The Value of Enhanced MR Radiomics in Estimating the IDH1 Genotype in High-Grade Gliomas

Figure 2

Radiomic feature selection using the Lasso logistic regression model. (a) Selection in the Lasso model used 10-fold cross-validation via minimum criteria to screen the feature set with the best efficiency. (b) A convergence graph of feature coefficients in the Lasso model for feature selection using a 10-fold cross-validation method. (c) Thirteen nonzero coefficients of the radiomic features.

(a)

(b)

(c)