Medical image reconstruction based on Bayesian compressed sensing

Author

Li, Yu-hong ; Wang, De-Feng ; Lui, L.M. ; Ahuja, A.T. ; Heng, Pheng Ann

Author_Institution

Shenzhen Inst. of Adv. Technol., Chinese Acad. of Sci., Shenzhen, China

Volume

4

fYear

2011

fDate

10-13 July 2011

Firstpage

1819

Lastpage

1824

Abstract

A medical image reconstruction method based on sparse Bayesian compressed sensing is presented, and the method employs a hierarchical model of the Laplace prior to model the sparse wavelet coefficients and unknown images. The experiments are designed to compare the Bayesian Compressed Sensing (BCS) method with the Basis Pursuit (BP) algorithm and the Orthogonal Matching Pursuit (OMP) algorithm. The results imply that the presented algorithm exceeds the greedy algorithm and the linear programming such as BP and OMP etc.

Keywords

belief networks; greedy algorithms; image reconstruction; linear programming; medical image processing; BCS; OMP; basis pursuit algorithm; greedy algorithm; linear programming; medical image reconstruction method; orthogonal matching pursuit algorithm; sparse Bayesian compressed sensing; sparse wavelet coefficients; Bayesian methods; Biomedical imaging; Compressed sensing; Image reconstruction; Matching pursuit algorithms; Measurement uncertainty; Noise; Compressed sensing; Gaussian distribution; Image reconstruction; Laplace prior; Marginal likelihood; Sparse Bayesian;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2011 International Conference on

Conference_Location

Guilin

ISSN

2160-133X

Print_ISBN

978-1-4577-0305-8

Type

conf

DOI

10.1109/ICMLC.2011.6016990

Filename

6016990