Table 10. Accuracy obtained by existing models and models used in the study.
| References | Images Type | No of Images | Method | Accuracy |
|---|---|---|---|---|
| Ozturk et al. [10] | Chest x-ray | 125COVID-19 / 500Normal | DarkCovidNet | 98.08% |
| Chest x-ray | 125COVID-19/ 500Normal/ 500Pneumonia | DarkCovidNet | 87.02% | |
| Narin et al. [8] | Chest x-ray | 50COVID-19 / 50Normal | ResNet50, Deep CNN | 98% |
| Sethey et al. [59] | Chest x-ray | 25COVID-19 / 25Normal | ResNet50 + SVM | 95.38% |
| Ioannis et al. [58] | Chest x-ray | 224COVID-19 / 700Pneumonia / 504Normal | VGG-19 | 93.48% |
| Wang et al. [9] | Chest x-ray | 53COVID-19 / 5526Normal | COVID-Net | 92.4% |
| Hemdan et al. [57] | Chest x-ray | 25COVID-19 / 25Normal | COVIDX-Net | 90% |
| Zheng et al. [62] | Chest CT | 213COVID-19 / 229Normal | UNet+3D Network | 90.8% |
| Ying et al. [60] | Chest CT | 777COVID-19 / 708 Normal | DRE-Net | 86% |
| Xu et al. [18] | Chest CT | 219COVID-19 / 175Normal / 224Pneumonia | ResNet + Location Attention | 86.7% |
| wang et al. [61] | Chest CT | 195COVID-19 / 258Normal | M-Inception | 82.9% |
| Our Proposed CNN Method | Chest x-ray | 140COVID-19 / 140Normal | CNN | 97.62% |
| Chest x-ray | 140COVID-19 / 140Normal /140 Pneumonia | CNN | 93.75% | |
| Our Employed Pre-trained Method | Chest x-ray | 140COVID-19 / 140Normal | VGG16 | 100% |
| Chest x-ray | 140COVID-19 / 140Normal /140 Pneumonia | VGG16 | 87.50% |