Tissue Mixture Characterization In The Presence of Mri Inhomogeneity by the Em Algorithm

Author

Liang, Z. ; Li, L. ; Eremina, D. ; Lu, H.

Author_Institution

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

Volume

2

fYear

2006

fDate

14-19 May 2006

Abstract

This paper presents a model-based approach to correct for both partial volume effect and inhomogeneity in segmenting tissue mixtures inside each voxel of magnetic resonance images. A maximum a posteriori probability (MAP) solution is sought. In calculating the solution, the well-known expectation maximization (EM) algorithm is employed. The models of data likelihood and Markov priors for tissue mixture and bias field in establishing this MAP-EM framework are described in details. A preliminary test is presented

Keywords

Markov processes; biological tissues; biomedical MRI; expectation-maximisation algorithm; image segmentation; medical image processing; MAP; MRI inhomogeneity; Markov priors; expectation maximization algorithm; magnetic resonance images; maximum a posteriori probability; segmenting tissue mixtures; tissue mixture characterization; Biomedical engineering; Computer science; Image segmentation; Magnetic resonance; Magnetic resonance imaging; Mathematics; Numerical models; Physics; Radiology; Random variables;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on

Conference_Location

Toulouse

ISSN

1520-6149

Print_ISBN

1-4244-0469-X

Type

conf

DOI

10.1109/ICASSP.2006.1660549

Filename

1660549