Skip to main content

Table 1 Results of group-wise radiomic feature-based cancer classifications for molecular breast cancer subtypes (training dataset)

From: Radiomic signatures with contrast-enhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes: initial results

 

Luminal A

Luminal B

HER2-enriched

TN

All others

Luminal A

–

84.2%

(MI; 6)

76.7%

(POE; 6)

69.4%

(POE; 7)

60.4%

(MI; 9)

Luminal B

84.2%

(MI; 6)

–

73.7%

(Fisher; 2)

83.9%

(Fisher; 3)

89%

(POE; 9)

HER2-enriched

76.7%

(POE; 6)

73.7%

(Fisher; 2)

–

73.5%

(POE; 3)

81.3%

(MI; 9)

TN

69.4%

(POE; 7)

83.9%

(Fisher; 3)

73.5%

(POE; 3)

–

73.6%

(MI; 9)

All others

60.4%

(MI; 9)

89%

(POE; 9)

81.3%

(MI; 9)

73.6%

(MI; 9)

–

  1. HER2 human epidermal growth factor receptor 2, MI mutual information, POE probability of error and average correlation, TN triple negative. The feature selection algorithm and number of features used for classification are given in parentheses
Back to article page

Breast Cancer Research

ISSN: 1465-542X

Contact us