Table 1 Summarization of previous works reported for COVID-19 detection.
From: MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features
Work ref. | Method | Dataset | Obtained accuracy |
|---|---|---|---|
Shibly et al.19 | Used faster R-CNN | COVIDx dataset | 97.65% |
Zheng et al.20 | UNet+3D network | Own dataset | 90.8% |
Jaiswal et al.21 | DenseNet 201 | SARS-Cov-2 dataset | 96.25% |
Soares et al.22 | xDNN | SARS-Cov-2 dataset | 97.38% |
Panwar et al.23 | Gradient-weighted class activation mapping (Grad-CAM) | Cohen dataset | 97.08% |
Kundu et al.24 | Fuzzy rank-based fusion of VGG-11, Wide ResNet-50-2, and Inception v3 | SARS-COV-2 dataset and Harvard Dataverse chest CT dataset | 98.93% and 98.80% (respectively on SARS-COV-2 and Harvard Dataverse chest CT datasets) |
