Table 3.
Comparison with state-of-the-art methods on the COVID-X dataset [30].
| Method | Data distribution | Accuracy % |
|---|---|---|
| COVID-Net (2020) [30] | 358 COVID-19, 5538 Pneumonia, 8066 Normal | 93.3 |
| ECOVNet (2020) [52] | 589 COVID-19 , 6053 Pneumonia, 8851 Normal | 96.00 |
| COVID-ResNet (2020) [16] | 68 COVID-19, 931 Bact. Pneumonia, 660 Viral Pneumonia, 1203 Normal | 96.23 |
| COVID-CAPS (2020) [23] | Not specified | 98.3 |
| COVIDiagnosis-Net (2020) [20] | 76 COVID-19, 4290 Pneumonia, 1583 Normal | 98.26 |
| EDL-COVID (2021) [51] | 100 COVID-19, 594 Pneumonia, 885 Normal | 95 |
| COVID-Net CT-2 S (2021) [32] | Not specified | 97.9 |
| COVID-NET CT-2 L (2021) [32] | Not specified | 98.1 |
| Blended ensembling | 568 COVID-19, 6052 Pneumonia, 8851 Normal | 94.55 |