Abstract
A Quantiser Neural Network (QNN) is proposed for the segmentation of MR and CT images. Elements of a feature vector are formed by image intensities at one neighbourhood of the pixel of interest. QNN is a novel neural network structure, which is trained by genetic algorithms. Each node in the first layer of the QNN forms a hyperplane (HP) in the input space. There is a constraint on the HPs in a QNN. The HP is represented by only one parameter in d-dimensional input space. Genetic algorithms are used to find the optimum values of the parameters which represent these nodes. The novel neural network is comparatively examined with a multilayer perceptron and a Kohonen network for the segmentation of MR and CT head images. It is observed that the QNN gives the best classification performance with fewer nodes after a short training time.
Similar content being viewed by others
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dokur, Z., Ölmez, T. Segmentation of MR and CT Images by Using a Quantiser Neural Network . Neur. Comp. App. 11, 168–177 (2003). https://doi.org/10.1007/s00521-003-0355-2
Issue Date:
DOI: https://doi.org/10.1007/s00521-003-0355-2