International Journal on Magnetic Particle Imaging IJMPI
Vol. 9 No. 1 Suppl 1 (2023): Int J Mag Part Imag
https://doi.org/10.18416/IJMPI.2023.2303043

Proceedings Articles

Parallel MPI image reconstructions in GPU using CUDA

Main Article Content

Klaus Natorf Quelhas (National Institute of Standards and Technology; UNiversidade Federal do Rio de Janeiro), Mark-Alexander Henn (NIST), Ricardo Cordeiro de Farias (UFRJ), Weston Leo Tew (NIST), Solomon Isaac Woods (NIST)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

This work shows that it is possible to obtain faster MPI image reconstructions by implementing the algorithms in parallel in Graphics Processing Units (GPUs) using NVIDIA’s CUDA (Compute Unified Device Architecture). While the parallel Kaczmarz’s algorithm was slower than its serial version running in the Central Processing Unit (CPU), the parallel version of the Conjugate Gradient Normal Residual (CGNR) algorithm was about 58 times faster than its serial implementation, and about 10 times faster than the serial implementation of Kaczmarz’s.

Article Details

References

[1] B. Gleich and J.Weizenecker. Tomographic imaging using the nonlinear response of magnetic particles.Nature, 435(7046):1214–1217, 2005, doi:10.1038/nature03808.
[2] T. Knopp and T. M. Buzug, Magnetic Particle Imaging: An Introduction to Imaging Principles and Scanner Instrumentation. Berlin/Heidelberg: Springer, 2012, doi:10.1007/978-3-642-04199-0.
[3] M. Storath, C. Brandt, M. Hofmann, T. Knopp, J. Salamon, A.Weber and A.Weinmann. Edge preserving and noise reducing reconstruction for magnetic particle imaging. IEEE TRANSACTIONS ON MEDICAL IMAGING, 36(1):74–85, 2017, doi:10.1109/TMI.2016.2593954.
[4] P. Vogel, S. Herz, T. Kampf, M. A. Rückert, T. A. Bley, and V. C. Behr. Low latency real-time reconstruction for MPI systems. International Journal on Magnetic Particle Imaging, 3(2):8, 2017,
doi:10.18416/ijmpi.2017.1707002.
[5] X. Chen, Z. Jiang, X. Han, X. Wang, and X. Tang. The reconstruction of magnetic particle imaging: Current approaches based on the system matrix. Diagnostics, 11(773):18, 2021,
doi:10.3390/diagnostics11050773.
[6] J. M. Elble, N. V. Sahinidis, and P. Vouzis. Gpu computing with kaczmarz’s and other iterative algorithms for linear systems. Parallel Computing, 36:215–231, 2009, doi:10.1016/j.parco.2009.12.003.
[8] M.-A. Henn, K. N. Quelhas, T. Q. Bui, and S. I. Woods. Improving model-based MPI image reconstructions: Baseline recovery, receive coil sensitivity, relaxation and uncertainty estimation.
International Journal on Magnetic Particle Imaging, 2022, doi:10.18416/IJMPI.2022.2208001.