Skip to main content
. 2020 Sep 15;10:1151. doi: 10.3389/fonc.2020.01151

Table 1.

The features selected with different methods.

Selection method Selected features
Distance correlation GLRLM_LGRE; GLRLM_HGRE; GLRLM_SRLGE; GLRLM_SRHGE; GLRLM_LRLGE; GLZLM_LGZE; GLZLM_HGZE; GLZLM_SZLGE
RF GLRLM_LGRE; GLRLM_HGRE; GLRLM_SRLGE; GLRLM_SRHGE; GLRLM_LRHGE; GLZLM_HGZE
LASSO minValue; meanValue; stdValue; SHAPE_Volume; GLCM_Contrast; GLRLM_HGRE; GLRLM_SRHGE; GLRLM_LRHGE; GLRLM_GLNU; GLRLM_RLNU; GLZLM_LZE; GLZLM_HGZE; GLZLM_SZHGE; GLZLM_LZHGE; GLZLM_GLNU; GLZLM_ZLNU
XgBoost GLRLM_LGRE
GBDT GLRLM_LGRE; GLRLM_HGRE; GLRLM_SRLGE; GLRLM_SRHGE; GLRLM_LRHGE; GLZLM_LGZE; GLZLM_HGZE; GLZLM_SZLGE; GLZLM_SZHGE

RF, random forest; LASSO, least absolute shrinkage and selection operator; Xgboost, eXtreme gradient boosting; GBDT, Gradient Boosting Decision Tree.