Segmentation of ultrasound images by using quantizer neural network

Author

Dokur, Zümray ; Kurnaz, Mehmet Nadir ; Ölmez, Tamer

Author_Institution

Dept. of Electron. & Commun. Eng., Istanbul Tech. Univ., Turkey

fYear

2002

fDate

2002

Firstpage

257

Lastpage

261

Abstract

A quantizer neural network (QNN) is proposed for the segmentation of ultrasound images. The elements of the feature vectors are formed by the image intensities within the neighborhood of the pixel of interest. The QNN is a hybrid neural network structure, which is trained by genetic algorithms. The genetic algorithms are used to find optimum values for the weights of the nodes. The hybrid neural network is compared with a multilayer perceptron (MLP) for the segmentation of ultrasound images.

Keywords

genetic algorithms; image segmentation; learning (artificial intelligence); neural nets; ultrasonic imaging; US image segmentation; genetic algorithms; hybrid neural network structure; image intensities; multilayer perceptron; neural net training; node weight optimum values; quantizer neural network; the feature vectors; Artificial neural networks; Biomedical imaging; Electronic mail; Genetic algorithms; Image segmentation; Multi-layer neural network; Multilayer perceptrons; Neural networks; Pixel; Ultrasonic imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 2002. (CBMS 2002). Proceedings of the 15th IEEE Symposium on

ISSN

1063-7125

Print_ISBN

0-7695-1614-9

Type

conf

DOI

10.1109/CBMS.2002.1011386

Filename

1011386