UW Madison UW School of Medicine and Public Health
UW Biiostatistics & Medical Informatics UW Biostatistics & Medical Informatics UW Madison UW Biostatistics & Medical Informatics Site Map

Seminars

General Departmental Seminar Series

Symetric Image Normalization in the Space of Diffeomorphisms

James C. Gee
Associate Professor of Radiologic Science
and Computer and Information Science
Director of Penn Image and Computing Science and Laboratory

Friday, October 5, 2007
12:00 pm
5275 MSC

 

ABSTRACT

Medical image analysis based on diffeomorphisms (differentiable
one to one and onto maps with differentiable inverse) has placed
computational analysis of anatomy and physiology on firm theoretical
ground.  We detail our approach to diffeomorphic computational anatomy
while highlighting both theoretical and practical benefits.  We first
introduce the metric used to locate geodesics in the diffeomorphic space.
Second, we give a variational energy that parameterizes the image
normalization problem in terms of a geodesic diffeomorphism, enabling a
fundamentally symmetric solution.  This approach to normalization is
extended for optimal template population studies using general imaging
data.  Finally, we show how the temporal parameterization and large
deformation capabilities of diffeomorphisms make them appropriate for
longitudinal analysis, particularly of neurodegenerative data.

Return to seminar list