Skip to main content
SpringerLink
Log in

Automatic Differentiation for GPU-Accelerated 2D/3D Registration

  • Conference paper
Advances in Automatic Differentiation

Part of the book series: Lecture Notes in Computational Science and Engineering ((LNCSE,volume 64))

Summary

A common task in medical image analysis is the alignment of data from different sources, e.g., X-ray images and computed tomography (CT) data. Such a task is generally known as registration. We demonstrate the applicability of automatic differentiation (AD) techniques to a class of 2D/3D registration problems which are highly computationally intensive and can therefore greatly benefit from a parallel implementation on recent graphics processing units (GPUs). However, being designed for graphics applications, GPUs have some restrictions which conflict with requirements for reverse mode AD, in particular for taping and TBR analysis. We discuss design and implementation issues in the presence of such restrictions on the target platform and present a method which can register a CT volume data set (512 × 512 × 288 voxels) with three X-ray images (512 × 512 pixels each) in 20 seconds on a GeForce 8800GTX graphics card.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 139.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 179.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Bauer, C., Frink, A., Kreckel, R.: Introduction to the GiNaC framework for symbolic computation within the C++ programming language. J. Symb. Comput. 33(1), 1–12 (2002). http://www.ginac.de

  2. Baur, W., Strassen, V.: The complexity of partial derivatives. Theoretical Computer Science 22(3), 317–330 (1983)

    Article  MATH  MathSciNet  Google Scholar 

  3. Bischof, C., Khademi, P., Mauer, A., Carle, A.: Adifor 2.0: Automatic differentiation of Fortran 77 programs. IEEE Computational Science & Engineering 3(3), 18–32 (1996)

    Article  Google Scholar 

  4. Bischof, C.H., Bücker, H.M.: Computing derivatives of computer programs. In: Modern Methods and Algorithms of Quantum Chemistry: Proceedings, Second Edition, NIC Series, vol. 3, pp. 315–327. NIC-Directors, Jülich (2000)

    Google Scholar 

  5. Chan, T., Shen, J.: Image Processing and Analysis – Variational, PDE, Wavelet, and Stochastic Methods. SIAM, Philadelphia (2005)

    MATH  Google Scholar 

  6. Corliss, G.F., Griewank, A.: Operator overloading as an enabling technology for automatic differentiation. Tech. Rep. MCS-P358-0493, Mathematics and Computer Science Division, Argonne National Laboratory (1993)

    Google Scholar 

  7. Faure, C., Naumann, U.: Minimizing the tape size. In: G. Corliss, C. Faure, A. Griewank, L. Hascoët, U. Naumann (eds.) Automatic Differentiation of Algorithms: From Simulation to Optimization, Computer and Information Science, chap. 34, pp. 293–298. Springer, New York, NY (2002)

    Google Scholar 

  8. Giering, R., Kaminski, T., Slawig, T.: Applying TAF to a Navier-Stokes solver that simulates an euler flow around an airfoil. Future Generation Computer Systems 21(8), 1345–1355 (2005)

    Article  Google Scholar 

  9. Gong, R.H., Abolmaesumi, P., Stewart, J.: A Robust Technique for 2D-3D Registration. In: Engineering in Medicine and Biology Society, pp. 1433–1436 (2006)

    Google Scholar 

  10. Griewank, A.: The chain rule revisited in scientific computing. SINEWS: SIAM News 24(4), 8–24 (1991)

    Google Scholar 

  11. Griewank, A.: Evaluating derivatives: Principles and techniques of algorithmic differentiation. Society for Industrial and Applied Mathematics, Philadelphia, PA, USA (2000)

    MATH  Google Scholar 

  12. Griewank, A., Juedes, D., Utke, J.: ADOL–C, A package for the automatic differentiation of algorithms written in C/C++. ACM Trans. Math. Software 22(2), 131–167 (1996)

    Article  MATH  Google Scholar 

  13. Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, second edn. Cambridge University Press (2004)

    Google Scholar 

  14. Hascoët, L., Greborio, R.M., Pascual, V.: Computing adjoints by automatic differentiation with TAPENADE. In: B. Sportisse, F.X.L. Dimet (eds.) École INRIA-CEA-EDF “Problèmes non-linéaires appliqués”. Springer (2005)

