GPU Accelerated Image Registration in Two and Three Dimensions
MeVis – Center for Medical Diagnostic Systems and Visualization, Universitat Bremen
Bildverarbeitung Fur Die Medizin 2006, Informatik aktuell, 2006, Part 3, 261-265
@article{kohn2006gpu,
title={GPU accelerated image registration in two and three dimensions},
author={K{\”o}hn, A. and Drexl, J. and Ritter, F. and K{\”o}nig, M. and Peitgen, H.},
journal={Bildverarbeitung f{\”u}r die Medizin 2006},
pages={261–265},
year={2006},
publisher={Springer}
}
Medical image registration tasks of large volume datasets, especially in the non-rigid case, often put a heavy burden on computing resources. GPUs are a promising new approach to address computational intensive image processing tasks. We investigate recently introduced GPU hardware features that accelerate 2D and 3D rigid and nonrigid registration tasks. Our implementation is entirely GPU based.
December 29, 2010 by hgpu
