Journal of Real-Time Image Processing

, Volume 9, Issue 1, pp 159–170 | Cite as

A comprehensive comparison of GPU- and FPGA-based acceleration of reflection image reconstruction for 3D ultrasound computer tomography

  • Matthias Birk
  • Michael Zapf
  • Matthias Balzer
  • Nicole Ruiter
  • Jürgen Becker
Special Issue


As today’s standard screening methods frequently fail to diagnose breast cancer before metastases have developed, earlier breast cancer diagnosis is still a major challenge. Three-dimensional ultrasound computer tomography promises high-quality images of the breast, but is currently limited by a time-consuming image reconstruction. In this work, we investigate the acceleration of the image reconstruction by GPUs and FPGAs. We compare the obtained performance results with a recent multi-core CPU. We show that both architectures are able to accelerate processing, whereas the GPU reaches the highest performance. Furthermore, we draw conclusions in terms of applicability of the accelerated reconstructions in future clinical application and highlight general principles for speed-up on GPUs and FPGAs.


Medical imaging Heterogeneous computing FPGA GPU Performance comparison 


  1. 1.
    Asano, S., Maruyama, T., Yamaguchi, Y.: Performance comparison of FPGA, GPU and CPU in image processing. In: International Conference on Field Programmable Logic and Applications, FPL, pp. 126–131 (2009)Google Scholar
  2. 2.
    Birk, M., Hagner, C., Balzer, M., Ruiter, N.V., Huebner, M., Becker, J.: Evaluation of the reconfiguration of the data acquisition system for 3D USCT. Int. J. Reconfigurable Comput. 2011, 9 (2011)CrossRefGoogle Scholar
  3. 3.
    Brodtkorb, A.R., Dyken, C., Hagen, T.R., Hjelmervik, J.M., Storaasli, O.O.: State-of-the-art in heterogeneous computing. Sci. Progr. 18, 1–33 (2010)Google Scholar
  4. 4.
    Chase, J., Nelson, B., Bodily, J., Wei, Z., Lee, D.J.: Real-time optical flow calculations on FPGA and GPU architectures: a comparison study. In: 16th International Symposium on field-programmable custom computing machines, FCCM ’08., pp. 173–182 (2008)Google Scholar
  5. 5.
    Cyclone II Device Handbook. Tech. rep., Altera Corporation (2007). (online, accessed 28-Feb-2012)
  6. 6.
    Che, S., Li, J., Sheaffer, J., Skadron, K., Lach, J.: Accelerating compute-intensive applications with GPUs and FPGAs. In: Symposium on Application Specific Processors, SASP, pp. 101–107 (2008)Google Scholar
  7. 7.
    Doctor, S., Hall, T., Reid, L.: SAFT the evolution of a signal processing technology for ultrasonic testing. NDT Int. 19(3), 163–167 (1986)CrossRefGoogle Scholar
  8. 8.
    Ferlay, J., Shin, H., Bray, F., Forman, D., Mathers, C., Parkin, D.: GLOBOCAN 2008 v1.2, Cancer Incidence and Mortality Worldwide: IARC CancerBase No. 10”. Tech. rep., International Agency for Research on Cancer, Lyon. (Internet, accessed 20-Feb-2012)
  9. 9.
    Gemmeke, H., Berger, L., Birk, M., Goebel, G., Menshikov, A., Tcherniakhovski, D., Zapf, M., Ruiter, N.: Hardware setup for the next generation of 3D ultrasound computer tomography. In: IEEE Nuclear Science Symposium Conference Record (NSS/MIC), pp. 2449–2454 (2010)Google Scholar
  10. 10.
    Heigl, B., Kowarschik, M.: High-speed reconstruction for C-arm computed tomography. In: Proceedings of the 9th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and, Nuclear Medicine, pp. 25–28 (2007)Google Scholar
