Table 3.
Performance analysis of DCSCNN Model between binary and multiclass classification.
| Dataset | Accuracy (%) | Precision (%) | Recall (%) | F1-Score | K (%) |
|---|---|---|---|---|---|
| COVID-19 vs. Normal | 98.8 | 98.8 | 98.8 | 98.8 | 97.6 |
| COVID-19 vs. Lung Opacity | 98.2 | 98.2 | 98.3 | 98.3 | 96.4 |
| Normal vs. Lung Opacity | 97.2 | 97.2 | 97.3 | 97.3 | 94.4 |
| COVID-19 vs. Pneumonia | 96.4 | 96.4 | 96.6 | 96.5 | 92.8 |
| Lung Opacity vs. Pneumonia | 95.8 | 95.8 | 96.1 | 95.9 | 91.6 |
| Normal vs. Pneumonia | 97.4 | 97.4 | 97.5 | 97.4 | 94.8 |
| COVID-19 vs. Pneumonia vs. Lung Opacity vs.Normal | 94.7 | 94.7 | 94.8 | 94.8 | 92.8 |
K = Cohen’s kappa.