CUDA-based acceleration and algorithm refinement for volume image registration
Shenzhen Inst. of Adv. Integration Technol., Chinese Univ. of Hong Kong, Shenzhen, China
International Conference on Future BioMedical Information Engineering, 2009. FBIE 2009
@inproceedings{chen2009cuda,
title={CUDA-based acceleration and algorithm refinement for volume image registration},
author={Chen, S. and Qin, J. and Xie, Y. and Pang, W.M. and Heng, P.A.},
booktitle={BioMedical Information Engineering, 2009. FBIE 2009. International Conference on Future},
pages={544–547},
organization={IEEE},
year={2009}
}
In this paper, we propose a GPU-based acceleration method to speed up volume image registration using Compute Unified Device Architecture(CUDA). A novel CUDA-based method for joint histogram computation is introduced in this paper, which is also valuable for 2D image registration and other general graphics applications. Additionally, an algorithm refinement is proposed to improve the widely used FMRIB’s Linear Image Registration Tool (FLIRT). Although extra time is taken by applying that algorithm refinement, our implementation showed the ability to perform a full 12 DOF (Degrees of Freedom) registration of two brain volume images in nearly 35 seconds, which is about 10 times faster than the native FLIRT implementation.
June 26, 2011 by hgpu
