11 August 1995 Hierarchical brain mapping via a generalized Dirichlet solution for mapping brain manifolds
Author Affiliations +
In this paper we present a coarse-to-fine approach for the transformation of digital anatomical textbooks from the ideal to the individual that unifies the work on landmark deformations and volume based transformation. The Hierarchical approach is linked to the Biological problem itself, coming out of the various kinds of information which is provided by the anatomists. This information is in the form of points, lines, surfaces and sub-volumes corresponding to 0, 1, 2, and 3 dimensional sub-manifolds respectively. The algorithm is driven by these sub- manifolds. We follow the approach that the highest dimensional transformation is a result from the solution of a sequence of lower dimensional problems driven by successive refinements or partitions of the images into various Biologically meaningful sub-structures.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sarang C. Joshi, Sarang C. Joshi, Michael I. Miller, Michael I. Miller, Gary E. Christensen, Gary E. Christensen, Ayan Banerjee, Ayan Banerjee, Tom Coogan, Tom Coogan, Ulf Grenander, Ulf Grenander, "Hierarchical brain mapping via a generalized Dirichlet solution for mapping brain manifolds", Proc. SPIE 2573, Vision Geometry IV, (11 August 1995); doi: 10.1117/12.216420; https://doi.org/10.1117/12.216420


Back to Top