Skip to main content

Table 1 Performance of different deep learning models with cubic SVM based on tenfold cross-validation

From: Rapid identification of COVID-19 severity in CT scans through classification of deep features

Backbone

Accuracy (%)

AUC

Sensitivity (%)

Specificity (%)

Inception-V3 [18]

91.91

0.97

84.96

95.84

ResNet-50 [19]

92.45

0.98

85.85

96.07

ResNet-101 [19]

94.24

0.98

89.02

96.06

DenseNet-201 [20]

95.20

0.99

91.87

96.87

  1. The highest performance value is in italics