BM3D-AMP-MRI Project Page Home
Denoising
AMP for MRI reconstruction: BM3D-AMP-MRI
E. M. Eksioglu and A. K. Tanc, Denoising AMP for MRI
reconstruction: BM3D-AMP-MRI, SIAM Journal of Imaging Sciences,
vol. 11, no. 3, pp. 2090-2109, September 2018. [pdf]
MATLAB
code to realize the BM3D-AMP-MRI algorithm:
BM3D_AMP_MRI.zip contains the functions and sample
data necessary for demonstrating the BM3D-AMP-MRI algorithm for MRI
reconstruction. The zip also contains "bm3d_thr_color.mexw64"
and "bm3d_thr_color.mexmaci64" taken from the BM3D-toolbox
(http://www.cs.tut.fi/~foi/GCF-BM3D). These files realize the BM3D denoising as utilized in this package for 64-bit Windows
and Mac platforms, respectively.
Abstract:
There is a
recurrent idea being promoted in the recent literature on iterative solvers for
imaging problems, the idea being the use of an actual denoising
step in each iteration. We give a brief review of some algorithms from the
literature which utilize this idea, and we broadly label these algorithms as
Iterative Denoising Regularization (IDR) algorithms.
We extend the Denoising Approximate Message Passing
(D-AMP) algorithm from this list to the magnetic resonance imaging (MRI)
reconstruction problem. We utilize Block Matching 3D (BM3D) as the denoiser of choice for the introduced MRI reconstruction
algorithm. The application of the denoiser for complex-valued
data necessitates a special handling of the denoiser.
The use of the adaptive and image-dependent BM3D image model prior together
with D-AMP results in highly competitive MRI reconstruction performance.
Keywords:
image
reconstruction, magnetic resonance, message passing, block matching, compressed
sensing, denoising
Results from the paper:
