Skip to main content

Table 2 Evaluation of the tumour extraction algorithm without colour deconvolution in BCC histology slides

From: Performance of a simple chromatin-rich segmentation algorithm in quantifying basal cell carcinoma from histology images

Tumours

Sensitivity (%)

Specificity (%)

PPV (%)

NPV (%)

Infiltrative

81.25

68.72

53.57

87.87

Superficial

98.46

74.20

27.34

99.78

Nodular

95.11

80.92

76.90

93.92

All

91.61

74.61

52.60

93.86

  1. PPV: Positive Predictive Value = [True Positive Pixels/(True Positive Pixels + False Positive Pixels)] · 100%; NPV: Negative Predictive Value = [True Negative Pixels/(True Negative Pixels + False Negative Pixels)] · 100%; Sensitivity = [True Positive Pixels/(True Positive Pixels + False Negative Pixels)] · 100%; Specificity = [True Negative Pixels/(True negative Pixels + False Positive Pixels)] · 100%
Back to article page

BMC Research Notes

ISSN: 1756-0500

Contact us