MARKOV RANDOM-FIELD SEGMENTATION OF BRAIN MR-IMAGES

We describe a fully automatic three-dimensional (3-D)-segmentation tec hnique for brain magnetic resonance (MR) images, By means of Markov ra ndom fields (MRF's) the segmentation algorithm captures three features that are of special importance for MR images, i.e., nonparametric dis tributions of tissue intensities, neighborhood correlations, and signa l inhomogeneities, Detailed simulations and real MR images demonstrate the performance of the segmentation algorithm, In particular, the imp act of noise, inhomogeneity, smoothing, and structure thickness are an alyzed quantitatively, Even single-echo MR images are well classified into gray matter, white matter, cerebrospinal fluid, scalp-bone, and b ackground, A simulated annealing and an iterated conditional modes imp lementation are presented.