Markov random field segmentation of brain MR images

Describes a fully-automatic three-dimensional (3-D)-segmentation technique for brain magnetic resonance (MR) images. By means of Markov random fields (MRF's) the segmentation algorithm captures three features that are of special importance for MR images, i.e., nonparametric distributions of tis...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on medical imaging Vol. 16; no. 6; pp. 878 - 886
Main Authors:	Held, K., Kops, E.R., Krause, B.J., Wells, W.M., Kikinis, R., Muller-Gartner, H.-W.
Format:	Journal Article
Language:	English
Published:	New York, NY IEEE 01-12-1997 Institute of Electrical and Electronics Engineers
Subjects:	Algorithms Biological and medical sciences Biomedical imaging Brain Brain - anatomy & histology Brain modeling Hospitals Humans Image Processing, Computer-Assisted - methods Image segmentation Investigative techniques, diagnostic techniques (general aspects) Iterative methods Magnetic noise Magnetic resonance Magnetic Resonance Imaging Markov processes Markov random fields Medical imaging Medical sciences Nervous system Neurophysiology Nuclear medicine Physiological models Radiodiagnosis. Nmr imagery. Nmr spectrometry Simulated annealing Smoothing methods Human Segmentation Central nervous system Markov model Anatomy Nuclear magnetic resonance imaging Random field Image analysis Simulation Medical imagery Tridimensional image Technique Quantitative analysis Brain (vertebrata)
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Describes a fully-automatic three-dimensional (3-D)-segmentation technique for brain magnetic resonance (MR) images. By means of Markov random fields (MRF's) the segmentation algorithm captures three features that are of special importance for MR images, i.e., nonparametric distributions of tissue intensities, neighborhood correlations, and signal inhomogeneities. Detailed simulations and real MR images demonstrate the performance of the segmentation algorithm. In particular, the impact of noise, inhomogeneity, smoothing, and structure thickness are analyzed quantitatively. Even single-echo MR images are well classified into gray matter, white matter, cerebrospinal fluid, scalp-bone, and background. A simulated annealing and an iterated conditional modes implementation are presented.
Bibliography:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 ObjectType-Article-1 ObjectType-Feature-2
ISSN:	0278-0062 1558-254X
DOI:	10.1109/42.650883