Abstract
This paper presents SCILAB implementation of Simultaneous Algebraic Reconstruction Technique (SART) which is one of a class algorithm iterative method for discretization of inverse problems in medical imaging. These so-called row-action methods rely on semi-convergence for achieving the necessary regularization of the problem. However, because iterative algebraic methods are computationally expensive, we improved utilization of computing resources and parallelize this method using CUDA platform implemented in NVIDIA Graphics Processing Units (GPUs) and SCILAB toolbox. Expansion of GPUs made it possible to explore use of SART. In this paper, we provide GPU-based SART implementation modified for a few simplified test problems in medical imaging with parallel beams and fan beams tomography techniques to test the solver.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hansen, P.C., Saxild-Hansen, M.: AIR Tools—A MATLAB package of algebraic iterative reconstruction methods. J. Comput. Appl. Math. (2012)
Andersen, A.: Algebraic reconstruction in CT from limited views. IEEE Trans. Med. Imaging 8, 50–55 (1989)
Andersen, A., Kak, A.: Simultaneous algebraic reconstruction technique (SART): a superior implementation of the ART algorithm. Ultrason. Imaging 6, 81–94 (1984)
Grama, A., Gupta, A., Karypis, G., Kumar, V.: Introduction to Parallel Computing. Addison Wesley, London (2003)
sciGPGPU QuickStart, http://forge.scilab.org/index.php/p/sciCuda
Andersen, A., Kak, A.: Simultaneous algebraic reconstruction technique (SART): a superior implementation of ART. In: Ultrasonic Imaging (1984)
Kak, A.C., Slaney, M.: Principles of Computerized Tomographic Imaging. SIAM, Philadelphia (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Agmalaro, M.A., Ilyas, M., Garnadi, A.D., Nurdiati, S. (2017). Parallelization of Simultaneous Algebraic Reconstruction Techniques for Medical Imaging Using GPU. In: Ahmad, AR., Kor, L., Ahmad, I., Idrus, Z. (eds) Proceedings of the International Conference on Computing, Mathematics and Statistics (iCMS 2015). Springer, Singapore. https://doi.org/10.1007/978-981-10-2772-7_6
Download citation
DOI: https://doi.org/10.1007/978-981-10-2772-7_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-2770-3
Online ISBN: 978-981-10-2772-7
eBook Packages: EducationEducation (R0)