Skip to main content

Table 1 Performance evaluation of Ranklet , GLCM , LBP and PCBP with the LOO-CV method

From: Robust phase-based texture descriptor for classification of breast ultrasound images

Methods

AUC

ACC (%)

SENS (%)

SPEC (%)

PPV (%)

NPV (%)

MCC

Ranklet

0.882

81.16

73.91

88.41

86.44

77.22

0.630

GLCM

0.848

77.54

68.12

86.96

83.93

73.13

0.561

LBP

0.850

83.33

81.16

85.51

84.85

81.94

0.667

PCBP

0.894

86.96

86.96

86.96

86.96

86.96

0.739

  1. Note. The best performance for each criterion is highlighted with bold, and the second best is italic.