Table 8.
The comparisons of the customized EyeNet, ResNet50 [40], Inception V3 [44], VGG-19 [45], and the proposed E-DenseNet BC with different depths and weights on MESSIDOR dataset due to ACC, SEN, SPE, DSC, QKS, and calculation time (T) in minutes (m) performance measures
| Model | ACC (%) | SEN (%) | SPE (%) | DSC (%) | QKS | T (m) |
|---|---|---|---|---|---|---|
| A customized EyeNet | 63 | 62.5 | 90.8 | 63 | 0.48 | 15 |
| ResNet50 [40] | 37.5 | 38 | 22 | 38 | 0 | 33 |
| Inception V3 [44] | 37.5 | 38 | 40 | 38 | 0 | 50 |
| VGG19 [45] | 43.7 | 44 | 37 | 44 | 0 | 28 |
| E-DenseNet BC-169-ImageNet | 38 | 38 | 21 | 37 | 0.09 | 4 |
| E-DenseNet BC-169 | 62.5 | 63 | 76 | 61 | 0.44 | 4 |
| E-DenseNet BC-121-ImageNet | 69.2 | 70 | 90 | 68.7 | 0.53 | 2 |
| E-DenseNet BC-201-ImageNet | 50.2 | 52 | 80 | 51.5 | 0.11 | 4 |
| E-DenseNet BC-121 | 91.6 | 95 | 58 | 95.1 | 0.92 | 2 |