Advertisement

A cooperative and adaptive approach to medical image segmentation

  • C. Spinu
  • C. Garbay
  • J. M. Chassery
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 934)

Abstract

The purpose of the paper is to discuss the potential of a multi-agent approach for low-level image analysis. The work is based on the assumption that low-level processings should be adjusted locally, on zones of given characteristics, and be applied in an iterative framework with careful evaluation and control. A multi-agent architecture has been designed to this end, which allows to develop a dedicated low-level analysis strategy for each detected zone in the image. This analysis is based on an initial segmentation result, obtained as the fusion of two maps: a noise map and a texture map, representing regions with similar noise or texture characteristics. For each zone, a filtering / edge detection strategy is carefully selected and adjusted, based on evaluating the resulting edge map. The results are finally combined in a global segmentation image. The potential of the approach is illustrated on a natural MRI image.

Keywords

Edge Detection Multiplicative Noise Impulsive Noise Medical Image Analysis Medical Image Segmentation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Baujard 94]
    Baujard O., Pesty S., Garbay C., “MAPS: a language for multi-agent system design”, Expert Systems, 11(2): 89–98, 1994.Google Scholar
  2. [Blake 87]
    Blake A., Zisserman A., “Visual Reconstruction”, MIT Press, Cambridge-MA, 1987.Google Scholar
  3. [Chehdi 92]
    Chehdi K., “A new approach to identify the nature of the noise affecting the image”, Proc. IEEE ICASSP'92, pp III.285–III.288, 1992.Google Scholar
  4. [Chin.86]
    Chin R., Dyer C. R., “Model-Based Recognition in Robot Vision”, Computing Surveys 18: 67–108, 1986.CrossRefGoogle Scholar
  5. [Cootes 94]
    Cootes T. F., Taylor C. J., “Using Grey-Level Models to Improve Active Shape Model Search”, 12th IAPR International Conference on Pattern Recognition, pp 63–67, oct. 1994.Google Scholar
  6. [Dellepiane 89]
    Dellepiane S., Ghilino G., Vernazza G., “Biomedical structures recognition by an opportunistic sequence of different segmentation methods”, Medical Imaging, 1989.Google Scholar
  7. [Deriche 87]
    Deriche R., “Using Canny's Criteria to Derive a Recursively Implemented Optimal Edge Detector”, International Journal of Computer Vision, 1(2): 167–187, 1987.CrossRefGoogle Scholar
  8. [Geiger 89]
    Geiger D., Girosi F., “Parallel and Deterministic algorithms for MRFs: surface reconstruction and integration”, MIT AI Memo 1114, June 1989.Google Scholar
  9. [Grimson 90]
    Grimson W. E. L., Lozano-Perez T., “Localising Overlapping parts by Searching the Interpretation Tree”, IEEE PAMI 9, 1987.Google Scholar
  10. [Haralick 79]
    Haralick R. M., “Statistical and structural approaches to texture”, Proc. IEEE, 67: 786–804, 1979.Google Scholar
  11. [Haralick 84]
    Haralick R.M., “Digital Step Edges from Zero-Crossings of Second Directional Derivative”, IEEE Transactions PAMI 6: 58–68, 1984.Google Scholar
  12. [Hueckel 71]
    Hueckel M.F., “An operator which locates edges in digitized pictures”, J. Ass. Comput. Mach., 18(1): 113–125, 1971.Google Scholar
  13. [Kirsch 71]
    Kirsch R., “Computer Determination of the Constituent Structure of Biological Images”, Computer Biomedical Research, 4: 315–328, 1971.CrossRefGoogle Scholar
  14. [Nagao 79]
    Nagao M., Matsuyama T., “Edge preserving smoothing”, Computer Graphics and Image Processing No. 9: 394–407, 1979.CrossRefGoogle Scholar
  15. [Pitas 90]
    Pitas I., Venetsanopoulos A.N., “Non linear digital filters. Principles and applications”, Kluwer Academic Press, 1990.Google Scholar
  16. [Pratt 78]
    Pratt W.K., “Digital Image Processing”, John Wiley, 1978.Google Scholar
  17. [Serra 88]
    Serra J., “Image analysis and Mathematical Morphology: Theoretical advances”, Academic Press, 1988.Google Scholar
  18. [Shen 86]
    Shen J., Castan S., “An Optimal Linear Operator for Edge Detection”, Proceedings CVPR'86, pp 109–114, 1986.Google Scholar
  19. [Venturi 92]
    Venturi G., Capitani P., Carboni M., “A target oriented adaptive segmentation method”, Proc. IEEE 14th Int. Conf. of Engineering in Medicine and Biology Society, pp 1441–1444, 1992.Google Scholar
  20. [Zamperoni 92]
    Zamperoni P., “Adaptive rank-order filters for image processing based on local anisotropy measures”, Digital Signal Processing, 2:174–182, July 1992.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • C. Spinu
    • 1
  • C. Garbay
    • 1
  • J. M. Chassery
    • 1
  1. 1.Faculté de médecine - Domaine de la MerciLab. TIMC / IMAG - Institut Albert BonniotLa Tronche CedexFrance

Personalised recommendations