Accelerating Cone Beam Reconstruction Using the CUDA-Enabled GPU

  • Yusuke Okitsu
  • Fumihiko Ino
  • Kenichi Hagihara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5374)

Abstract

Compute unified device architecture (CUDA) is a software development platform that enables us to write and run general-purpose applications on the graphics processing unit (GPU). This paper presents a fast method for cone beam reconstruction using the CUDA-enabled GPU. The proposed method is accelerated by two techniques: (1) off-chip memory access reduction; and (2) memory latency hiding. We describe how these techniques can be incorporated into CUDA code. Experimental results show that the proposed method runs at 82% of the peak memory bandwidth, taking 5.6 seconds to reconstruct a 5123-voxel volume from 360 5122-pixel projections. This performance is 18% faster than the prior method. Some detailed analyses are also presented to understand how effectively the acceleration techniques increase the reconstruction performance of a naive method.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kachelrieß, M., Knaup, M., Bockenbach, O.: Hyperfast parallel-beam and cone-beam backprojection using the cell general purpose hardware. Medical Physics 34(4), 1474–1486 (2007)CrossRefGoogle Scholar
  2. 2.
    Xu, F., Mueller, K.: Real-time 3D computed tomographic reconstruction using commodity graphics hardware. Physics in Medicine and Biology 52(12), 3405–3419 (2007)CrossRefGoogle Scholar
  3. 3.
    Scherl, H., Keck, B., Kowarschik, M., Hornegger, J.: Fast GPU-based CT reconstruction using the common unified device architecture (CUDA). In: Proc. Nuclear Science Symp. and Medical Imaging Conf (NSS/MIC 2007), October 2007, pp. 4464–4466 (2007)Google Scholar
  4. 4.
    Riabkov, D., Xue, X., Tubbs, D., Cheryauka, A.: Accelerated cone-beam backprojection using GPU-CPU hardware. In: Proc. 9th Int’l. Meeting Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine (Fully 3D 2007), July 2007, pp. 68–71 (2007)Google Scholar
  5. 5.
    Zhao, X., Bian, J., Sidky, E.Y., Cho, S., Zhang, P., Pan, X.: GPU-based 3D cone-beam CT image reconstruction: application to micro CT. In: Proc. Nuclear Science Symp. and Medical Imaging Conf. (NSS/MIC 2007), October 2007, pp. 3922–3925 (2007)Google Scholar
  6. 6.
    Schiwietz, T., Bose, S., Maltz, J., Westermann, R.: A fast and high-quality cone beam reconstruction pipeline using the GPU. In: Proc. SPIE Medical Imaging 2007, February 2007, pp. 1279–1290 (2007)Google Scholar
  7. 7.
    Gac, N., Mancini, S., Desvignes, M.: Hardware/software 2D-3D backprojection on a SoPC platform. In: Proc. 21st ACM Symp. Applied Computing (SAC 2006), pp. 222–228 (April 2006)Google Scholar
  8. 8.
    nVIDIA Corporation: CUDA Programming Guide Version 1.1 (November 2007), http://developer.nvidia.com/cuda/
  9. 9.
    Feldkamp, L.A., Davis, L.C., Kress, J.W.: Practical cone-beam algorithm. J. Optical Society of America 1(6), 612–619 (1984)CrossRefGoogle Scholar
  10. 10.
    Li, M., Yang, H., Koizumi, K., Kudo, H.: Fast cone-beam CT reconstruction using CUDA architecture. Medical Imaging Technology 25(4), 243–250 (2007) (in Japanese)Google Scholar
  11. 11.
    Ikeda, T., Ino, F., Hagihara, K.: A code motion technique for accelerating general-purpose computation on the GPU. In: Proc. 20th IEEE Int’l. Parallel and Distributed Processing Symp. (IPDPS 2006), 10 pages (April 2006) (CD-ROM)Google Scholar
  12. 12.
    Grass, M., Köhler, T., Proksa, R.: 3D cone-beam CT reconstruction for circular trajectories. Physics in Medicine and Biology 45(2), 329–347 (2000)CrossRefGoogle Scholar
  13. 13.
    Shepp, L.A., Logan, B.F.: The fourier reconstruction of a head section. IEEE Trans. Nuclear Science 21(3), 21–43 (1974)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Yusuke Okitsu
    • 1
  • Fumihiko Ino
    • 1
  • Kenichi Hagihara
    • 1
  1. 1.Graduate School of Information Science and TechnologyOsaka UniversityOsakaJapan

Personalised recommendations