Skip to main content

Table 2 Names and Coefficients of High Weight Features

From: Magnetic resonance imaging-based radiomics was used to evaluate the level of prognosis-related immune cell infiltration in breast cancer tumor microenvironment

Name

Coefficients

(1) Names and Coefficients of High Weight Features Extracted from Peritumor

 square_firstorder_Minimum

− 0.481

 wavelet.LLH_firstorder_Skewness

− 0.350

 lbp.2D_glszm_ZoneVariance

−0.186

 wavelet.LLL_firstorder_10Percentile

−0.098

 squareroot_firstorder_10Percentile

−0.064

 wavelet.HLH_gldm_DependenceVariance

0.071

 wavelet.LLH_firstorder_Kurtosis

0.093

 wavelet.LLH_glrlm_LongRunEmphasis

0.597

(2) Names and Coefficients of High Weight Features Extracted from Intratumor

 wavelet.HLL_glrlm_RunVarianc

0.389

(3) Names and Coefficients of High Weight Features Extracted from Combined

 Peri_square_firstorder_Minimum

−1.071

 Peri_lbp.2D_glszm_ZoneVariance

−0.464

 Peri_wavelet.LLH_firstorder_Skewness

−0.409

 Peri_squareroot_firstorder_10Percentile

−0.168

 Peri_wavelet.LLL_firstorder_10Percentile

−0.155

 Peri_wavelet.HLH_gldm_DependenceVariance

0.132

 Intra_wavelet.HLL_glrlm_RunVarianc

0.231

 Peri_wavelet.LLH_firstorder_Kurtosis

0.257

 Peri_wavelet.LLH_glrlm_LongRunEmphasis

0.784