Fast iterative contourlet thresholding for compressed sensing MRI

Proposed is the use of the contourlet as a sparse transform which is combined with the fast iterative shrinkage/threshold algorithm (FISTA) for compressed sensing magnetic resonance imaging reconstruction. The proposed method not only inherits the simplicity and effectiveness of the original FISTA but also has the sparse curve representation ability of the contourlet. Simulation results validate the superior performance of the proposed method in terms of reconstruction accuracy and computation time.