Abstract
We present a method that performs a rigid 2D/3D image registration efficiently on the Graphical Processing Unit (GPU). As one main contribution of this paper, we propose an efficient method for generating realistic DRRs that are visually similar to x-ray images. Therefore, we model some of the electronic post-processes of current x-ray C-arm-systems. As another main contribution, the GPU is used to compute eight intensity-based similarity measures between the DRR and the x-ray image in parallel. A combination of these eight similarity measures is used as a new similarity measure for the optimization. We evaluated the performance and the precision of our 2D/3D image registration algorithm using two phantom models. Compared to a CPU + GPU algorithm, which calculates the similarity measures on the CPU, our GPU algorithm is between three and six times faster. In contrast to single similarity measures, our new similarity measure achieved precise and robust registration results for both phantom models.
Similar content being viewed by others
References
R. Goecke, J. Weese, and H. Schumann, “Fast Volume Rendering Methods for Voxel-Based 2D/3D Registration—A Comparative Study,” in Proceedings of International Workshop on Biomedical Image Registration’99 (1999), pp. 89–102.
A. Khamene, R. Chisu, W. Wein, N. Navab, and F. Sauer, “A Novel Projection Based Approach for Medical Image Registration,” in Proceedings of Third International Workshop on Biomedical Image Registration (Springer, Berlin, 2006), pp. 247–256.
D. B. Russakoff, T. Rohlfing, K. Mori, D. Rueckert, J. R. Adler, Jr., and C. R. Maurer, Jr., “Fast Generation of Digitally Reconstructed Radiographs Using Attenuation Fields with Application to 2D–3D Image Registration,” IEEE Transactions on Medical Imaging 24(11), 1441–1454 (2005).
R. Strzodka, M. Droske, and M. Rumpf, “Image Registration by a Regularized Gradient Flow—A Streaming Implementation in DX9 Graphics Hardware,” Computing 73(4), 373–389 (2004).
A. Köhn, J. Drexl, F. Ritter, M. König, and H. O. Peitgen, “GPU Accelerated Image Registration in Two and Three Dimensions,” in Proceedings of Bildverarbeitung für die Medizin 2006 (Springer, Berlin, 2006), pp. 261–265.
G. P. Penney, “Registration of Tomographic Images to X-ray Projections for Use in Image Guided Interventions,” PhD Thesis (King’s College, London, 1999).
D. A. LaRose, “Iterative X-ray/CT Registration Using Accelerated Volume Rendering,” PhD Thesis (Carnegie Mellon University, 2001).
A. Khamene, “Automatic Registration of Portal Images and Volumetric CT for Patient Positioning in Radiation Therapy,” Medical Image Analysis 10, 96–112 (2005).
W. Wein, “Intensity Based Rigid 2D–3D Registration Algorithms for Radiation Therapy,” Master’s Thesis (TU München, 2003).
J. Krüger and R. Westermann, “Acceleration Techniques for GPU-based Volume Rendering,” in Proceedings of the 14th IEEE Visualization 2003 (Washington, DC, USA, IEEE Computer Society, 2003), pp. 287–292.
H. Scharsach, “Advanced GPU Raycasting,” in Proceedings of Central European Seminar on Computer Graphics for Students 2005 (2005), pp. 67–76.
E. Trucco and A. Verri, Introductory Techniques for 3D Computer Vision (Prentice Hall, New York, 1998).
A. Zhigljavsky, Theory of Global Random Search (Kluwer Academic, Edmonton, 1991).
A. Törn and A. Zilinskas, Global Optimization (Springer, Berlin, 1989).
Ed. by A. Oppelt, Imaging Systems for Medical Diagnostics (Publicis, Erlangen, 2005).
G. Cox, “Automatic Registration of Temporal Image Pairs for Digital Subtraction,” in Proceedings of SPIE Medical Imaging 1994: Image Processing (SPIE Press, 1994), Vol. 2167, pp. 188–199.
R. P. Woods, S. R. Cherry, and J. C. Mazziotta, “Rapid Automated Algorithm for Alignment and Reslicing PET Images,” Journal of Computer Assisted Tomography 16(4), 634–639 (1992).
