Abstract
A neural network classifier for detecting vascular structures in angiograms is developed. The classifier consists of a Hopfield network applied to a square window in which the centre pixel is classified from binary information within the window. Tests are performed using a binary test image corrupted by inverting a percentage of the image pixels. The resulting noisy images simulate the output of a detector using a simple threshold derived from local image statistics. The factors affecting the size of window and the choice of stored patterns are discussed. The results are compared with those obtained from a multi-layer perceptron using a similar approach. The Hopfield network is found to be effective at rejecting the high levels of noise that would result from low-contrast source imagery. Another important feature is that the processed image retains an accurate representation of blood vessel diameter.
Similar content being viewed by others
References
Hertz, J., Krogh, A., andPalmer, R. G. (1991): ‘Introduction to the theory of neural computation’, (Addison-Wesley, California)
Kottke, D. andSun, Y. (1990): ‘Segmentation of coronary arteriograms by iterative ternary classification’,IEEE Trans. Biomed. Eng.,37, pp. 778–785
Nekovei, R. andSun, Y. (1995): ‘Back-propagation network and its configuration for blood vessel detection in angiograms’,IEEE Trans. Neural Netw.,6, pp. 64–72
Nguyen, T. V. andSklansky, J. (1986): ‘Computing the skeleton of coronary arteries in cineangiograms’,Comput. and Biomed. Res.’,19, pp. 428–444
Pappas, T. andLim J. (1988): ‘A new method for estimation of coronary artery dimensions in angiograms’,IEEE Trans. Acoust., Speech, and Sig. Proc.,36, pp. 1501–1513
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Karapataki, M., De Wilde, P. Hopfield network applied to blood vessel detection in angiograms. Med. Biol. Eng. Comput. 35, 428–430 (1997). https://doi.org/10.1007/BF02534103
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02534103