    Google Scholar 

  15. Hascoët, L., Naumann, U., Pascual, V.: “To be recorded” analysis in reverse-mode automatic differentiation. Future Generation Computer Systems 21(8), 1401–1417 (2005)

    Article  Google Scholar 

  16. Köhn, A., Drexl, J., Ritter, F., König, M., Peitgen, H.O.: GPU accelerated image registration in two and three dimensions. In: Bildverarbeitung für die Medizin, pp. 261–265. Springer (2006)

    Google Scholar 

  17. van de Kraats, E.B., Penney, G.P., Tomazevic, D., van Walsum, T., Niessen, W.J.: Standardized evaluation of 2D-3D registration. In: C. Barillot, D.R. Haynor, P. Hellier (eds.) Proceedings Medical Image Computing and Computer-Assisted Intervention–MICCAI, Lecture Notes in Computer Science, vol. 3216, pp. 574–581. Springer (2004)

    Google Scholar 

  18. Kubias, A., Deinzer, F., Feldmann, T., Paulus, S., Paulus, D., Schreiber, B., Brunner, T.: 2D/3D Image Registration on the GPU. In: Proceedings of the OGRW (2007)

    Google Scholar 

  19. LaRose, D.: Iterative X-ray/CT Registration Using Accelerated Volume Rendering. Ph.D. thesis, Carnegie Mellon University (2001)

    Google Scholar 

  20. Maintz, J.B.A., Viergever, M.A.: A survey of medical image registration. Medical Image Analysis 2(1), 1–36 (1998)

    Article  Google Scholar 

  21. Mark, W.R., Glanville, R.S., Akeley, K., Kilgard, M.J.: Cg: a system for programming graphics hardware in a C-like language. In: J. Hodgins (ed.) SIGGRAPH 2003 Conference Proceedings, Annual Conference Series, pp. 896–907. ACM SIGGRAPH, ACM Press, New York, NY, USA (2003)

    Google Scholar 

  22. Naumann, U.: Reducing the memory requirement in reverse mode automatic differentiation by solving TBR flow equations. Lecture Notes in Computer Science 2330/2002, 1039 (2002)

    Google Scholar 

  23. NVidia Corporation: Compute unified device architecture programming guide version 1.1 (2007). http://developer.nvidia.com/object/cuda.html

  24. Pharr, M. (ed.): GPU Gems 2. Addison Wesley (2005)

    Google Scholar 

  25. Pock, T., Grabner, M., Bischof, H.: Real-time computation of variational methods on graphics hardware. In: 12th Computer Vision Winter Workshop (CVWW 2007). St. Lamprecht (2007)

    Google Scholar 

  26. Pock, T., Pock, M., Bischof, H.: Algorithmic differentiation: Application to variational problems in computer vision. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(7), 1180–1193 (2007)

    Article  Google Scholar 

  27. Wein, W., Röper, B., Navab, N.: 2D/3D registration based on volume gradients. In: SPIE Medical Imaging 2005, San Diego (2005)

    Google Scholar 

  28. Zhu, C., Byrd, R.H., Lu, P., Nocedal, J.: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization. ACM Transactions on Mathematical Software 23(4), 550–560 (1997)

    Article  MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16a/II, 8010, Graz, Austria

    Markus Grabner, Thomas Pock, Tobias Gross & Bernhard Kainz

Authors
  1. Markus Grabner
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas Pock
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tobias Gross
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bernhard Kainz
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institute for Scientific Computing, RWTH Aachen University, 52056, Aachen, Germany

    Christian H. Bischof  & H. Martin Bücker  & 

  2. Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S Cass Ave, Argonne, IL, 60439, USA

    Paul Hovland  & Jean Utke  & 

  3. Software and Tools for Computational Engineering, RWTH Aachen University, 52056, Aachen, Germany

    Uwe Naumann

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Grabner, M., Pock, T., Gross, T., Kainz, B. (2008). Automatic Differentiation for GPU-Accelerated 2D/3D Registration. In: Bischof, C.H., Bücker, H.M., Hovland, P., Naumann, U., Utke, J. (eds) Advances in Automatic Differentiation. Lecture Notes in Computational Science and Engineering, vol 64. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-68942-3_23

Download citation

Publish with us

Policies and ethics

Search

Navigation