Table 2.
Illustrates the various metrics including recall, precision, specificity and F1-score evaluated for the 4 models trained and tested on X-ray and CT scan images. Some of the values have been rounded to the nearest decimal point
| X-ray | CT scan | |||||||
|---|---|---|---|---|---|---|---|---|
| Recall (%) | Precision (%) | Specificity (%) | F1-score (%) | Recall (%) | Precision (%) | Specificity (%) | F1-score (%) | |
| Custom CNN | 94.6 | 87.6 | 86.6 | 90.9 | 95.8 | 98.2 | 98.2 | 96.9 |
| EfficientNetB0 | 98.2 | 95.3 | 95.2 | 96.7 | 95.0 | 97.3 | 97.4 | 96.2 |
| VGG-16 | 93.4 | 98.1 | 98.2 | 95.7 | 94.6 | 93.1 | 93.0 | 93.9 |
| ResNet-50 | 97.6 | 99.8 | 99.8 | 98.7 | 98.6 | 99.2 | 99.2 | 98.9 |