Fig. 1.

Radiomics feature selection using logistic regression with the least absolute shrinkage and selection operator (LASSO) regularization. (a) Ten-fold cross-validation via minimum criteria was used to select the tuning parameter (λ) in LASSO model. The optimal values of the LASSO tuning parameter (λ) are indicated by the dotted vertical lines. An optimal λ value of 0.0714, with log(λ) = − 2.6394 was chosen (b) LASSO coefficient profiles of the 764 raidomics features. A coefficient profile plot was generated versus the selected log (λ) value using ten-fold cross validation, the vertical line was plotted with 10 selected radiomics features