Communication optimization and auto load balancing in parallel OSEM algorithm for fully 3-D SPECT reconstruction

Author

Tianyu, Ma ; Rong, Zhou ; Yongjie, Jin

Volume

5

fYear

2005

fDate

23-29 Oct. 2005

Firstpage

2695

Lastpage

2699

Abstract

In order to improve the computation speed of ordered subset expectation maximization (OSEM) algorithm for fully 3-D single photon emission computed tomography (SPECT) reconstruction, a parallelizing scheme of OSEM reconstruction algorithm was implemented on an experimental beowulf-type cluster and impact factors on the parallel efficiency were investigated. Two approaches were employed to improve the efficiency: (1) the communication cost was minimized via overlapping communication with computation and (2) the idle time of processes was reduced by auto load balancing. Performance of the optimized parallel algorithm was evaluated in terms of computation time, speedup factor and parallel efficiency. Improvements were observed after optimization. The efficiency was raised from 83.86% to 92.07% in fully 3-D 128 times 128 times 128 SPECT reconstruction

Keywords

image reconstruction; medical image processing; optimisation; parallel algorithms; single photon emission computed tomography; auto load balancing; beowulf-type cluster; communication optimization; computation time; fully 3-D SPECT reconstruction; impact factors; ordered subset expectation maximization; parallel OSEM algorithm; parallel efficiency; parallelizing scheme; single photon emission computed tomography; speedup factor; Clustering algorithms; Concurrent computing; Image reconstruction; Load management; Optical computing; Parallel algorithms; Positron emission tomography; Reconstruction algorithms; Single photon emission computed tomography; Three dimensional displays;

fLanguage

English

Publisher

ieee

Conference_Titel

Nuclear Science Symposium Conference Record, 2005 IEEE

Conference_Location

Fajardo

ISSN

1095-7863

Print_ISBN

0-7803-9221-3

Type

conf

DOI

10.1109/NSSMIC.2005.1596892

Filename

1596892