Neural networks for parallel contrast enhancement in medical images

  • J. Mattes
  • D. Trystram
  • J. Demongeot
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 919)


The aim of the project described in this paper is contrast enhancement in medical images in real time. Our approach is a parallel neural network algorithm, implemented in a SIMD environement. We describe a new learning rule for this algorithm. We design an optimal communication pattern and some experiments on a parallel machine for treating a real image.


Learning Rule Input Matrix Presynaptic Neuron Neural Network Technique Processor Element 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lavallée, S., Troccaz, J., Sautot, P., Brunie, L., Cinquin, P., Merloz, P., Chirossel, J. P.: Robot assisted spine surgery. IEEE Trans. Robotics & Automation (accepted)Google Scholar
  2. 2.
    Tenorio, M. F., Hughes, C. S.: Real time noisy image segmentation using an artificial neural network model. Proc. of IEEE ICNN87 (1987) IV:357–IV:363Google Scholar
  3. 3.
    Cottet, G.H.: Modèles de réaction-diffusion pour les réseaux de neurones stochastiques et déterministes. C.R.Acad.Sc. 312 (1991) 217–221MATHMathSciNetGoogle Scholar
  4. 4.
    Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans. PAMI 13 (1984) 721–741Google Scholar
  5. 5.
    Catte, F., Lions, P. L., Morel, J. M., Coll, T.: Image selective smoothing and edge detection by non linear diffusion. SIAM J. Numer. Anal. 29 (1992) 182–193MathSciNetGoogle Scholar
  6. 6.
    Leitner, F., Marque, I., Berthommier, F., Coll, T., Francois, O., Cinquin, P., Demongeot, J.: Neural Networks, differential systems and image processing. In: From Pixels to features II, eds. J. C. Simon (North Holland, 1991) 253–274Google Scholar
  7. 7.
    Hervé, T., Dolmazon J. M., and Demongeot, J.: Random field and neural information: a new representation for multi-neural activity. Proc. Natl. Acad. Sc., USA 87 (1990) 806–810Google Scholar
  8. 8.
    K. A. Grajski et al.: Neural network simulation on the MasPar MP-1 massively parallel processor. In: Proc. INNC, Paris, France, July (1990)Google Scholar
  9. 9.
    Digital Equipment Corp.: DECmpp programming Language User's Guide. (Maynard, Massachusetts, 1992)Google Scholar
  10. 10.
    Hwang, K.: Advanced Computer Architectures — Parallelism, Scalability, Programmability. (Mac Graw Hill, 1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • J. Mattes
    • 1
  • D. Trystram
    • 2
  • J. Demongeot
    • 1
  1. 1.TIMC-IMAGUniversité Joseph FourierLa Tronche CedexFrance
  2. 2.LMC-IMAGGrenoble CedexFrance

Personalised recommendations