Classification of magnetic resonance images by using genetic algorithms


Dokur Z. , OLMEZ T. , YAZGAN E.

International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society, Illinois, United States Of America, 30 October - 02 November 1997, vol.19, pp.1391-1393 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 19
  • City: Illinois
  • Country: United States Of America
  • Page Numbers: pp.1391-1393

Abstract

A neural network trained by the genetic algorithms (GANN) is presented. Each neuron of the network forms a closed region in the input space. The closed regions which are formed by the neurons overlap each other, like STAR Genetic algorithms are used to improve the classification performances of the magnetic resonance (MR) images with minimized number of neurons. GANN is examined comparatively with multilayer perceptron (MLP), and restricted coulomb energy (RCE). It is observed that GANN gives the best classification performance with less number of neurons after a short training time.