Table 7.

Comparison with the current state-of-art/relevant studies.

Articles	Techniques	Dataset	Performance
Tsung et al. [52]	CNN (ResNet50)	15478 chest X-ray images (473 COVID)	accuracy, sensitivity, and specifcity obtained is 93%, 90.1%, and 89.6%
Abbas et al. [7]	CNN (DeTraC)	1768 chest X-ray images (949 COVID)	Accuracy-93.1%
Jain et al. [53]	CNN (Inception V3, Xception, and ResNet)	6432 chest X-ray images (490 COVID)	Accuracy-96% and Recall-92%
Ohata et al. [54]	Transfer learning + machine learning method (DenseNet201 + MLP)	388 chest X-ray images (194 COVID)	Acc: 95.641%, F1-score: 95.633%, FPR: 4.103%
Ioannis et al. [6]	CNN	1427 chest X-ray images (224 COVID)	accuracy, sensitivity, and specifcity obtained is 96%, 96.66%, and 96.46%
Zulfaezal et al. [55]	CNN (ResNet101)	5982 chest X-ray images (1765 COVID)	sensitivity, specificity, and accuracy of 77.3%, 71.8%, and 71.9%, respectively
Proposed study	Seven different deep CNN networks for classification and modified Unet network for segmentation	18479 chest x-ray images (3616 COVID)	accuracy of 96.29%, the sensitivity of 97.28%, and the F1-score of 96.28%. In segmentation, Accuracy of 98.63%, and Dice score of 96.94%