Multiple regularization based MRI reconstruction

Abstract

This paper introduces an efficient algorithm for magnetic resonance (MR) image reconstruction. The proposed method minimizes a linear combination of nonlocal total variation, least square data fitting term and wavelet sparsity terms to reconstruct the MR image from undersampled k-space data. The nonlocal total variation and wavelet sparsity are taken as the hybrid L1-regularization functional and solving it using a Split Bregman algorithm. The proposed algorithm is compared with previous methods in terms of the reconstruction accuracy and computational complexity. The comparison results demonstrate the superiority of the proposed algorithm for compressed MR image reconstruction.