A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Simple points, topological numbers and geodesic neighborhoods in cubic grids
Pattern Recognition Letters
Journal of Mathematical Imaging and Vision - Special issue on mathematical imaging
Journal of Computational Physics
An Extensible MRI Simulator for Post-Processing Evaluation
VBC '96 Proceedings of the 4th International Conference on Visualization in Biomedical Computing
CTIC'12 Proceedings of the 4th international conference on Computational Topology in Image Context
Hi-index | 0.00 |
Registration of brain atlases to MR images is important in both anatomic and functional studies of human brains. Existing intensity-based methods are confronted with the translation of image-similarity functions to desired anatomic correspondences; while feature-based methods are challenged with the automated extraction of required features. In this paper, we propose a non-rigid registration method, in which, a block matching method is first used to calculate boundary displacement of all structures in a brain atlas, and a topology preserving front propagation method is then used to deform the atlas by warping the structures according to their boundary displacements. The novelty of our method is that the registration procedure is automated and anatomically driven while there is no need to extract particular structures. Experiments on the registration of the Talairach---Tournoux brain atlas to phantom brain MR images and real data show that our method is robust to noise and intensity inhomogeneity, more accurate than the commonly used Talairach stereotaxic spatial normalization, and thus promising to open new applications for brain atlases.