Table 4.
Models trained with 70% of the data achieved accuracy and kappa values of no less than 0.95 and 0.88, respectively.
| Model | Epoch | CNN | Learner | Accuracy | Sensitivity | Specificity | PPV | NPV | Kappa |
|---|---|---|---|---|---|---|---|---|---|
| M73 | 15 | ResNet50 | SVM | 0.95 | 0.97 | 0.91 | 0.96 | 0.93 | 0.89 |
| M57 | 10 | DenseNet201 | SVM | 0.96 | 0.98 | 0.91 | 0.96 | 0.95 | 0.90 |
| M88 | 20 | ResNet50 | SVM | 0.96 | 0.97 | 0.94 | 0.97 | 0.94 | 0.91 |
| M58 | 10 | ResNet50 | SVM | 0.97 | 0.97 | 0.97 | 0.99 | 0.92 | 0.92 |
| M87 | 20 | DenseNet201 | SVM | 0.97 | 0.97 | 0.95 | 0.98 | 0.94 | 0.92 |
| M60 | 10 | VGG19 | SVM | 0.97 | 0.97 | 0.97 | 0.99 | 0.94 | 0.93 |
| M56 | 10 | AlexNet | SVM | 0.98 | 0.99 | 0.94 | 0.97 | 0.98 | 0.94 |
| M71 | 15 | AlexNet | SVM | 0.98 | 0.99 | 0.95 | 0.98 | 0.97 | 0.94 |
| M75 | 15 | VGG19 | SVM | 0.98 | 0.99 | 0.95 | 0.98 | 0.97 | 0.94 |
| M59 | 10 | VGG16 | SVM | 0.98 | 0.99 | 0.97 | 0.99 | 0.97 | 0.96 |
| M74 | 15 | VGG16 | SVM | 0.98 | 1.00 | 0.94 | 0.97 | 1.00 | 0.96 |
| M86 | 20 | AlexNet | SVM | 0.98 | 0.98 | 0.98 | 0.99 | 0.95 | 0.96 |
| M89 | 20 | VGG16 | SVM | 0.98 | 0.98 | 0.98 | 0.99 | 0.95 | 0.96 |
| M90 | 20 | VGG19 | SVM | 0.99 | 0.99 | 0.97 | 0.99 | 0.98 | 0.97 |