Predicting the Grade of Prostate Cancer Based on a Biparametric MRI Radiomics Signature

Figure 3

The process of feature selection using the LASSO algorithm. (a) The optimal tuning parameter (lambda) in the LASSO model was selected using 10-fold cross-validation and the 1 standard error rule. (b) LASSO coefficient profiles of the 26 features. The vertical line was drawn according to the 10-fold cross-validation in (a). LASSO, least absolute shrinkage selection operator.

(a)

(b)