Multi-spectral probabilistic diffusion using bayesian classification

  • Simon R. Arridge
  • Andrew Simmons
Regular Papers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1252)


This paper proposes a diffusion scheme for multi-spectral images which incorporates both spatial derivatives and feature-space classification. A variety of conductance terms are suggested that use the posterior probability maps and their spatial derivatives to create resistive boundaries that reflect objectness rather than intensity differences alone. A theoretical test case is discussed as well as simulated and real magnetic resonance dual echo images. We compare the method for both supervised and unsupervised classification.


Scale Space Anisotropic Diffusion Feature-Space classification Magnetic Resonance Imaging 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Witkin, A.P.: Scale space filtering. In: Proc. of IJCAI, Karlsruhe, (1983), 1019–1021.Google Scholar
  2. 2.
    Simmons, A., Arridge, S.R., Barker, G.J., Tofts, P.S.: Segmentation of neu-roanatomy in magnetic resonance images. In: Medical Imaging VI: Image Processing, (Ed: M.H.Loew), SPIE-1652 (1992) 2–13Google Scholar
  3. 3.
    Niessen, W.J., Vincken, K.L., Viergever, M.A.: Comparison of multiscale representations for a linking-based image segmentation model. In: Proc. MMBIA'96 (1996) 263–272Google Scholar
  4. 4.
    Alvarez, L., Morel, J.-M.: Morphological approach to multiscale analysis: from principles to equations. In: Geometry-Drive Diffusion in Computer Vision, (ed: B.M. ter Harr Romeney) Kluwer: Dordrecht (1994) 229–254Google Scholar
  5. 5.
    Perona, P., Malik, J. Scale-space and edge-detection using anisotropic diffusion. IEEE Transactions PAMI 12(7) (1990) 629–639.Google Scholar
  6. 6.
    Catté, F., Lions, P.-L., Morel, J.-M., Coll T.: Image selective smoothing and edge detection by nonlinear diffusion. SIAM J. Num. Anal. 29(1) (1992) 182–193Google Scholar
  7. 7.
    Whitaker, R.T.: Geometry Limited Diffusion. PhD thesis, University of North Carolina at Chapel Hill, North Carolina 27599-3175 (1993)Google Scholar
  8. 8.
    Whitaker, R.T., Pizer, S.M.: A multi-scale approach to nonuniform diffusion. Computer Vision, Graphics, and Image Processing: Image Understanding 57(1) (1993) 99–110.Google Scholar
  9. 9.
    Udupa, J.K., Samaraseka, S.: Fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation. Graphical Models and Image Processing 58(3) (1996), 246–261Google Scholar
  10. 10.
    Yoo, S.T., Coggins, J.M.: Using statistical pattern recognition techniques to control variable conductance diffusion. In: Proc. 13th Intnl. Conf. on Information Processing in Medical Imaging, (eds: H.H. Barrett and A.F. Gmitro), Lecture Notes in Computer Science 687, (Springer-Verlag: Berlin) (1993) 459–471Google Scholar
  11. 11.
    Yoo, S.T.: Image geometry through multiscale statistics. PhD thesis, University of North Carolina at Chapel Hill, North Carolina (1996)Google Scholar
  12. 12.
    Gerig, G., Kübler, Kikinis, R., Jolesz, F.A.: Nonlinear anisotropic filtering of MRI data. IEEE Transactions MI. 11(2) (1992) 221–232Google Scholar
  13. 13.
    Bezdek, J.C., Hall, L.O., Clarke, L.P.: Review of MR image segmentation techniques using pattern recognition. Med. Phys. 20(4) (1993) 1033–1048Google Scholar
  14. 14.
    Simmons, A., Arridge, S.R., Barker, G.J., Williams S.C.R.: Simulation of MRI Cluster Plots and Application to Neurological Segmentation. Magnetic Resonance Imaging 14(1) (1996) 73–92Google Scholar
  15. 15.
    Fukunaga, K.: Introduction to statistical pattern recognition. San Diego: Academic Press Inc. 14(1) (1990)Google Scholar
  16. 16.
    Saint-Marc, P., Chen, J.-R.: Adaptive smoothing: a general tool for early vision IEEE Transactions PAMI 13(6) (1991) 514–528Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Simon R. Arridge
    • 1
  • Andrew Simmons
    • 2
  1. 1.Dept. of Computer ScienceUniversity College LondonLondon
  2. 2.Dept. NeurologyInstitute of PsychiatryDenmark Hill

Personalised recommendations