Training of a Skull-Stripping Neural Network with efficient data augmentation

TL;DR

This paper introduces a convolutional neural network for skull-stripping in brain MRI scans, emphasizing an efficient data augmentation pipeline to enhance training and achieve high accuracy and fast processing times.

Contribution

It presents a novel CNN-based skull-stripping method with an optimized data augmentation strategy for improved training efficiency and performance.

Findings

Dice score of 96.5% on NFBS database

Processing time of 4.5 seconds per volume

Effective data augmentation improves neural network training

Abstract

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.