Bayesian approach to segmentation of statistical parametric maps

• Published in: IEEE transactions on biomedical engineering Vol. 48; no. 10; pp. 1186 - 1194
• Main Authors: Rajapakse, J.C., Piyaratna, J.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.10.2001; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Analytical models; Bayes Theorem; Bayesian methods; Biological and medical sciences; Brain; Brain Mapping; Brain modeling; Discrete event simulation; Humans; Image Processing, Computer-Assisted; Image segmentation; Investigative techniques, diagnostic techniques (general aspects); Iterative algorithms; Magnetic Resonance Imaging; Markov Chains; Markov random fields; Medical sciences; Nervous system; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Radionuclide investigations; Scanning probe microscopy; Simulated annealing; Studies; Radionuclide study; Human; Cartography; Evaluation; Segmentation; Image processing; Central nervous system; Parametric system; Functional analysis; Digital image; Nuclear magnetic resonance imaging; Statistical model; Medical imagery; Bayes decision; Brain (vertebrata); Emission tomography
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/10.951522

A contextual segmentation technique to detect brain activation from functional brain images is presented in the Bayesian framework. Unlike earlier similar approaches [Holmes and Ford (1993) and Descombes et al. (1998)], a Markov random field (MRF) is used to represent configurations of activated brain voxels, and likelihoods given by statistical parametric maps (SPM's) are directly used to find the maximum a posteriori (MAP) estimation of segmentation. The iterative segmentation algorithm, which is based on a simulated annealing scheme, is fully data-driven and capable of analyzing experiments involving multiple-input stimuli. Simulation results and comparisons with the simple thresholding and the statistical parametric mapping (SPM) approaches are presented with synthetic images, and functional MR images acquired in memory retrieval and event-related working memory tasks. The experiments show that an MRF Is a valid representation of the activation patterns obtained in functional brain images, and the present technique renders a superior segmentation scheme to the context-free approach and the SPM approach.