Advertisement

Neural Network Based Classification of Cell Images via Estimation of Fractal Dimensions

  • Changjing Shang
  • Craig Daly
  • John McGrath
  • John Barker
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)

Abstract

This paper1 presents a system for classifying cells in human resistance arteries via estimating and analysing fractal dimensions of normal and abnormal cell images. The use of fractal features helps characterise and differentiate between categories of cell images. The classification task is implemented using a multi-layer feedforward neural network, which maps estimated fractal feature patterns onto their underlying cell index. This system has been applied to a large database of images (which were taken from proximal and distal areas of subcutaneous resistance arteries, of patients suffering from critical limb ischaemia, by means of laser scanning confocal microscopy), with the overall classification rate reaching 90.5%.

Keywords

Fractal Dimension Cell Image Critical Limb Ischaemia Correct Classification Rate Cell Category 
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. [1]
    Mandelbrot BB. The fractal geometry of nature. San. Francisco: Freeman, 1982MATHGoogle Scholar
  2. [2]
    Keller J, Chen S, Crownover R. Texture description and segmentation through fractal geometry. Comp. Vision Graph, and Image Proc. 1989; 45:150–166CrossRefGoogle Scholar
  3. [3]
    Steve D, Hall P. Fractal analysis of surface roughness by using spatial data. J. R. Statist. Soc.B 1999; 61:1–27CrossRefGoogle Scholar
  4. [4]
    Wu CM, Chen YC. Texture features for classification of ultrasonic liver images. IEEE Trans. Medical Imaging 1992; 11:141–152CrossRefGoogle Scholar
  5. [5]
    Bishop CM. Neural networks for pattern recognition. Oxford University Press, Oxford, 1995Google Scholar
  6. [6]
    Jennings M, Graham J. A neural network approach to automatic chromosome classification. Phs. Med. Boil. 1993; 38:959–970CrossRefGoogle Scholar
  7. [7]
    Shang C, Brown KE. Principal feature based texture classification with neural networks. Pattern Recognition 1994; 27:675–687CrossRefGoogle Scholar
  8. [8]
    Rumelhant DE, Hinton GE, Williams RJ. Learning internal representations by error propagating. In: Parallel Distributed Processing. Rumelhant E, McClelland JL. (Eds.), MIT Press, 1986Google Scholar
  9. [9]
    Mulvang MJ. Vascular remodelling of resistance vessels: can we define this? J. Cardiovascular Research 1999; 41:9–13CrossRefGoogle Scholar
  10. [10]
    Daly CJ, Gordon JF, McGrath JC. The use of fluorescent nuclear dyes for the study of blood vessel structure and function: novel applications of existing techniques. J. Cardiovascular Research 1992; 29:41–48Google Scholar
  11. [11]
    Arribas SM, Gordon JF, Daly CJ, Dominiczak AF, McGrath JC. Confocal microscopic characterisation of a lesion in an acerebral vessel of the stroke-prone spontaneously hypertensive rat. Stroke 1996; 27:1118–1123CrossRefGoogle Scholar
  12. [12]
    Duda RO, Hart PE. Pattern classification and scene analysis. Jone Wiley and Sons, New York, 1993Google Scholar

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • Changjing Shang
    • 1
  • Craig Daly
    • 1
  • John McGrath
    • 1
  • John Barker
    • 2
  1. 1.Division of Neuroscience and Biomedical SystemsIBLS, University of GlasgowGlasgowUK
  2. 2.Department of Electronics and Electrical EngineeringUniversity of GlasgowGlasgowUK

Personalised recommendations