Table 3 Diagnostic performance for classification.

From: Initial experience of a deep learning application for the differentiation of Kikuchi-Fujimoto’s disease from tuberculous lymphadenitis on neck CECT

ResNet-50

Original image with aspect ratios = {1.0, 1.5, 2.0}

Aspect ratio = {3.0}

Aspect ratio = {4.0}

Accuracy (%)

69.15

94.67

86.05

Sensitivity (%)

71.93

99.52

88.98

Specificity (%)

57.29

73.90

73.56

PPV (%)

87.80

94.22

93.50

NPV (%)

32.31

97.32

60.96

AUC

0.71

0.91

0.87

F1-score

0.74

0.97

0.91

  1. PPV positive predictive value, NPV negative predictive value, AUC area under the receiver operating characteristic curve.
Back to article page