Research Article
Research on Classification of COVID-19 Chest X-Ray Image Modal Feature Fusion Based on Deep Learning
Table 6
Comparative study of the proposed model 2 with existing works with respect to accuracy, precision, recall and F1-score.
| Author | Type of images | Architecture | Classes | Accuracy (%) | F1-score (%) | Precision (%) | Recall (%) |
| Sethy and Behera [20] | Chest X-ray | ResNet50 + SVM | 2 | 95.33 | 95.34 | — | — | Hemdan et al. [31] | Chest X-ray | VGG19 | 2 | 90.00 | 90.00 | 91.50 | 90.00 | DenseNet201 | 2 | 90.00 | 90.00 | 91.50 | 90.00 | Kumar et al. [17] | Chest X-ray | DeQueezeNet | 2 | 94.52 | — | 90.48 | 96.15 | Jaiswal et al. [34] | Chest X-ray | COVIDPEN | 2 | 96.00 | 94.00 | 92.00 | 96.00 | Ismael and Şengür [30] | Chest X-ray | ResNet50 + SVM | 2 | 94.70 | 94.79 | — | 91.00 | Das [33] | Chest X-ray | DenseNet201 + Resnet50V2 + Inceptionv3 | 2 | 91.62 | — | — | 95.09 | Sahinbas and Catak [32] | Chest X-ray | VGG16 | 2 | 80.00 | 80.00 | 80.00 | 80.00 | This study | Chest X-ray | Model 2 | 2 | 96.00 | 95.50 | 96.10 | 96.42 |
|
|