Research Article
COVID-19 Diagnosis Using an Enhanced Inception-ResNetV2 Deep Learning Model in CXR Images
Table 7
Average classification results for the classification task of the new release of the dataset.
| Model | Accuracy (%) | F1-score (%) | Precision (%) | Recall (%) | Training time (s) | Testing time (s) |
| Inception-ResNetV2 | 97.23 | 96.35 | 96.75 | 96.00 | 3449 | 10.78 | Xception | 50.66 | 32.02 | 29.27 | 30.50 | 2942 | 5.74 | VGG16 | 98.29 | 97.30 | 97.48 | 97.12 | 1833 | 4.85 | ResNet50V2 | 55.48 | 50.37 | 48.65 | 56.64 | 1496 | 5.85 | InceptionV3 | 98.42 | 97.64 | 97.67 | 97.62 | 1587 | 5.70 | MobileNetV2 | 98.15 | 97.11 | 96.91 | 97.32 | 1406 | 4.64 | DenseNet121 | 98.88 | 98.18 | 97.61 | 98.78 | 1938 | 4.89 | ResNet101V2 | 98.62 | 97.93 | 97.60 | 98.27 | 2441 | 6.59 |
|
|