Fig. 1From: Radiomic analysis of Gd-EOB-DTPA-enhanced MRI predicts Ki-67 expression in hepatocellular carcinomaFeature selection using the least absolute shrinkage and selection operator (LASSO) logistic regression in AP radiomics model.Ā aĀ Tuning parameter (Ī») selection in the LASSO model used 5-fold cross-validation. Dotted vertical lines were drawn at the optimal values by using the minimum criteria and the 1 standard error of the minimum criteria (the 1-SE criteria). A Ī» value of 0.045, with log (Ī»), āā2.725 was chosen (1-SE criteria). bĀ Vertical line was drawn at the value selected, where optimal Ī» resulted in 12 nonzero coefficientsBack to article page