Autotuning Plug-and-Play Algorithms for MRI

12/01/2020
by   Saurav K. Shastri, et al.
0

For magnetic resonance imaging (MRI), recently proposed "plug-and-play" (PnP) image recovery algorithms have shown remarkable performance. These PnP algorithms are similar to traditional iterative algorithms like FISTA, ADMM, or primal-dual splitting (PDS), but differ in that the proximal update is replaced by a call to an application-specific image denoiser, such as BM3D or DnCNN. The fixed-points of PnP algorithms depend upon an algorithmic stepsize parameter, however, which must be tuned for optimal performance. In this work, we propose a fast and robust auto-tuning PnP-PDS algorithm that exploits knowledge of the measurement-noise variance that is available from a pre-scan in MRI. Experimental results show that our algorithm converges very close to genie-tuned performance, and does so significantly faster than existing autotuning approaches.

READ FULL TEXT
10/21/2020

MRI Image Recovery using Damped Denoising Vector AMP

Motivated by image recovery in magnetic resonance imaging (MRI), we prop...
12/20/2020

Iterative regularization methods for a discrete inverse problem in MRI

We propose and investigate efficient numerical methods for inverse probl...
06/09/2022

Denoising Generalized Expectation-Consistent Approximation for MRI Image Recovery

To solve inverse problems, plug-and-play (PnP) methods have been develop...
04/21/2022

Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction

Unrolled neural networks have enabled state-of-the-art reconstruction pe...
11/09/2021

Lymph Node Detection in T2 MRI with Transformers

Identification of lymph nodes (LN) in T2 Magnetic Resonance Imaging (MRI...
07/12/2019

Find It: A Novel Way to Learn Through Play

Autism Spectrum Disorder (ASD) is the area where many researches endurin...