Table 11 Pathological variations analysis using the CNN-DenseNet model.

From: Integrative hybrid deep learning for enhanced breast cancer diagnosis: leveraging the Wisconsin Breast Cancer Database and the CBIS-DDSM dataset

Model

Age groups

Pathological parameters

Number of instances

Accuracy %

Error rate

CNN-DenseNet

35–45

10

1000

83

0.000889

2000

84

0.000721

2500

85

0.000382

20

1000

86

0.000963

2000

88

0.000565

2500

87

0.000421

30

1000

92

0.000796

2000

95

0.000245

2500

97

0.000372

45–55

10

1000

80

0.000352

2000

81

0.000463

2500

84

0.000278

20

1000

85

0.000332

2000

86

0.000339

2500

86

0.000587

30

1000

92

0.000785

2000

94

0.000214

2500

96

0.000238

55–65

10

1000

83

0.000845

2000

84

0.000718

2500

83

0.000509

20

1000

86

0.000703

2000

87

0.000624

2500

88

0.000536

30

1000

85

0.000542

2000

92

0.000325

2500

95

0.000239