Fig. 2

The radiomic feature selection using the least absolute shrinkage and selection operator (LASSO) binary logistic regression model. a Parameter (Lambda) is tuned in the LASSO model using fivefold cross-validation via maximum area under the ROC curve criteria. AUC on each fold was drawn versus log (Lambda). Vertical line was drawn at the determined optical log (Lambda) with one standard error among fivefold cross-validation, where optimal Lambda resulted in nonzero coefficients. b A coefficient profile plotted against the log (Lambda)