MR image resolution enhancement using a multi-layer neural network

Author

Yan, Hong ; Mao, Jintong ; Chen, Benjamin

Author_Institution

Sch. of Electr. Eng., Sydney Univ., NSW, Australia

fYear

1992

fDate

14-17 Jun 1992

Firstpage

624

Lastpage

632

Abstract

A magnetic resonance image may contain truncation artifacts if there are not enough high-frequency data when the conventional Fourier transform method is used for reconstruction. The authors propose a method for reducing the artifacts using a multilayer neural network. The network consists of one linear output layer and at least one nonlinear hidden layer. In this method the missing high-frequency components are predicted based on known low-frequency components and are used to improve the resolution of the image. The method is tested with simulated data with good results

Keywords

biomedical NMR; medical image processing; neural nets; Fourier transform method; high-frequency components; linear output layer; low-frequency components; magnetic resonance image; multilayer neural network; nonlinear hidden layer; resolution enhancement; truncation artifacts; Fourier transforms; Frequency; Image coding; Image reconstruction; Image resolution; Multi-layer neural network; Neural networks; Predictive models; Signal resolution; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 1992. Proceedings., Fifth Annual IEEE Symposium on

Conference_Location

Durham, NC

Print_ISBN

0-8186-2742-5

Type

conf

DOI

10.1109/CBMS.1992.245027

Filename

245027