Figure 2.

US radiomics feature selection using LASSO logistic regression model in the training cohort. (A) The tuning parameter (λ) was selected using 10-fold cross-validation via minimum criteria. Dotted vertical lines were drawn at the optimal values using the minimum criteria and 1 standard error of the minimum criteria (1−SE criteria). A λ value of 0.0273, with a log (λ) value of −3.601, was obtained. (B) The vertical line was drawn at the value selected using 10-fold cross-validation, where optimal λ resulted in four non-zero coefficients. LASSO, least absolute shrinkage and selection operator.