Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration

Arno Klein; Jesper Andersson; Babak Ardekani; John Ashburner; Brian Avants; Ming-Chang Chiang; Gary Christensen; D. Louis Collins; Pierre Hellier; Joo Hyun Song; Mark Jenkinson; Claude Lepage; Daniel Rueckert; Paul Thompson; Tom Vercauteren; Roger Woods; John Mann; Ramin Parsey

doi:10.1016/j.neuroimage.2008.12.037

Back

Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration

Journal article

Open access

Peer reviewed

Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration

Arno Klein, Jesper Andersson, Babak Ardekani, John Ashburner, Brian Avants, Ming-Chang Chiang, Gary Christensen, D. Louis Collins, Pierre Hellier, Joo Hyun Song, …

NeuroImage (Orlando, Fla.), Vol.46(3), pp.786-802

07/01/2009

DOI: 10.1016/j.neuroimage.2008.12.037

PMCID: PMC2747506

PMID: 19195496

Files and links (1)

url

http://doi.org/10.1016/j.neuroimage.2008.12.037View

Open Access

Abstract

All fields of neuroscience that employ brain imaging need to communicate their results with reference to anatomical regions. In particular, comparative morphometry and group analysis of functional and physiological data require coregistration of brains to establish correspondences across brain structures. It is well established that linear registration of one brain to another is inadequate for aligning brain structures, so numerous algorithms have emerged to nonlinearly register brains to one another. This study is the largest evaluation of nonlinear deformation algorithms applied to brain image registration ever conducted. Fourteen algorithms from laboratories around the world are evaluated using 8 different error measures. More than 45,000 registrations between 80 manually labeled brains were performed by algorithms including: AIR, ANIMAL, ART, Diffeomorphic Demons, FNIRT, IRTK, JRD-fluid, ROMEO, SICLE, SyN, and four different SPM5 algorithms ("SPM2-type" and regular Normalization, Unified Segmentation, and the DARTEL Toolbox). All of these registrations were preceded by linear registration between the same image pairs using FLIRT. One of the most significant findings of this study is that the relative performances of the registration methods under comparison appear to be little affected by the choice of subject population, labeling protocol, and type of overlap measure. This is important because it suggests that the findings are generalizable to new subject populations that are labeled or evaluated using different labeling protocols. Furthermore, we ranked the 14 methods according to three completely independent analyses (permutation tests, one-way ANOVA tests, and indifference-zone ranking) and derived three almost identical top rankings of the methods. ART, SyN, IRTK, and SPM's DARTEL Toolbox gave the best results according to overlap and distance measures, with ART and SyN delivering the most consistently high accuracy across subjects and label sets. Updates will be published on the www.mindboggle.info/papers/ website.

Algorithms

Bioengineering

Brain

Computer Science

Life Sciences

Magnetic Resonance Imaging

Medical Imaging

Nonlinear Dynamics

Nuclear Medicine

Reproducibility of Results

Image Enhancement

Artificial Intelligence

Humans

Image Interpretation, Computer-Assisted

Male

Subtraction Technique

Sensitivity and Specificity

Imaging

Adult

Female

Pattern Recognition, Automated

Details

Title: Subtitle: Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration
Creators: Arno Klein - New York State Psychiatric Institute
Jesper Andersson - Department of Clinical Neurology [Oxford]
Babak Ardekani - Nathan S. Kline Institute for Psychiatric Research
John Ashburner - Functional Imaging Laboratory
Brian Avants - Penn Image Computing & Science Lab [Philadelphia]
Ming-Chang Chiang - Laboratory of Neuro Imaging [Los Angeles]
Gary Christensen - Department of Electrical and Computer Engineering [Iowa]
D. Louis Collins - McConnell Brain Imaging Center
Pierre Hellier - Vision, Action et Gestion d'informations en Santé
Joo Hyun Song - Department of Electrical and Computer Engineering [Iowa]
Mark Jenkinson - Department of Clinical Neurology [Oxford]
Claude Lepage - McConnell Brain Imaging Center
Daniel Rueckert - Visual Information Processing
Paul Thompson - Laboratory of Neuro Imaging [Los Angeles]
Tom Vercauteren - Mauna Kea Technologies
Roger Woods - Department of Neurology [UCLA]
John Mann - New York State Psychiatric Institute
Ramin Parsey - New York State Psychiatric Institute
Resource Type: Journal article
Publication Details: NeuroImage (Orlando, Fla.), Vol.46(3), pp.786-802
DOI: 10.1016/j.neuroimage.2008.12.037
PMID: 19195496
PMCID: PMC2747506
NLM abbreviation: Neuroimage
ISSN: 1053-8119
eISSN: 1095-9572
Publisher: Elsevier
Language: English
Date published: 07/01/2009
Academic Unit: Electrical and Computer Engineering; Radiation Oncology; Radiation Research Laboratory
Record Identifier: 9984047640702771

Metrics

14 Record Views

1767 Times Cited - Web of Science