  11. 11.
    Jensen, J., Hansen, M., Tomov, B., Nikolov, S., Holten-Lund, H.: 8A–3 System Architecture of an Experimental Synthetic Aperture Real-Time Ultrasound System. In: Ultrasonics Symposium, IEEE pp. 636–640 (2007)Google Scholar
  12. 12.
    Intel Microarchitecture Codename Nehalem. Tech. rep., Intel Corporation. (online, accessed 20-Feb-2012)
  13. 13.
    Kalarot, R., Morris, J.: Comparison of FPGA and GPU implementations of real-time stereo vision. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 9–15 (2010)Google Scholar
  14. 14.
    Marcus, G., Gao, W., Kugel, A., Manner, R.: The MPRACE framework: an open source stack for communication with custom FPGA-based accelerators. In: VII Southern Conference on Programmable Logic (SPL), pp. 155–160 (2011)Google Scholar
  15. 15.
    Nickolls, J., Dally, W.: The GPU computing era. Micro. IEEE 30(2), 56–69 (2010)CrossRefGoogle Scholar
  16. 16.
    Nol, P.B., Walczak, A.M., Xu, J., Corso, J.J., Hoffmann, K.R., Schafer, S.: GPU-based cone beam computed tomography. Comput. Methods Progr. Biomed. 98(3), 271–277 (2010)CrossRefGoogle Scholar
  17. 17.
    Norton, S.J., Linzer, M.: Ultrasonic reflectivity imaging in three dimensions: reconstruction with spherical transducer arrays. Ultrason. Imag. 1(3), 210–231 (1979)Google Scholar
  18. 18.
    Romero, D., Martinez-Graullera, O., Martin, C., Higuti, R., Octavio, A.: Using GPUs for beamforming acceleration on SAFT imaging. In: IEEE International Ultrasonics Symposium (IUS), pp. 1334–1337 (2009)Google Scholar
  19. 19.
    Ruiter, N., Schwarzenberg, G., Zapf, M., Gemmeke, H.: Improvement of 3D ultrasound computer tomography images by signal pre-processing. In: IEEE Ultrasonics Symposium, IUS 2008, pp. 852–855 (2008)Google Scholar
  20. 20.
    Ruiter, N.V., Goebel, G., Berger, L., Zapf, M., Gemmeke, H.: Realization of an optimized 3D. USCT 7968(1), 796–805 (2011)Google Scholar
  21. 21.
    Sorokin, N.: Parallel backprojector for cone-beam computer tomography. In: International Conference on Reconfigurable Computing and FPGAs, ReConFig ’08, pp. 175–180 (2008)Google Scholar
  22. 22.
    Stone, S., Haldar, J., Tsao, S., Hwu, WmW, Sutton, B., Liang, Z.P.: Accelerating advanced MRI reconstructions on GPUs. J. Parallel Distributed Comput. 68(10), 1307–1318 (2008)CrossRefGoogle Scholar
  23. 23.
    Wu, X.L., Zhuo, Y., Gai, J., Lam, F., Fu, M., Haldar, J.P., Hwu, W.M., Liang, Z.P., Sutton, B.P.: Advanced MRI reconstruction toolbox with accelerating on GPU. Proc SPIE 7872(1), 78720Q (2011)CrossRefGoogle Scholar
  24. 24.
    Xilinx Virtex-6 Documentation. Tech. rep., Xilinx Corporation. (online, accessed 20-Feb-2012)
  25. 25.
    Zapf, M., Schwarzenberg, G.F., Ruiter, N.V.: High throughput SAFT for an experimental USCT system as MATLAB implementation with use of SIMD CPU instructions. Proc SPIE 6920, 692010–692011 (2008).Google Scholar

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • Matthias Birk
    • 1
  • Michael Zapf
    • 1
  • Matthias Balzer
    • 1
  • Nicole Ruiter
    • 1
  • Jürgen Becker
    • 2
  1. 1.Institute for Data Processing and ElectronicsKarlsruhe Institute of Technology (KIT)KarlsruheGermany
  2. 2.Institute for Information Processing TechnologyKarlsruhe Institute of Technology (KIT)KarlsruheGermany

Personalised recommendations