We describe a fully-automatic 3D-segmentation technique for brain MR images. Using Markov random fields the segmentation algorithm captures three important MR features, i.e. non-parametric distributions of tissue intensities, neighborhood correlations and signal inhomogeneities. Detailed simulations and real MR images demonstrate the performance of the segmentation algorithm. The impact of noise, inhomogeneity, smoothing and structure thickness is 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. Keywords: Magnetic Resonance Imaging, Segmentation, Markov Random Fields
@article{arxiv.0903.3114,
title = {Markov Random Field Segmentation of Brain MR Images},
author = {Karsten Held and Elena Rota Kops and Bernd J. Krause and William M. Wells and Ron Kikinis and Hans-Wilhelm Mueller-Gaertner},
journal= {arXiv preprint arXiv:0903.3114},
year = {2009}
}
Comments
34 pages, 10 figures; the paper (published in 1997) has introduced the concept of Markov random field to the segmentation of medical MR images. For the published version see http://dx.doi.org/10.1109/42.650883