Table 2 Number of features extracted by different feature extraction methods and the average AUC.

From: Prediction of blood supply in vestibular schwannomas using radiomics machine learning classifiers

Feature_Selection_Methods

AUC of classification methods

Number of selected Voxel

RF

MLR

SVM

DT

Average

t_test

0.65

0.74

0.70

0.63

0.68

10

LASSO

0.70

0.88

0.84

0.62

0.76

12

ANOVA

0.60

0.61

0.50

0.61

0.58

14

t_test + LASSO

0.73

0.80

0.77

0.65

0.74

12

Average

0.67

0.76

0.70

0.63

0.69

 
Back to article page