A Physically-Based Statistical Deformable Model for Brain Image Analysis
A probabilistic deformable model for the representation of brain structures is described. The statistically learned deformable model represents the relative location of head (skull and scalp) and brain surfaces in Magnetic Resonance Images (MRIs) and accommodates their significant variability across different individuals. The head and brain surfaces of each volume are parameterized by the amplitudes of the vibration modes of a deformable spherical mesh. For a given MRI in the training set, a vector containing the largest vibration modes describing the head and the brain is created. This random vector is statistically constrained by retaining the most significant variation modes of its Karhunen-Loeve expansion on the training population. By these means, the conjunction of surfaces are deformed according to the anatomical variability observed in the training set. Two applications of the probabilistic deformable model are presented: the deformable model-based registration of 3D multimodal (MR/SPECT) brain images without removing non-brain structures and the segmentation of the brain in MRI using the probabilistic constraints embedded in the deformable model. The multi-object deformable model may be considered as a first step towards the development of a general purpose probabilistic anatomical brain atlas.
KeywordsRegistration Error Deformable Model Brain Surface Training Population Rigid Registration
- 1.K. J. Bathe. Finite element procedures. Prentice Hall, Englewood Cliffs, New Jersey, 1996.Google Scholar
- 12.C. Nikou, F. Heitz, and J. P. Armspach. Robust registration of dissimilar single and multimodal images. In Lecture Notes in Computer Science. Proceedings of the 5 th European Conference on Computer Vision (ECCV’98), volume 2, pages 51–65, Freiburg, Germany, 2–6 June 1998.Google Scholar
- 14.G. Székely, A. Keleman, A. Brechbuhler, and G. Gerig. Segmentation of 2D and 3D objects from MRI data using constrained elastic deformations of flexible Fourier contour and surface models. Medical Image Analysis, 1(1):19–34, 1996.Google Scholar