Table 3.
Model | CNN | DenseNet121 | ResNet50V2 | CNN | DenseNet121 | ResNet50V2 |
---|---|---|---|---|---|---|
Method | Supervised Learning |
Supervised Learning |
Supervised Learning |
Supervised Contrastive Learning |
Supervised Contrastive Learning |
Supervised Contrastive Learning |
Accuracy | 0.933 | 0.919 | 0.936 | 0.976 | 0.952 | 0.946 |
Sensitivity | 0.179 | 0.561 | 0.272 | 0.774 | 0.469 | 0.417 |
Specificity | 1.000 | 0.951 | 0.995 | 0.994 | 0.995 | 0.992 |
Prevalence | 0.081 | 0.081 | 0.081 | 0.081 | 0.081 | 0.081 |
Precision | 0.975 | 0.695 | 0.576 | 0.923 | 0.888 | 0.694 |
NPV | 0.932 | 0.961 | 0.940 | 0.980 | 0.955 | 0.951 |
F1 Score | 0.301 | 0.576 | 0.353 | 0.842 | 0.594 | 0.519 |