Fig. 3From: An MRI-based radiomics nomogram for detecting cervical esophagus invasion in hypopharyngeal squamous cell carcinomaRadiomic feature selection by least absolute shrinkage and selection operator (LASSO) logistic regression. (a) Selection of tuning parameter (λ) in the LASSO model using 10-fold cross-validation. Dotted vertical lines were drawn at the optimal values by using the minimum criteria and 1 standard error of the minimum criteria (the 1-standard error criteria). The optimal log (λ) of -2.53 was chosen. (b) LASSO coefficient profiles of the 31 features. A vertical line was plotted at the optimal log (λ), which resulted in 11 features with non-zero coefficientsBack to article page