Neural networks for the segmentation of magnetic resonance images

  • Rachid Sammouda
  • Noboru Niki
  • Hiromu Nishitani
Session IA2b — Biomedical Imaging
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1024)


The segmentation of the images obtained from magnetic resonance imaging (MRI) is an important step in the visualization of soft tissues in the human body. In this preliminary study, we report an application of Hopfield neural network (HNN) for the multispectral unsupcrvised classification of head MR images. We formulate the classification problem as a minimization of an energy function constructed with two terms, the cost-term which is the sum of the squares errors, and the second term is a temporary noise added to the cost-term as an excitation to the network to escape from certain local minimums and be more close to the global minimum. We present here the segmentation result with two and three channels data obtained using the here described HNN approach. We compare these results to those corresponding to the same data obtained with the Boltzmann Machine (BM) approach.


Energy Function Segmentation Result Hopfield Neural Network Boltzmann Machine Channel Case 
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.
    Hopfield, J. J., “Neural networks and physical systems with emergent collective computational abilities,”in Proc. Nat. Acad. Sci., vol. 79, pp. 2554–2558, 1982Google Scholar
  2. 2.
    Jacobs, R. A., “Increased rates of convergence through learning rate adoption,” Neural Networks, vol. 1, pp. 295–307, 1988Google Scholar
  3. 3.
    Duda, R. O., and Hart, P. E., “Pattern Classification and Scene Analysis,” New York: Wiley, 1973Google Scholar
  4. 4.
    Geman, S., and Hwang, C. R., “Diffusions for global optimization,” SIAM J. of Control and Optimization, vol. 24, no. 5, pp. 1031–1043, 1986Google Scholar
  5. 5.
    Amartur, S. C., Piraino, D., and Takefuji, Y. “Optimization Neural Networks for the Segmentation of Magnetic Resonance Images,” IEEE Transactions on Medical Imaging, vol. 11, no. 2, pp. 215–220, 1992.Google Scholar
  6. 6.
    E. Aart and J. Korst, “Simulated Annealing and Boltzmann Machines” New York: Wiley, 1989.Google Scholar
  7. 7.
    G.E. Hinton, R.J. Sejnowski and D. H. Ackley, “Boltzmann machines: Constraints satisfaction networks that learn”, Tech. Rep. CMU-CS-84-119 Carnegie-Mellon Univ. Dept. of Computer Science, 1984.Google Scholar
  8. 8.
    S. Kirkpatrik, C.D. Gelatt and M.P. Vecchi, “Optimization by simulated annealing” Science, vol. 220, pp. 671–680, 1983.Google Scholar
  9. 9.
    R. Samouda, N. Niki, “Optimization Neural Networks for the Segmentation of Brain MRI Images” CAR'95, Berlin, pp. 171–176, 1995.Google Scholar
  10. 10.
    R. Sammouda, N. Niki, “Multichannel Segmentation of Magnetic Resonance Cerebral Images Based on Neural Networks”, ICIP, Washington, October 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Rachid Sammouda
    • 1
  • Noboru Niki
    • 1
  • Hiromu Nishitani
    • 1
    • 2
  1. 1.Dept. of Information ScienceUniv. of TokushimaJapan
  2. 2.Medical SchoolUniv. of TokushimaJapan

Personalised recommendations