Fig. 5From: Differentiation of Pseudoprogression from True Progressionin Glioblastoma Patients after Standard Treatment: A Machine Learning Strategy Combinedwith Radiomics Features from T1-weighted Contrast-enhanced ImagingFeature importance plot showing the mean decrease in Gini impurity. Features that most reduced the Gini impurity were those that resulted in the least misclassificationsBack to article page