It is challenging to save acquisition time and reconstruct a medical magnetic resonance (MR) image with important details and\nfeatures fromits compressive measurements. In this paper, a novel method is proposed for longitudinal compressive sensing (LCS)\nMR imaging (MRI), where the similarity between reference and acquired image is combined with joint sparsifying transform.\nFurthermore, the joint sparsifying transform with the wavelet and the Contourlet can efficiently represent both isotropic and\nanisotropic features and the objective function is solved by extended smooth-based monotone version of the fast iterative shrinkage\nthresholding algorithm (SFISTA). The experiment results demonstrate that the existing regularization model obtains better\nperformance with less acquisition time and recovers both edges and fine details of MR images, much better than the existing\nregularization model based on the similarity and the wavelet transform for LCS-MRI.
Loading....