A Weighted two-level Bregman method with dictionary updating for nonconvex MR image reconstruction

作者：Liu Qiegen; Peng Xi; Liu Jianbo; Yang Dingcheng; Liang Dong^*

来源：International Journal of Biomedical Imaging, 2014, 2014: 1-23.

DOI：10.1155/2014/128596

• Acceleration factors
• Alternating direction methods
• Bregman iteration
• Dictionary learning
• Nonconvex optimization
• Number of iterations
• Numerical algorithms
• Sampling trajectories

Nonconvex optimization has shown that it needs substantially fewer measurements than lminimization for exact recovery under fixed transform/overcomplete dictionary. In this work, two efficient numerical algorithms which are unified by the method named weighted two-level Bregman method with dictionary updating (WTBMDU) are proposed for solving loptimization under the dictionary learning model and subjecting the fidelity to the partial measurements. By incorporating the iteratively reweighted norm into the two-level Bregman iteration method with dictionary updating scheme (TBMDU), the modified alternating direction method (ADM) solves the model of pursuing the approximated lnorm penalty efficiently. Specifically, the algorithms converge after a relatively small number of iterations, under the formulation of iteratively reweighted land lminimization. Experimental results on MR image simulations and real MR data, under a variety of sampling trajectories and acceleration factors, consistently demonstrate that the proposed method can efficiently reconstruct MR images from highly undersampled k-space data and presents advantages over the current state-of-the-art reconstruction approaches, in terms of higher PSNR and lower HFEN values.

• 出版日期2014