Fully-Deformable 3D Image Registration in Two Seconds

  • Daniel BudelmannEmail author
  • Lars König
  • Nils Papenberg
  • Jan Lellmann
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


We present a highly parallel method for accurate and efficient variational deformable 3D image registration on a consumer-grade graphics processing unit (GPU). We build on recent matrix-free variational approaches and specialize the concepts to the massively-parallel manycore architecture provided by the GPU. Compared to a parallel and optimized CPU implementation, this allows us to achieve an average speedup of 32:53 on 986 real-world CT thorax-abdomen follow-up scans. At a resolution of approximately 2563 voxels, the average runtime is 1:99 seconds for the full registration. On the publicly available DIR-lab benchmark, our method ranks third with respect to average landmark error at an average runtime of 0:32 seconds.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    König L, Rühaak J. A fast and accurate parallel algorithm for non-linear image registration using normalized gradient fields. Proc ISBI. 2014; p. 580-583.Google Scholar
  2. 2.
    König L, et al. A matrix-free approach to parallel and memory-efficient deformable image registration. SIAM J Sci Comput. 2018;40(3):B858-B888.MathSciNetCrossRefGoogle Scholar
  3. 3.
    Meike M. GPU-basierte nichtlineare Bildregistrierung [mathesis]. 2016;.Google Scholar
  4. 4.
    Modersitzki J. FAIR: Flexible Algorithms for Image Registration. Proc SIAM; 2009.Google Scholar
  5. 5.
    Fischer B, Modersitzki J. A unified approach to fast image registration and a new curvature based registration technique. Linear Algebr Appl. 2004;380:107-124.MathSciNetCrossRefGoogle Scholar
  6. 6.
    Nocedal J. Updating quasi-newton matrices with limited storage. Math Comput. 1980;35(151):773-782.MathSciNetCrossRefGoogle Scholar
  7. 7.
    Wilt N. The CUDA Handbook: A Comprehensive Guide to GPU Programming. Addison-Wesley; 2013.Google Scholar
  8. 8.
    Castillo R, et al. A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets. Phys Med Biol. 2009;54(7):1849-1870.CrossRefGoogle Scholar
  9. 9.
    Castillo E, et al. Four-dimensional deformable image registration using trajectory modeling. Phys Med Biol. 2009;55(1):305-327.CrossRefGoogle Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Daniel Budelmann
    • 1
    Email author
  • Lars König
    • 1
  • Nils Papenberg
    • 1
  • Jan Lellmann
    • 2
  1. 1.Fraunhofer Institute for Medical Image Computing (MEVIS)LübeckDeutschland
  2. 2.Institute of Mathematics and Image ComputingUniversität zu LübeckLübeckDeutschland

Personalised recommendations