Title :
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
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;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2011 International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-1-4577-0305-8
DOI :
10.1109/ICMLC.2011.6016990
