Fig. 5

Feature selection using the LASSO logistic regression algorithm and the diagnostic efficiency of the radiomics signature. a Selection of the tuning parameter (λ). The LASSO logistic regression model was used with penalty parameter tuning that was conducted by 10-fold cross-validation based on minimum criteria. The y-axis indicates binomial deviances, and the lower x-axis indicates the log (λ). Numbers along the upper x-axis represent the average number of predictors. Red dots indicate average deviance values for each model with a givenλ, and vertical bars through the red dots show the upper and lower values of the deviances. The vertical black lines define the optimal values of λ, where the model provides its best fit to the data. The optimal value of log (λ) = − 2.894 resulting in 8 nonzero coefficients were selected. b LASSO coefficient profiles of the 30 texture features, the dotted vertical line was plotted at the value selected using 10-fold cross-validation in a. c ~ d Diagnostic efficiency of radiomics signature using ROC analysis in the training set (C) and validation set (d)