Figure 2.

Heatmap depicting the mean area under the receiver operating characteristic curve of five machine learning classifier (columns) and seven feature selection (rows) methods in the training set. (A) CE mask alone, (B) PT mask alone, (C) CE and PT masks combined. CE contrast-enhancing, PT peritumoral T2 hyperintense, MI mutual information, RFE  recursive feature elimination, Lasso least absolute shrinkage and selection operator, kNN k-nearest neighbor, NB naïve Bayes, RF random forest, Ada adaptive boosting, L-SVM linear support vector machine, R-SVM radial basis function support vector machine, LDA linear discriminant analysis.