Multispectral Tissue Characterization In Magnetic Resonance Imaging Using Bayesian Estimation And Markov Random Fields
M. Goldbach, Wido Menhardt, J. Stevens · 2005
A stochastic model bs been developed to provide visualization and classification of 3 dimensional mullispecld nugnetic mnnnce images. A set of manually drawn regiona comprirt the ramplc space on which a statistical model is built for each tiwe. The stack of imagw is then analyzed using parametric Maximum A Posteriori @LAP) classification with the a priori probability modeled as a Markov random field. The result is either a stack of claasificd inuges or a stack of imager whicb epresents the probability of finding a particular tissue at each location in space. Either of the image stacks can be used as direct input to 3V object reconstructionpackages like that found in ISG Allegro.