Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Hauptseminar: Medical Image Registration

Nassir Navab and Wolfgang Wein

SWS: 2+0
*Time/Location: to be announced
The seminar language is English.


Please send an Email to Wolfgang Wein, including your favorite topic.

General content

In clinical practice medical imaging is a crucial component of a large number of applications. Usually not only one image modality (imaging device) is used but several (like Computed Tomography, Magnetic Resonance Imaging, Angiography, Ultrasound, or the real patient), providing different kinds of information to physicians. Moreover, medical image data acquired during diagnosis is often used to aid in operations and intraoperative images are revised for follow-up. One of the goals of medical image registration is to merge the different image modalities in order to improve visual judgement for treatment or diagnosis. For instance, injected instruments can be visualized in 3D or tumor positions can be detected, both without opening the patient.

Schein requirements

  • attendance of the weekly meeting
  • active class participation
  • presentation in the weekly meeting (about 45 minutes + discussion)
  • workout of the presentation (about 15 pages)

Detailed Overview

Multi-modal image registration can provide enhanced information from different image modalities. For that, the modalities (like CT, MR, Angiography, Ultrasound) must be aligned such that anatomical features of one modality can be automatically detected in the other modality (or modalities). Modalities can differ in viewpoint (from where the images were taken), the sensor (e.g. X-ray, Utrasound, or laser scanner), and the time the images were recorded. Depending on which specific anatomy is imaged, or which device has been used for it respectively, registration methods differ in their applicability. Furthermore, if a real patient is to be aligned with preoperative data, one has to evaluate how to acquire data from the real patient that can be registered with the image data. For instance, laser scanners can compute point clouds in space, which are later registered with the preoperative image data. For all this different applications one has to determine the best registration method. For instance, registering a region of the heart is hardly performed on rigid models since the beating heart deforms patient or modalities involved. Thus, non-rigid approaches are used in order to compensate for heart beat. Multi-modal registration offers feature-based and intensity-based methods, the former ones registering on anatomical features (landmarks, markers), the latter ones only on image intensities (e.g. gray values). Intensity-based registration, for instance, needs data comparison, so filters or other image processing algorithms are applied to the modalities for a suitable sensor comparability. Optimizing an initial guess of the registration parameters is crucial in almost any registration procedure. Again, the most suitable optimization algorithm (e.g. nonlinear methods like Gauss-Newton, Levenberg-Marquardt, or Best Neighbor iteration) must be chosen for a specific application. All these issues of medical image registration will be discussed in this seminar. For participants, a general interest in Medicine and Computer Graphics/Vision would be a good point to start from.


Date Topic Supervisor Student
Oct 26, 2004 Introduction to (medical) image registration    
Nov 02, 2004 Projective Geometry and Transformations in Space    
Nov 09, 2004 Registration Based on Point Correspondences    
Nov 16, 2004 Linear and non-linear optimization techniques    
Nov 23, 2004 Segmentation 1: Pixel-, Region- and Edge-Based Approaches    
Nov 30, 2004 Segmentation 2: Model-Based Approaches, Snakes and Level Sets    
Dec 07, 2004 Surface-Based Registration: Iterative Closest Point    
Dec 14, 2004 Voxel-Based 3D-3D Registration    
Dec 21, 2004 Volume Rendering of Medical Image Data    
Jan 11, 2004 Voxel-Based 2D-3D Registration    
Jan 18, 2004 Non-Rigid Registration: Overview & Parametric Deformation Models    
Jan 25, 2005 Non-Rigid Registration: PDE & Tensor approaches    
Feb 01, 2005 not fixed yet    
Feb 08, 2005 not fixed yet    

Topics & Literature

Image Registration Methodology & Terminology

  • J. V. Hajnal, D.L.G. Hill, and D. J. Hawkes (editors): Medical Image Registration; The Biomedical Engineering Series, CRC Press, 2001
  • A.G. Brown: A survey of Image Registration Techniques; ACM Computing Surveys, vol.24, pp.326-276, 1992
  • B. Zitova and J. Flusser: Image Registration Methods: a Survey; Image and Vision Computing, vol.24, pp.977-1000, 2003
  • J.B.A. Maintz and M.A. Viergever: A Survey of Medical Image Registration; Medical Image Analysis, vol.2, pp.1-36, 1998

Registration Based on Point Correspondences

  • K.S. Arun, T.S. Huang and S.D. Blostein: Least-Squares Fitting of Two 3-D Point Sets
  • Shinji Umeyama: Least-Squares Estimation of Transformation Parameters Between Two Point Patterns
  • Berthold K.P. Horn: Tsai's camera calibration method revisited

