3D MRI brain tumor segmentation using autoencoder regularization

27 Oct 2018Andriy Myronenko

Automated segmentation of brain tumors from 3D magnetic resonance images (MRIs) is necessary for the diagnosis, monitoring, and treatment planning of the disease. Manual delineation practices require anatomical knowledge, are expensive, time consuming and can be inaccurate due to human error... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Brain Tumor Segmentation BRATS 2018 NVDLMED Dice Score 0.87049 # 1