Table 4 Evaluation metrics for the SIPaKMeD data (5-class).

From: A hybrid learning network with progressive resizing and PCA for diagnosis of cervical cancer on WSI slides

Iteration

Algorithm

Precision (%)

Sensitivity (%)

Accuracy (%)

MCC

F-Score

Iteration-1

ResNet-152

93.84

94.6

93.37

0.92

0.94

VGG-16

95.86

95.73

94.9

0.94

0.96

Proposed method

97.99

98.06

97.45

0.97

0.98

Iteration-2

ResNet-152

94.91

94.75

93.88

0.92

0.95

VGG-16

96.3

96.51

95.41

0.94

0.96

Proposed method

98.36

98.5

97.96

0.97

0.98

Iteration-3

ResNet-152

95.26

95.52

94.39

0.93

0.95

VGG-16

97.11

97.28

96.43

0.96

0.97

Proposed method

98.72

98.97

98.47

0.98

0.99

  1. Significant values are in bold.