A probabilistic neural network based image segmentation network for magnetic resonance images

Author

Morrison, Matthew ; Attikiouzel, Y.

Author_Institution

Centre for Intelligent Inf. Process. Syst., Univ. of Western Australia, Nedlands, WA, Australia

Volume

3

fYear

1992

fDate

7-11 Jun 1992

Firstpage

60

Abstract

A network structure for segmenting magnetic resonance medical images is proposed. The incorporation of a probabilistic neural network structure into the segmentation process allows decisions regarding the characterization of each pixel to be made in a probabilistic manner, thus reducing the effect of an incorrect decision early in the process on the final segmentation result. The probabilistic neural network facilitates the generation of likelihood estimates for use in an iterative segmentation process, which was shown to produce good segmentation results on real magnetic resonance images

Keywords

biomedical NMR; image segmentation; medical image processing; neural nets; probability; image segmentation network; iterative segmentation; likelihood estimate generation; magnetic resonance images; pixel characterization; probabilistic neural network; High-resolution imaging; Image analysis; Image segmentation; Intelligent systems; Iterative algorithms; Magnetic resonance; Magnetic resonance imaging; Muscles; Neural networks; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.227189

Filename

227189