Table 4.
Comparisons with related literatures.
| Literatures | Methods | Images (classes) | Dataset Quant | Test _acc (%) |
|---|---|---|---|---|
| Mukherjee32 | Shallow CNN | X-ray(2) | 260 | 96.92 |
| Abbas33 | DeTrac | X-ray(2) | 1764 | 95.12 |
| Gupta34 | COVID-WideNet | X-ray(2) | 13,942 | 91 |
| Hemdan35 | COVIDX-Net | X-ray(2) | 50 | 91 |
| Apostolopoulos36 | MobileNet v2(transfer learning) | X-ray(2) | 1419 | 87.02 |
| Wu37 | ASA-CoroNet | X-ray(3) | 994 | 97.59 |
| Ozturk38 | DarkCovidNet | X-ray(3) | 1442 | 96.78 |
| Aslan39 | Deep Learning &Machine Learning | X-ray(3) | 2905 | 96.29 |
| Quan40 | DenseCapsNet | X-ray(3) | 750 | 90.7 |
| Chen8 | MGMADS-3 | X-ray(4) | 17,439 | 96.75 |
| Wang7 | COVID-Net | X-ray(4) | 13,975 | 93.3 |
| Khan41 | CoroNet | X-ray(4) | 1300 | 89.6 |
| Proposed | RMT-Net | X-ray(4) | 25,100 | 97.65 |
| Chen42 | UNet++ | CT(2) | 35,355 | 98.85 |
| Rahimzadeh43 | Feature Pyramid Network | CT(2) | 63,849 | 98.49 |
| Chen8 | MGMADS-3 | CT(2) | 10,839 | 98.25 |
| Yang44 | Ednc | CT(2) | 2458 | 97.55 |
| Song9 | DRE-Net | CT(2) | 1485 | 94.0 |
| Singh45 | MODE-CNN | CT(2) | 150 | 93.25 |
| Heidarian46 | COVID-FACT | CT(2) | 23,409 | 90.82 |
| Wang27 | DeCovNet | CT(2) | 630 | 90.1 |
| Li47 | COVNet | CT(2) | 4356 | 90 |
| Amyar48 | Encoder-Decoder with multi-layer perceptron | CT(2) | 1044 | 86 |
| Proposed | RMT-Net | CT(2) | 17,500 | 99.12 |