Figure 2.

Texture feature parameter selection using LASSO binary logistic regression model. (A) Binomial deviation curve of radiomics model with parameter λ. The vertical axis represents the binomial deviation. The horizontal axis represents the log(λ) value. The upper number represents the optimal value (the perpendicular dotted line), where the smallest binomial deviation is found for the quantitative model with the selected features. (B) Graph of radiomics characteristic parameters changing with λ. LASSO, least absolute shrinkage and selection operator.