Skip to main content
. 2022 Mar 28;28(3):732–738. doi: 10.1016/j.radi.2022.03.011

Table 3.

Comparison of the proposed method with DarkCovidNet (3-class problem).

Proposed Method DarkCovidNet
Sensitivity 95.20 88.17
Specificity 100 93.66
Precision 92.50 90.97
F1-score 91.20 89.44
Accuracy 89.70 89.33