Linear and non-linear optimization techniques

  • W. Press, B. Flannery, S. Teukolsky, W. Vetterling: Numerical Recipes in C; Cambridge University Press, 1988
  • R. Hartley, A. Zisserman: Appendix 6, Iterative Estimation Methods, in Multiple View Geometry in Computer Vision; Cambridge University Press, 2nd edition, 2003
  • P.E. Gill, W. Murray, M.H. Wright: Practical Optimization; 12th printing, Academic Press, San Diego, 2000
  • P.E. Gill, W. Murray: Algorithms for the solution of the nonlinear least-squares problem; SIAM Journal of Numerical Analysis, 15(5), pp. 977-992, 1978

Segmentation 1: Pixel-, Region- and Edge-Based Approaches

  • T. Lehmann, W. Oberschelp, E. Pelikan, R. Repges: Bildverarbeitung für die Medizin. Springer, 1997.

Segmentation 2: Model-Based Approaches, Snakes and Level Sets

  • Kass, Witkin, Terzopoulos: Snakes: Active contour models, International Journal Computer Vision, 321-331, 1987
  • J.A. Sethian: Level set methods and fast marching methods

Surface-Based Registration: Iterative Closest Point

  • Zhengyou Zhang: Iterative Point Matching for Registration of Free-Form Curves, INRIA, March 1992
  • Selected chapters of Joseph V. Hajnal, Derek L.G. Hill and David J. Hawkes: Medical Image Registration
  • M.A. Audette, F.P. Ferrie, T.M. Peters: An Algorithmic Overview of Suface Registration Techniques for Medical Imaging, Medical Image Analysis, vol 4, no. 3, pp 201 - 217, 2000

Voxel-Based 3D-3D Registration

  • J. V. Hajnal, D.L.G. Hill, and D. J. Hawkes (editors): Medical Image Registration (Chapter 3)
  • F. Maes, D. Vandermeulen and P. Suetens: Medical Image Registration Using Mutual Information, IEEE Proceedings Vol. 91 No. 10, October 2003

Volume Rendering

  • R. Yagel: Classification and Survey of Algorithms for Volume Viewing, 1996
  • T. Todd Elvins, A Survey of Algorithms for Volume Visualization; Computer Graphics, 26 (3), 1992
  • P. Heckbert: A Survery of Texture Mapping; IEEE Computer Graphics and Applications, Nov 1986
  • R. Westermann, T. Ertl: Efficiently using Graphics Hardware in Volume Rendering Applications; ACM SIGGRAPH 1998, pp. 169-177
  • C. Rezk-Salama: Volume Rendering Techniques for General Purpose Graphics Hardware; PhD-Thesis, University of Erlanden, 2001

Voxel-Based 2D-3D Registration

  • G.P. Penney, J. Weese, J.A. Little, P. Desmedt, D.L.G. Hill, D.J. Hawkes: A Comparison of Similarity Measures for use in 2-D-3-D Medical Image Registration; IEEE Transactions on Medical Imaging, 17(4), Aug 1998
  • J.H. Hipwell, G.P. Penney, R.A. McLaughlin, K. Rhode, P. Summers, T.C. Cox, J.V. Byrne, J.A. Noble, D.J. Hawkes: Intensity-Based 2-D-3-D Registration of Cerebral Angiograms; IEEE Transactions on Medical Imaging, 22(11), Nov 2003
  • H. Livyatan, Z. Yaniv, L. Joskowicz: Gradient-Based 2-D/3-D Rigid Registration of Fluoroscopic X-ray to CT; IEEE Transactions on Medical Imaging, 22(11), Nov 2003
  • D. Tomazevic, B. Likar, T. Slivnik, F. Pernus: 3-D/2-D Registration of CT and MR to X-ray Images IEEE Transactions on Medical Imaging, 22(11), Nov 2003

Non-Rigid Approaches

  • J. V. Hajnal, D.L.G. Hill, and D. J. Hawkes (editors): Chapter 13: Nonrigid Registration: Concepts, Algorithms, and Applications; Medical Image Registration; The Biomedical Engineering Series, CRC Press, 2001
  • W.R. Crum, L.D. Griffin, D.L.G. Hill, D.J. Hawkes: Zen and the art of medical image registration: correspondence, homology, and quality; Neuroimage. 2003 Nov;20(3):1425-37.
  • G.K. Rohde, A. Aldroubi, B.M. Dawant: The Adaptive Bases Algorithm for Intensity-Based Nonrigid Image Registration; IEEE Transactions on Medical Imaging, 22(11), Nov. 2003

Edit | Attach | Refresh | Diffs | More | Revision r1.1 - 19 Jan 2005 - 17:59 - JoergTraub

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif