Table 4.
Classification performance attained with pre-trained DL scheme with DF and SoftMax classifier. Here TP—true positives, FN—false negatives, TN—true negatives, FP—false positives, ACC—accuracy, PRE—precision, SEN—sensitivity, SPE—specificity, NPV—negative predictive value and F1S—F1-score.
| DL Scheme (Image Size) |
TP | FN | TN | FP | ACC (%) | PRE (%) | SEN (%) | SPE (%) | NPV (%) | F1S (%) |
|---|---|---|---|---|---|---|---|---|---|---|
| VGG19 (224 × 224 × 3) |
235 | 15 | 236 | 14 | 94.20 | 94.38 | 94.00 | 94.40 | 94.02 | 94.19 |
| VGG16 (224 × 224 × 3) |
236 | 14 | 230 | 20 | 93.20 | 92.19 | 94.40 | 92.00 | 94.26 | 93.28 |
| ResNet18 (224 × 224 × 3) |
229 | 21 | 228 | 22 | 91.40 | 91.23 | 91.60 | 91.20 | 91.57 | 91.42 |
| ResNet50 (224 × 224 × 3) |
228 | 22 | 231 | 19 | 91.80 | 92.31 | 91.20 | 92.40 | 91.30 | 91.75 |
| Ale × Net (2274 × 227 × 3) |
231 | 19 | 233 | 17 | 92.80 | 93.14 | 92.40 | 93.20 | 92.46 | 92.77 |