Denoising Generalized Expectation-Consistent Approximation for MR Image Recovery
This work addresses a specific bottleneck in plug-and-play methods for medical imaging, offering incremental improvements for MR image recovery.
The authors tackled the problem of inaccurate denoiser input error in plug-and-play methods for inverse problems by proposing a new algorithm based on generalized expectation-consistent approximation and a tailored deep neural network denoiser for magnetic resonance image recovery, demonstrating advantages over existing methods.
To solve inverse problems, plug-and-play (PnP) methods replace the proximal step in a convex optimization algorithm with a call to an application-specific denoiser, often implemented using a deep neural network (DNN). Although such methods yield accurate solutions, they can be improved. For example, denoisers are usually designed/trained to remove white Gaussian noise, but the denoiser input error in PnP algorithms is usually far from white or Gaussian. Approximate message passing (AMP) methods provide white and Gaussian denoiser input error, but only when the forward operator is sufficiently random. In this work, for Fourier-based forward operators, we propose a PnP algorithm based on generalized expectation-consistent (GEC) approximation -- a close cousin of AMP -- that offers predictable error statistics at each iteration, as well as a new DNN denoiser that leverages those statistics. We apply our approach to magnetic resonance (MR) image recovery and demonstrate its advantages over existing PnP and AMP methods.