Fig. 1.

Texture feature selection using the LASSO binary logistic regression model. a Tuning parameter (λ) selection in the LASSO model used 10-fold cross-validation via minimum criteria. The AUC for the ROC curve was plotted versus log(λ). Dotted vertical lines were drawn at the optimal values using the minimum criteria and the 1 SE of the minimum criteria (the 1-SE criteria). A λ value of 0.076, with a log(λ) of 2.567 was chosen (1-SE criteria) according to 10-fold cross-validation. b LASSOcoefficient profiles. A coefficient profile plot was produced against the log(λ) sequence. A vertical line was drawn at the value selected using 10-fold cross-validation, where the optimal l resulted in 4 factors.