TABLE V. Results of COVID-19 Prediction Using Retrained COVIDNet-CXR A, Retrained COVID-CAPS, ResNet-50 With and Without Segmentation, FuCiTNet and COVID-SDNet. All Four Levels of Severity in the Positive Class are Taken Into Account.
Class | N | P | Accuracy | |||||
---|---|---|---|---|---|---|---|---|
Metric | Specificity | Precision | F1 | Sensitivity | Precision | F1 | ||
COVIDNet-CXR | 88.82![]() |
3.36![]() |
73.31![]() |
46.82![]() |
81.65![]() |
56.94![]() |
67.82![]() |
|
COVID-CAPS | 65.74![]() |
65.62![]() |
65.15![]() |
64.93![]() |
66.07![]() |
64.87![]() |
65.34![]() |
|
Without seg. | 79.87![]() |
71.91![]() |
75.40![]() |
68.63![]() |
78.75![]() |
72.689![]() |
74.25![]() |
|
With seg. | 78.41![]() |
73.36![]() |
75.46![]() |
70.80![]() |
77.17![]() |
73.40![]() |
74.60![]() |
|
FuCiTNet |
80.79![]() |
72.00![]() |
75.84![]() |
67.90![]() |
78.48![]() |
72.35![]() |
74.35![]() |
|
COVID-SDNet | ||||||||
79.76![]() |
74.74![]() |
76.94![]() |
72.59![]() |
78.67![]() |
75.71![]() |
76.18![]() |