An Approximate Message Passing Algorithm for Rapid Parameter-Free Compressed Sensing MRI
share
For certain sensing matrices, the Approximate Message Passing (AMP) algorithm and more recent Vector Approximate Message Passing (VAMP) algorithm efficiently reconstruct undersampled signals. However, in Magnetic Resonance Imaging (MRI), where Fourier coefficients of a natural image are sampled with variable density, AMP and VAMP encounter convergence problems. In response we present a new approximate message passing algorithm constructed specifically for variable density partial Fourier sensing matrices with a sparse model on wavelet coefficients. For the first time in this setting a state evolution has been observed. A practical advantage of state evolution is that Stein's Unbiased Risk Estimate (SURE) can be effectively implemented, yielding an algorithm with no free parameters. We empirically evaluate the effectiveness of the parameter-free algorithm on simulated data and find that it converges over 5x faster and to a lower mean-squared error solution than Fast Iterative Shrinkage-Thresholding (FISTA).
READ FULL TEXT
