Off-the-Grid Compressed Sensing MRI Reconstruction via Data Driven Tight Frame Regularization

Recently, the finite-rate-of-innovation (FRI) based continuous domain restoration is emerging as an alternative to the conventional on-the-grid compressed sensing (CS) MRI restoration due to its ability to alleviate the basis mismatch between the true support of the shape in the continuous domain and the discrete grid. In this paper, we propose a new off-the-grid approach for the CS-MRI reconstruction. Following the recent works on two dimensional FRI, we assume that the discontinuities/edges of the image are localized in the zero level set of a band-limited periodic function. This assumption induces the linear dependencies among the Fourier samples of the gradient of the image, which leads to a low rank two-fold Hankel matrix. We further observe that the singular value decomposition of a low rank Hankel matrix corresponds to an adaptive tight frame system which can represent the image with a few nonzero canonical coefficients. Based on this observation, we propose a data driven tight frame based off-the-grid CS-MRI reconstruction model for the MR image reconstruction. To solve the nonconvex and nonsmooth model, a proximal alternating minimization algorithm with a guaranteed global convergence is adopted. Finally, the numerical experiments show that our proposed data driven tight frame based approach outperforms the existing approaches.