Table 1.
Empirical research for detecting COVID-19 using deep learninga
| Model proposed | Study | Dataset size | Training samples sufficiency | Model performance |
|---|---|---|---|---|
| MODE (Multi-objective differential evolution) based CNN | Singh et al. [47] | 1000 + CT images | + + + | Accuracy—90.6% |
| UNET + + | Chen et al. [44] | 46,000 + CT images | + + + |
Accuracy—95.24% Sensitivity—100% Specificity—93.55% |
| Stacked Two CNN three dimensional for classification and VNET for Segmentation | Xu et al. [43] | 19,000 + CT Images with COVID-19, 1175 healthy samples | + + + | Accuracy—86.70% |
| COVNet + ResNet 50 for classification and U-Net for segmentation | Li et al. [35] | 4000 + CT Samples | + + + |
Sensitivity—90.0% Specificity—96.0% |
| Transfer Learning + ResNet 50 for classification and UNet + + (3D) for segmentation | Jin et al. [10] | 1100 + total samples with 730 positive samples | + + |
AUC—0.991 Sensitivity—97.4% Specificity—92.2% |
| Inception with Transfer Learning technique | Wang et al. [32] | 450 + CT scans of confirmed COVID-19 | + |
Accuracy—82.9% Sensitivity—84.0% Specificity—80.5% |
| Neural Networks with ResNET 50, attention technique and Feature Pyramid Network | Song et al. [42] | 750 + Images | + |
Accuracy—86.0% F-Score—87.0% Sensitivity—93.0% |
| Deep Conv Net(2D) on ResNet-50 for classification and UNet for segmentation | Gozes et al. [41] | 50 + patients’ samples | + |
AUC—0.996 Sensitivity—98.2% Specificity—92.2% |
|
VBNet neural network to Segment COVID-19 infection regions in CT scans |
Shan et al. [13] | 200 + CT scan samples | + | Dice Coef.—91.6% |
| 2D CNN | Jin et al. [10] | 970 CT Scan samples | + |
Accuracy—94.0% AUC—0.979 |
| SVM + Wavelet transformation | Barstugan et al. [39] | 150 CT Scan Samples | + | Accuracy—99.68% |
| Deep CNN(3D) for classification and U-Net for segmentation | Zheng et al. [46] | 500 + Samples | + | AUC-ROC—0.959 |
| DCNN | Heinrich et al. [31] | 500 + Samples | + | Dice Coef.—71.0% |
| CNN-LSTM | Islam et al. [60] | 4000 + X-ray Samples | + + + |
AUC—0.992 Sensitivity—99.3% Specificity—98.9% |
| VGG-19-RNN | Zabirul Islam et al. [59] | 6000 + x-ray samples(sample with CoViD, pneumonia and normal cases) | + + + |
Accuracy—99.9% AUC—99.9% Recall -99.8% |
| Ensemble DCCNs | Singh [1] | 6000 + (sample with CoViD, tuberculosis, pneumonia) | + + + | Accuracy—99.2% |
aRefer to Abbreviations for detailed nomenclature