Title :
Classification of MR and CT images using genetic algorithms
Author :
Dokur, Zumray ; Olmez, Tamer ; Yazgan, Ertugrul
Author_Institution :
Dept. of Electron. & Commun. Eng., Istanbul Tech. Univ., Turkey
fDate :
29 Oct-1 Nov 1998
Abstract :
A modified restricted Coulomb energy (MoRCE) network trained by the genetic algorithm 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) and computer tomography (CT) images with minimized number of neurons. MoRCE is examined comparatively with multilayer perceptron (MLP), and restricted Coulomb energy (RCE). It is observed that MoRCE gives the best classification performance with less number of neurons after a short training time
Keywords :
biomedical MRI; computerised tomography; genetic algorithms; image classification; learning (artificial intelligence); medical expert systems; medical image processing; neural nets; MRI images; closed region; computer tomography images; genetic algorithm; hyperspheres; image classification performance; input space; minimized number of neurons; modified restricted Coulomb energy network; multilayer perceptron comparison; short training time; supervised learning; Chromium; Computed tomography; Electronic mail; Genetic algorithms; Genetic engineering; Magnetic multilayers; Magnetic resonance; Neural networks; Neurons; Power engineering and energy;
Conference_Titel :
Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE
Conference_Location :
Hong Kong
Print_ISBN :
0-7803-5164-9
DOI :
10.1109/IEMBS.1998.747149
