0 | 90.0 | 89.7 | 94.7 |
EfficientNetB018 | 4.0 | 85.4 | 84.5 | 92.1 |
EfficientNetV232 | 24.0 | 93.2 | 92.3 | 96.0 |
Kermany et al.25 | 0. 02 | 83.9 | 82.9 | 91.4 |
Kaymak et al.26 | 58.3 | 80.2 | 80.0 | 89.4 |
Thomas et al.29 | 2.5 | 68.5 | 69.1 | 83.8 |
FPN-VGG1630 | 21.6 | 92.6 | 91.8 | 95.8 |
Moradi31 | 158.5 | 97.3 | 97.0 | 97.2 |
MSA-NET (ours) | 27.3 | 98.1 | 97.9 | 98.0 |
