Table 8 Multi-class classification results for existing and proposed model on CBIS-DDSM.

From: Hybrid convolutional neural network and bi-LSTM model with EfficientNet-B0 for high-accuracy breast cancer detection and classification

CNN classifier

Accuracy (%)

Sensitivity (%)

Specificity (%)

Precision (%)

AUC

Cohen’s Kappa (κ)

F1 Score (%)

VGG-16

77.80

68.23

86.76

73.05

0.83

0.58

70.54

VGG-19

83.05

70.05

90.52

77.05

0.82

0.63

73.38

DenseNet169

82.53

72.07

91.50

78.07

0.84

0.64

74.92

ResNet-50

83.06

74.54

92.02

79.50

0.86

0.67

76.94

DenseNet201

85.82

75.50

93.45

80.62

0.87

0.68

77.99

Proposed Hybrid Model

99.08

96.05

99.07

98.06

0.98

0.97

97.04

Back to article page