期刊
NEUROIMAGE
卷 143, 期 -, 页码 235-249出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.neuroimage.2016.09.011
关键词
MRI; Segmentation; Atlases; Parametric models; Bayesian modeling
资金
- NIH NCRR [P41-RR14075, 1S10RR023043]
- NIBIB [R01EB013565]
- Lundbeck foundation [R141-2013-13117]
- Technical University of Denmark
- Gipuzkoako Foru Aldundia (Fellows Gipuzkoa Program)
- European Union's Horizon Research and innovation program under the Marie Sklodowska-Curie grant [654911]
- Spanish Ministry of Economy and Competetiveness (MINECO) [TEC2014-51882-P]
- Engineering and Physical Sciences Research Council [EP/M020533/1] Funding Source: researchfish
- Lundbeck Foundation [R141-2013-13117] Funding Source: researchfish
- Marie Curie Actions (MSCA) [654911] Funding Source: Marie Curie Actions (MSCA)
- EPSRC [EP/M020533/1] Funding Source: UKRI
Quantitative analysis of magnetic resonance imaging (MRI) scans of the brain requires accurate automated segmentation of anatomical structures. A desirable feature for such segmentation methods is to be robust against changes in acquisition platform and imaging protocol. In this paper we validate the performance of a segmentation algorithm designed to meet these requirements, building upon generative parametric models previously used in tissue classification. The method is tested on four different datasets acquired with different scanners, field strengths and pulse sequences, demonstrating comparable accuracy to state-of-the-art methods on T1-weighted scans while being one to two orders of magnitude faster. The proposed algorithm is also shown to be robust against small training datasets, and readily handles images with different MRI contrast as well as multi-contrast data. (C) 2016 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据