NeuroNet: fast and robust reproduction of multiple brain Image segmentation pipelines
File(s)
Author(s)
Rajchl, Martin
Pawlowski, Nick
Rueckert, Daniel
Matthews, Paul M
Glocker, Ben
Type
Conference Paper
Abstract
NeuroNet is a deep convolutional neural network mimicking multiple popular
and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM.
The network is trained on 5,000 T1-weighted brain MRI scans from the UK Biobank
Imaging Study that have been automatically segmented into brain tissue and
cortical and sub-cortical structures using the standard neuroimaging pipelines.
Training a single model from these complementary and partially overlapping
label maps yields a new powerful "all-in-one", multi-output segmentation tool.
The processing time for a single subject is reduced by an order of magnitude
compared to running each individual software package. We demonstrate very good
reproducibility of the original outputs while increasing robustness to
variations in the input data. We believe NeuroNet could be an important tool in
large-scale population imaging studies and serve as a new standard in
neuroscience by reducing the risk of introducing bias when choosing a specific
software package.
and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM.
The network is trained on 5,000 T1-weighted brain MRI scans from the UK Biobank
Imaging Study that have been automatically segmented into brain tissue and
cortical and sub-cortical structures using the standard neuroimaging pipelines.
Training a single model from these complementary and partially overlapping
label maps yields a new powerful "all-in-one", multi-output segmentation tool.
The processing time for a single subject is reduced by an order of magnitude
compared to running each individual software package. We demonstrate very good
reproducibility of the original outputs while increasing robustness to
variations in the input data. We believe NeuroNet could be an important tool in
large-scale population imaging studies and serve as a new standard in
neuroscience by reducing the risk of introducing bias when choosing a specific
software package.
Date Issued
2018-07-04
Date Acceptance
2018-05-15
Citation
2018
Publisher
MIDL
Copyright Statement
© 2018 The Author(s)
Sponsor
Imperial College London
Commission of the European Communities
Identifier
http://arxiv.org/abs/1806.04224v1
Grant Number
Imperial College Research Fellowship
H2020 - 757173
Source
International Conference on Medical Imaging with Deep Learning (MIDL)
Subjects
cs.CV
cs.CV
cs.LG
Notes
International conference on Medical Imaging with Deep Learning (MIDL) 2018
Publication Status
Published
Start Date
2018-07-04
Coverage Spatial
Amsterdam, The Netherlands