Paired Dictionary Learning Based MR Image Reconstruction from Undersampled k-Space Data

In this paper, a novel magnetic resonance (MR) images reconstruction framework based on paired dictionary learning (PDL) is proposed by jointly training two dictionaries for both undersampled k-space data and fully sampled k-space data. We find an optimal sparse representation for each undersampled k-space patch of the input MR image, and then utilize these representation coeffificients and fully sampled k-space patch dictionary to reconstruct the MR image. Two undersampling schemes and different sampling rates are applied to verify the performance of the proposed method. Experiments on brain images data set show that the proposed PDL algorithm can achieve higher structural similarity measure (SSIM) and lower relative l
2
norm error (RLNE), meanwhile, it is superior to classical compressed sensing MRI (CS-MRI) methods on suppressing image artifacts and retaining image edge details.