Skip to main content

Table 8 Performance of different machine learning methods obtained by Shan et al. [8]

From: Performance of machine learning software to classify breast lesions using BI-RADS radiomic features on ultrasound images

Method

Features

Sensitivity (%)

Specificity (%)

Area under the curve

Decision tree

{4, 3, 10, 2, 7}

74.0

82.0

0.803

Multilayer perceptron

{4, 3, 2, 6, 5, 1}

78.0

78.2

0.823

Random forest

{6, 10, 2, 9, 3}

75.3

82.0

0.828

Support vector machine

{4, 2, 6, 3, 10}

77.3

78.2

0.842