Multi-resolution 3D Nonrigid Registration via Optimal Mass Transport on the GPU

Thumbnail Image
Files
2007_miccai_02.pdf (818.7 KB)
Author(s)
Rehman, Tauseef ur
Pryor, Gallagher D.
Melonakos, John
Tannenbaum, Allen R.
Advisor(s)
Editor(s)
Associated Organization(s)
Organizational Unit
Wallace H. Coulter Department of Biomedical Engineering
The joint Georgia Tech and Emory department was established in 1997
Organizational Unit
Series
Collections
Research Publications
Supplementary to:
Permanent Link
http://hdl.handle.net/1853/29321
Abstract
In this paper we present computationally efficient implementation of the minimizing flow approach for optimal mass transport (OMT) with applications to non-rigid 3D image registration. Our implementation solves the OMT problem via multi-resolution, multigrid, and parallel methodologies on a consumer graphics processing unit (GPU). Although computing the optimal map has shown to be computationally expensive in the past, we show that our approach is almost two orders magnitude faster than previous work and is capable of finding transport maps with optimality measures (mean curl) previously unattainable by other works (which directly influences the accuracy of registration). We give results where the algorithm was used to compute non-rigid registrations of 3D synthetic data as well as intra-patient pre-operative and post-operative 3D brain MRI datasets.
Sponsor
Date
2007
Extent
Resource Type
Text
Resource Subtype
Proceedings
Rights Statement
Rights URI