Parameter estimation and NMR image segmentation

Author

Liang, Z. ; MacFall, J.

Author_Institution

Dept. of Radiol., State Univ. of New York, Stony Brook, NY, USA

fYear

1992

fDate

25-31 Oct 1992

Firstpage

1322

Abstract

A statistical method is proposed to classify tissue types and to segment the corresponding tissue regions from relaxation time T₁, T₂, and proton density N_H weighted nuclear magnetic resonance (NMR) images. The method assumes that the distribution of image intensities associated with each tissue type can be expressed as a multivariate likelihood function of three variables (T ₁, T₂, N_H) at each location within that tissue region. The method is tested by a set of T₁, T₂, and N_H weighted images of the brain acquired with a 1.5-T whole body scanner. The number of tissue types and the parameters of these tissue types are satisfactorily estimated. The regions of different tissue types are successfully segmented

Keywords

biomedical NMR; image segmentation; medical image processing; parameter estimation; 1.5 T; NMR image segmentation; T₁; T₂; brain images; image intensities distribution; medical diagnostic imaging; multivariate likelihood function; proton density; statistical method; tissue region; tissue types classification; weighted nuclear magnetic resonance images; whole body scanner; Image segmentation; Markov random fields; Maximum likelihood estimation; Medical treatment; Nuclear magnetic resonance; Parameter estimation; Protons; Radiology; Three dimensional displays; X-ray imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Nuclear Science Symposium and Medical Imaging Conference, 1992., Conference Record of the 1992 IEEE

Conference_Location

Orlando, FL

Print_ISBN

0-7803-0884-0

Type

conf

DOI

10.1109/NSSMIC.1992.301525

Filename

301525