Table 4 Performance comparison on MOD dataset.

From: Explainable label guided lightweight network with axial transformer encoder for early detection of oral cancer

Metric

DenseNet

ShuffleNet

ResNeXt

MnasNet

CellViT

LWENet

Recall

83.16

81.37

85.29

88.07

91.87

94.09

Precision

82.34

80.24

87.84

86.18

92.58

95.71

F1-score

82.75

80.81

86.55

87.11

92.22

96.97

Accuracy

85.17

83.45

89.62

90.72

94.12

97.86

Kappa

84.23

82.06

87.23

91.63

95.30

96.30

Back to article page