Figure 3 Texture feature selection was conducted using the Least Absolute Shrinkage and Selection Operator (LASSO) binary logistic regression model(A) The LASSO model’s adjustment parameter (λ) was selected by cross-validating 10-fold with the least criterion. The area under the receiver operating characteristic (AUC) curve was plotted against log(λ), with dotted vertical lines drawn at the optimal values determined by the minimum criterion and one standard error of the minimum criterion (1-SE criterion). The best λ value (1-SE criterion) was chosen based on the 10-fold cross-validation results. (B) The LASSO coefficient profiles for 6 texture features were generated for the log(λ) sequence. The vertical lines were drawn on the values selected by the 10-fold cross-validation method, where the best λ led to 3 non-zero coefficients.