GPU-based parallel-beam and cone-beam forward- and backprojection using CUDA
Institute of Medical Physics (IMP), University of Erlangen-Nurnberg, Henkestr. 91, 91052, Germany
IEEE Nuclear Science Symposium Conference Record, 2008. NSS ’08
@inproceedings{knaup2008gpu,
title={Gpu-based parallel-beam and cone-beam forward-and backprojection using cuda},
author={Knaup, M. and Steckmann, S. and Kachelriess, M.},
booktitle={Nuclear Science Symposium Conference Record, 2008. NSS’08. IEEE},
pages={5153–5157},
organization={IEEE},
year={2008}
}
Analytic and iterative tomographic image reconstruction suffers from the time-consuming forward- and back-projection steps. We recently presented a set of acceleration techniques that improve the performance of forward- and backprojection on CPU (central processing unit) and CBE (cell broadband engine) -based platforms compared to straight-forward implementations by several orders of magnitude.
May 29, 2011 by hgpu
