Title :
Accelerated cone beam CT reconstruction based on OpenCL
Author :
Wang, Bo ; Zhu, Lei ; Jia, Kebin ; Zheng, Jie
Author_Institution :
Coll. of Electron. Inf. & Control Eng., Beijing Univ. of Technol., Beijing, China
Abstract :
Open Computing Language (OpenCL) is a fundamental technology for cross-platform parallel programming. The emerging of OpenCL provides portable and efficient access to the power of modern processors. This revolutionary new technology is applied to accelerate the reconstruction of cone beam computed tomography (CBCT) on Graphics Processing Unit (GPU) in this paper. An OpenCL-based implementation of the Feldkamp-Davis-Kress (FDK) algorithm is presented. The required transformations to parallelize the algorithm for the OpenCL architecture are also explained. Comparing to the conventional CPU-based implementation, the proposed method reaches an over 57 times speedup. Experimental results show a great performance boost, which can pave the way for widespread application and new conceptual innovation of CBCT. Besides, the feasibility and potential of OpenCL-based implementation are also indicated.
Keywords :
computer graphic equipment; computer graphics; computerised tomography; coprocessors; image reconstruction; parallel programming; programming languages; FDK; Feldkamp-Davis- Kress algorithm; OpenCL architecture; cone beam computed tomography; graphics processing unit; image reconstruction; open computing language; parallel programming; Acceleration; Computed tomography; Computer architecture; Concurrent computing; Image reconstruction; Kernel; Parallel programming; Particle beams; Reconstruction algorithms; Runtime; FDK; OpenCL; cone beam computed tomography; image reconstruction; parallel computing;
Conference_Titel :
Image Analysis and Signal Processing (IASP), 2010 International Conference on
Conference_Location :
Zhejiang
Print_ISBN :
978-1-4244-5554-6
Electronic_ISBN :
978-1-4244-5556-0
DOI :
10.1109/IASP.2010.5476110
