Direct segmentation of the major white matter tracts in diffusion tensor images

Diffusion-weighted images of the human brain are acquired more and more routinely in clinical research settings, yet segmenting and labeling white matter tracts in these images is still challenging. We present in this paper a fully automated method to extract many anatomical tracts at once on diffus...

Full description

Saved in:

Bibliographic Details
Published in:	NeuroImage (Orlando, Fla.) Fla.), 2011-09, Vol.58 (2), p.458-468
Main Authors:	Bazin, Pierre-Louis, Ye, Chuyang, Bogovic, John A., Shiee, Navid, Reich, Daniel S., Prince, Jerry L., Pham, Dzung L.
Format:	Article
Language:	eng
Subjects:	Algorithms Anisotropy Atlases as Topic Brain Brain - anatomy & histology Brain Diseases - pathology Computer Simulation Dietary fiber Diffusion Diffusion Tensor Imaging - methods Disease DTI segmentation Grants Humans Image Processing, Computer-Assisted - methods Markov Chains Markov random field modeling Methods Models, Neurological Models, Statistical Multiple sclerosis Nerve Fibers - physiology Neural Pathways - anatomy & histology Noise Probability Probability distribution Programming languages Registration Reproducibility of Results Studies White matter tracts
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Diffusion-weighted images of the human brain are acquired more and more routinely in clinical research settings, yet segmenting and labeling white matter tracts in these images is still challenging. We present in this paper a fully automated method to extract many anatomical tracts at once on diffusion tensor images, based on a Markov random field model and anatomical priors. The approach provides a direct voxel labeling, models explicitly fiber crossings and can handle white matter lesions. Experiments on simulations and repeatability studies show robustness to noise and reproducibility of the algorithm, which has been made publicly available. [Display omitted] ► Diffusion tensor image segmentation into white matter tracts is still challenging. ► Our Markov field model with atlas priors enables direct, automated segmentation. ► Crossings and lesions are successfully handled on clinical quality images. ► The segmentation software and an extensive tract atlas are freely available.
ISSN:	1053-8119 1095-9572