G. P. Penney, J. Weese, J. A. Little, P. Desmedt, D. L. Hill, and D. J. Hawkes, “A Comparison of Similarity Measures for Use in 2D–3D Medical Image Registration,” IEEE Transactions on Medical Imaging 17(4), 586–595 (1998).
Author information
Authors and Affiliations
Corresponding author
Additional information
The text was submitted by the authors in English.
Alexander Kubias. Born 1982. Obtained his diploma (Dipl.-Inf.) degree in 2006 from the University of Koblenz-Landau. Currently research assistant for semantic web applications at the University of Koblenz-Landau, Koblenz, Germany. Research interests: image processing and semantic web. Author and coauthor of several conference/workshop articles about medical image registration and semantic web query languages.
Frank Deinzer. Born 1972. Obtained his diploma (Dipl.-Inf.) degree in 1998 and his PhD (Dr.-Ing.) in computer science in 2005 from the University of Erlangen. Currently project lead for medical image fusion at Siemens AG, Medical Solutions, Forchheim, Germany. Research interests: statistical fusion of sensor data in the field of medical image processing. Author and coauthor of more than 30 conference/journal articles and books. His work on sensor fusion for active object recognition was awarded the DAGM best paper award in 2001. He is a member of Gesellschaft für Informatik (GI, German society for computer science).
Tobias Feldmann. Born 1976. Obtained his diploma (Dipl.-Inf.) degree in 2006 from the University of Koblenz-Landau. He was a member of the research group “Active Vision” at the University of Koblenz-Landau until 2007 and is currently a researcher at the University of Karlsruhe, “Institute for Algorithms and Cognitive Systems,” Group on Human Motion Analysis. Research interests: Image Registration, Image-based 3D Reconstruction and Pose Tracking. Author and coauthor of 6 publications. He is a member of GI (German society for computer science) and DAGM (German Society for Pattern Recognition).
Dietrich Paulus. Obtained a Bachelor degree in Computer Science from the University of Western Ontario, London, Ontario, Canada, followed by a diploma (Dipl.-Inf.) in Computer Science and a PhD (Dr.-Ing.) from Friedrich-Alexander University Erlangen-Nuremberg, Germany. He worked as a senior researcher at the chair for pattern recognition (Prof. Dr. H. Niemann) at Erlangen University from 1991–2002. Since 2001 he is at the institute for computational visualistics at the University of Koblenz-Landau, Germany, where he became a full professor in 2002. He is currently the dean of the department of computer science at the University of Koblenz-Landau. His primary research interests are active computer vision, object recognition, color image processing, medical image processing, and software engineering for computer vision. He has published over 150 papers on these topics, and he is the author of three textbooks. He is member of Gesellschaft für Informatik (GI) and IEEE.
Bernd Schreiber. Born in 1965. Physics Diploma in 1990 by the University of Erlangen-Nürnberg, PhD in Physics in 1993 by the University of Erlangen-Nürnberg (Area of research: Theoretical High Energy Physics). Postgraduate Student from 1993 to 1995 at the Massachusetts Institute of Technology, Cambridge, USA. From 1995 to 2004 employee at the Philips Research Laboratories in Hamburg, Germany (main areas of research: radiation therapy, explosives and narcotics detection in checked luggage by coherent x-ray scatter methods, landmine detection by Compton scatter methods). Since 2004 with Siemens Medical Solutions in Forchheim, Germany: 3D Imaging with open C-arm x-ray systems. Author and coauthor of more than 20 publications.
Thomas Brunner. Born 1960. Obtained his diploma (Dipl.-Phys.) in 1985 and his PhD (Dr. rer. nat., Theoretical Solid State Physics) in 1990 from the University of Munich (Technische Universität München). Currently Senior Expert for Engineering at Siemens AG, Medical Solutions, Forchheim, Germany. Research interests: C-arm Computed Tomography. Author and coauthor of 27 articles.
Rights and permissions
About this article
Cite this article
Kubias, A., Deinzer, F., Feldmann, T. et al. 2D/3D image registration on the GPU. Pattern Recognit. Image Anal. 18, 381–389 (2008). https://doi.org/10.1134/S1054661808030048
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661808030048