Classification of tissues in MR images by using discrete cosine transform

Author

Dokur, Zümray ; Kumaz, M.N. ; Ölmez, Tamer

Author_Institution

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

Volume

2

fYear

2002

fDate

2002

Firstpage

1101

Abstract

In this study, the tissues in the magnetic resonance (MR) images are classified. Feature vectors are formed by the discrete cosine transform of pixel intensities in the region of interest. In this study, discrete cosine, and Fourier transforms are comparatively investigated for the segmentation. An incremental self-organized map (ISOM) is proposed as the classifier for the segmentation process.

Keywords

Fourier transforms; biological tissues; biomedical MRI; discrete cosine transforms; feature extraction; image classification; image segmentation; medical image processing; neural nets; vectors; MR images; discrete cosine transform; incremental neural network; magnetic resonance imaging; medical diagnostic imaging; physical process; pixel intensities; realistic classifiers; region of interest; subimages size; tissues classification; Artificial neural networks; Data mining; Discrete cosine transforms; Fourier transforms; Frequency; Image segmentation; Magnetic resonance; Pixel; Ultrasonic imaging; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society EMBS/BMES Conference, 2002. Proceedings of the Second Joint

ISSN

1094-687X

Print_ISBN

0-7803-7612-9

Type

conf

DOI

10.1109/IEMBS.2002.1106297

Filename

1106297