2.

Radiomics features selected in LASSO regression analysis

Intercept and radiomics features	Coefficients
Thirteen radiomics features with non-zero coefficients in the least absolute shrinkage and selection operator method (LASSO) logistic regression model were selected. The radiomics signature was constructed based on the regression analysis with a radiomics score calculated for each patient. The formula to calculate the score of radiomics signature is Score = Intercept + Coefficient × Radiomics features. The details of radiomics features were described in Supplementary Table S1 .
Intercept	−0.893
Contrast_135_1_0	0.099
Contrast_90_2_0	0.011
Correlation_45_3_0	−0.178
Homogeneity_135_2_0	0.241
Homogeneity_90_3_0	0.076
Gln_45_0	−0.145
His_10_Mean_0	0.075
Entropy_0_3_1.0	−0.007
His_25_SD_1.0	−0.060
Correlation_0_1_1.5	−0.186
Entropy_0_3_1.5	−0.015
His_10_SD_2.0	0.091
Gabor_2_4	−0.095