A Neuro-Fuzzy Image Analysis System for Biomedical Imaging Applications

  • L. Patino
  • M. Razaz


Intelligent image analysis is becoming increasingly important in biological and medical imaging applications. We present here an adaptable and intelligent image analysis system based on a combination of neural networks and fuzzy logic. The system has been applied successfully for diagnostic application such as recognition of the left ventricle in blood pool myocardial Single Photon Emission Computed Tomography (SPECT) images. We briefly discuss this system and present typical results from the application to SPECT images.


Membership Function Fuzzy Logic Adaptive Resonance Theory Recognition Procedure Gate Blood Pool 
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]
    Porenta G. et aI., “Evaluation of a neural network classifier for PET scans of normal and Alzheimer s disease subjects”, Journal of Nuclear Medicine, vol. 33, pp. 1459–1467, 1992.Google Scholar
  2. [2]
    Kippenhan J. S. et al., “Neural-network classification of normal and Alzheimer s disease subjects using high-resolution and low resolution PET cameras” Journal of Nuclear Medicine, vol. 35, pp. 7–15, 1993.Google Scholar
  3. [3]
    Tourassi G. D., Floyd C. E. Jr., “Lesion size quantification in SPECT using an artificial neural network classification approach”, Computers and Biomedical Research, vol. 28, pp. 257–270, 1995.CrossRefGoogle Scholar
  4. [4]
    Yan Z., Hong Y., “Computerized tumor boundary detection using a Hopfield neural network”, IEEE Transactions on Medical Imaging, vol. 16, pp. 55–67, 1997.Google Scholar
  5. [5]
    Teodorescu H. N., Kandel A., Jain L. C., “Fuzzy and Neuro-Fuzzy Systems in Medicine”, CRC Press, pp. 3–16, 1999.Google Scholar
  6. [6]
    Aurengo A., “L′intelligence artificielle en imagerie médicale: pourquoi le my the tarde-t-il it à dévenir réalité ?”, Médecine Nucléaire Imagérie FonctionneUe et Métabolique, pp. 53–55, 1997.Google Scholar
  7. [7]
    Patino L., Mertz L., Hirsh E., Constantinesco A., “Segmentation and contouring of blood pool myocardial SPECT images with wavelet-fuzzy constraints”, Proceedings of EUFIT, pp. 2086–2090 1996.Google Scholar
  8. [8]
    Patino L., Mertz L., Hirsh E., Dumitrescu B., Constantinesco A., “Contouring blood pool myocardial gated SPECT images with a neural network leader segmentation and a decision-based fuzzy logic”, Proceedings of FUZZ-IEEE, pp. 969–974, 1997.Google Scholar
  9. [9]
    Patino L., Constantinesco A., Hirsh E., “Contouring blood pool myocardial gated SPECT images with a sequence of three techniques based on wavelets, neural networks, and fuzzy logic”, CRC Press, pp. 95–136, 1999.Google Scholar
  10. [10]
    Carpenter G. A., Grossberg S., “The ART of adaptive pattern recognition by a self-organizing neural network” Computer, vol. 21, pp. 77–88, 1988.CrossRefGoogle Scholar
  11. [11]
    Chin B. B., “Right and left ventricular volume and ejection fraction by tomographic gated blood pool scintigraphy”, Journal of Nuclear Medecine, vol. 38, pp. 942–948, 1997.Google Scholar
  12. [12]
    Razaz M., Hagyard D.M.P., Lee R.A., “A Segmentation Methodology for Real 3D Images”, Non-linear Model Based Image Analysis, pp. 269–276 1998.Google Scholar
  13. [13]
    Bersini H., Gorrini V., “FUNNY (FUzzY or Neural Net) methods for adaptive process control”, Proceedings of EUFIT, pp. 55–61, 1993.Google Scholar
  14. [14]
    Razaz M., Hagyard D.M.P., “Morphological Segmentation of Multidimensional Images”, Image Processing, vol. 2, pp. 294–312, 2000.Google Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • L. Patino
  • M. Razaz
    • 1
  1. 1.Royal Society Wolfson Bioinformatics LaboratoryUniversity of East AngliaNorwichEngland

Personalised recommendations