Research Article
COVID-19 Diagnosis Using an Enhanced Inception-ResNetV2 Deep Learning Model in CXR Images
Table 5
Average classification results for the classification task of the original dataset.
| Model | Accuracy (%) | F1-score (%) | Precision (%) | Recall (%) | Training time (s) | Testing time (s) |
| Inception-ResNetV2 | 98.80 | 98.86 | 98.61 | 99.11 | 1138 | 4.10 | Xception | 98.30 | 98.45 | 98.15 | 98.78 | 1051 | 2.13 | VGG16 | 97.60 | 97.30 | 98.29 | 96.40 | 912 | 1.85 | ResNet50V2 | 97.60 | 97.65 | 97.08 | 98.28 | 890 | 2.28 | InceptionV3 | 97.90 | 98.20 | 97.90 | 98.51 | 894 | 2.16 | MobileNetV2 | 98.10 | 97.67 | 98.67 | 96.77 | 881 | 1.74 | DenseNet121 | 98.30 | 98.45 | 98.15 | 98.78 | 940 | 1.91 | ResNet101V2 | 97.40 | 97.19 | 97.50 | 96.90 | 1006 | 2.55 |
|
|