Training of a Skull-Stripping Neural Network with efficient data augmentation
This work addresses skull-stripping for brain imaging analysis, but it appears incremental as it builds on existing neural network methods with a focus on efficient training.
The authors tackled the problem of skull-stripping in brain MR images by proposing a convolutional neural network approach, achieving a Dice score of 96.5% and a processing time of 4.5 seconds per volume on the NFBS database.
Skull-stripping methods aim to remove the non-brain tissue from acquisition of brain scans in magnetic resonance (MR) imaging. Although several methods sharing this common purpose have been presented in literature, they all suffer from the great variability of the MR images. In this work we propose a novel approach based on Convolutional Neural Networks to automatically perform the brain extraction obtaining cutting-edge performance in the NFBS public database. Additionally, we focus on the efficient training of the neural network designing an effective data augmentation pipeline. Obtained results are evaluated through Dice metric, obtaining a value of 96.5%, and processing time, with 4.5s per volume.