An Empirical Model of Brain Shape
A method is presented to systematically encode brain shape variation, observed from actual image samples, in the form of empirical distributions that can be applied to guide the Bayesian analysis of future image studies. Unlike eigendecompositions based on intrinsic features of a physical model, our modal basis for describing anatomic variation is derived directly from spatial mappings which bring previous brain samples into alignment with a reference configuration. The resultant representation ensures parsimony, yet captures information about the variation across the entire volumetric extent of the brain samples, and facilitates analyses that are governed by the measured statistics of anatomic variability rather than by the physics of some assumed model.
Key wordsBayesian image analysis Shape models Cerebral anatomy
Unable to display preview. Download preview PDF.
- 1.J. C. Gee and R. K. Bajcsy, “Elastic matching: Continuum mechanical and probabilistic analysis,” in Brain Warping, A. Toga, ed., Academic Press, San Diego, In preparation.Google Scholar
- 2.J. C. Gee, D. R. Haynor, M. Reivich, and R. Bajcsy, “Finite element approach to warping of brain images,” in Medical Imaging 1994: Image Processing, M. H. Loew, ed., SPIE, Bellingham, 1994.Google Scholar
- 4.A. Hill, T. F. Cootes, and C. J. Taylor, “A generic system for image interpretation using flexible templates,” in Proc. British Machine Vision Conference, pp. 276–285, 1992.Google Scholar
- 5.J. Martin, A. Pentland, S. Sclaroff, and R. Kikinis, “Characterization of neuropathological shape deformations,” IEEE Trans. Pattern Anal. Machine Intell, To appear.Google Scholar
- 7.J. C. Gee, “Atlas warping for brain morphometry,” in Medical Imaging 1998: Image Processing, K. M. Hanson, ed., SPIE, Bellingham, To appear, 1998.Google Scholar
- 8.D. Heeger and J. Bergen, “Pyramid-based texture analysis/synthesis,” in ACM SIG-GRAPH, 1995.Google Scholar
- 9.S. C. Zhu, Y. Wu, and D. Mumford, “Filters, random fields, and maximum entropy (Frame) — Towards a unified theory for texture modeling,” Int. J. Comput. Vision, To appear.Google Scholar
- 11.J. DeBonet and P. Viola, “A non-parametric multi-scale statistical model for natural images,” in Adv. in Neural Info. Processing, To appear, 1997.Google Scholar
- 12.E. P. Simoncelli, “Statistical models for images: compression, restoration and synthesis,” in 31st Asilomar Conf. Signals, Systems, and Computers, IEEE, New York, 1997.Google Scholar