10
IRUS Total
Downloads

NeuroNet: fast and robust reproduction of multiple brain Image segmentation pipelines

File Description SizeFormat 
1806.04224v1.pdf1.24 MBAdobe PDFView/Open
Title: NeuroNet: fast and robust reproduction of multiple brain Image segmentation pipelines
Authors: Rajchl, M
Pawlowski, N
Rueckert, D
Matthews, PM
Glocker, B
Item 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.
Issue Date: 4-Jul-2018
Date of Acceptance: 15-May-2018
URI: http://hdl.handle.net/10044/1/63012
Publisher: MIDL
Copyright Statement: © 2018 The Author(s)
Sponsor/Funder: Imperial College London
Commission of the European Communities
Funder's Grant Number: Imperial College Research Fellowship
H2020 - 757173
Conference Name: International Conference on Medical Imaging with Deep Learning (MIDL)
Keywords: cs.CV
cs.LG
Notes: International conference on Medical Imaging with Deep Learning (MIDL) 2018
Publication Status: Published
Start Date: 2018-07-04
Conference Place: Amsterdam, The Netherlands
Appears in Collections:Faculty of Engineering
Computing
Department of Medicine (up to 2019)