Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm

9 Jun 2019Mateusz BudaAshirbani SahaMaciej A Mazurowski

Recent analysis identified distinct genomic subtypes of lower-grade glioma tumors which are associated with shape features. In this study, we propose a fully automatic way to quantify tumor imaging characteristics using deep learning-based segmentation and test whether these characteristics are predictive of tumor genomic subtypes... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Brain Segmentation Brain MRI segmentation U-Net Dice Score 0.82 # 1