Table 7 The performance measures of the 3SNet mode using Grey and HOG features.

From: Morphological diagnosis of hematologic malignancy using feature fusion-based deep convolutional neural network

Folds

Performance measures

Accuracy (%)

Precision (%)

Recall (%)

F1-Score (%)

Fold1

87.15

45.04

42.74

43.85

Fold2

97.23

89.87

93.18

91.50

Fold3

98.42

97.28

92.59

94.87

Fold4

98.78

99.51

96.94

98.21

Fold5

99.11

99.76

97.64

98.69

Average

96.13

86.29

84.61

85.42

Back to article page