Advertisement

Abstract

There are various applications, both in medical and non-medical image analysis, which require the automatic detection of the line (2D images) or plane (3D) of reflective symmetry of objects. There exist relatively simple methods of finding reflective symmetry when object images are complete (i.e., completely symmetric and perfectly segmented from image “background”). A much harder problem is finding the line or plane of symmetry when the object of interest contains asymmetries, and may not have well defined edges.

A major area of interest is brain image analysis; there are various reasons why one would want to be able to automatically, robustly and accurately find the (sagittal) mid-plane from a 3D brain image. Example applications include pre-alignment (or sanity checking) for standard registration methods, mid-plane finding as part of symmetric probabilistic anatomical map generation, and, in particular, symmetry-based analyses (e.g., for schizophrenia research). This paper describes EROS – Extraction of Robust Orientation using Symmetry, which has been developed to solve this problem. It has been shown to work with MRI (T1, T2, EPI), PET, SPECT and CT, using robust measures to give accurate results even with images containing large asymmetries.

Keywords

Symmetry detection robust registration mid-plane 

References

  1. 1.
    Di Gesù, V., Valenti, C.: Symmetry operators in computer vision. Vistas in Astronomy 40 (1996)Google Scholar
  2. 2.
    Jenkinson, M., Smith, S.: Robustness issues in automatic brain image registration. In: Proc. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention (1999) (submitted)Google Scholar
  3. 3.
    Minoshima, S., Berger, K.L., Lee, K.S., Mintun, M.A.: An automated method for rotation correction and centering of three-dimensional functional brain images. Journal of Nuclear Medicine 33, 1579–1585 (1992)Google Scholar
  4. 4.
    Reisfeld, D., Wolfson, H., Yeshurun, Y.: Context free attentional operators: The generalized symmetry transform. Int. Journal of Computer Vision 14, 119–130 (1995)CrossRefGoogle Scholar
  5. 5.
    Sun, C.: Symmetry detection using gradient information. Pattern Recognition Letters 16(9), 987–996 (1995)CrossRefGoogle Scholar
  6. 6.
    Thirion, J.-P., Prima, S., Subsol, G.: Statistical analysis of dissymmetry in volumetric medical images. Technical Report 3178, INRIA Sophia-Antipolis (1997)Google Scholar
  7. 7.
    Woods, R.P., Cherry, S.R., Mazziotta, J.C.: Rapid automated algorithm for aligning and reslicing PET images. Journal of Computer Assisted Tomography 16(4), 620–633 (1992)CrossRefGoogle Scholar
  8. 8.
    Woods, R.P., Mazziotta, J.C., Cherry, S.R.: MRI–PET registration with automated algorithm. Journal of Computer Assisted Tomography 17(4), 536–546 (1993)CrossRefGoogle Scholar
  9. 9.
    Zielke, T., Brauckmann, M., von Seelen, W.: Intensity and edge-based symmetry detection applied to car-following. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 865–873. Springer, Heidelberg (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Stephen Smith
    • 1
  • Mark Jenkinson
    • 1
  1. 1.FMRIB (Oxford Centre for Functional Magnetic Resonance Imaging of the Brain), Department of Clinical NeurologyUniversity of Oxford, John Radcliffe HospitalOxfordUK

Personalised recommendations