Fig. 4From: Deep learning-based algorithm for postoperative glioblastoma MRI segmentation: a promising new tool for tumor burden assessmentIllustrates the trend DICE scores (A) and Hausdorff 95 distance scores (B) on the “complete” configuration for preoperative segmentation. y axis: DS and H95 values; x axis: each point represents a patient from the Molinette hospital dataset. Segments considered are TC, ET and WTBack to article page