Skip to main content

Table 3 Evaluation metrics of binary classification for different deep neural network models: frame-based scheme

From: Wireless capsule endoscopy multiclass classification using three-dimensional deep convolutional neural network model

 

3D

2D

AlexNet

Inception-V3

ResNet-18

SqueezeNet

DenseNet-201

Sensitivity (%)

98.92

98.05

79.03

77.74

77.58

81.12

85.48

Specificity (%)

99.50

86.94

98.62

98.22

98.74

98.70

99.22

PPV (%)

99.51

88.61

98.69

8546

89.23

89.34

93.63

NPV (%)

98.92

97.73

97.19

97.05

97.04

95.50

98.07

F1 score

99.21

92.95

97.93

90.89

92.97

92.32

95.80

Accuracy (%)

99.20

92.60

94.81

95.65

96.12

96.26

97.10

Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us