Low Latency and Generalizable Dynamic MRI via L+S Alternating GD and Minimization

TL;DR

This paper introduces a novel MRI reconstruction method that achieves fast, accurate, and low-latency results across various dynamic MRI applications without the need for problem-specific parameter tuning, emphasizing its generalizability.

Contribution

The work develops a new algorithm based on L+S alternating gradient descent and minimization that is simple, fast, and generalizable across multiple MRI sampling schemes and rates.

Findings

Achieves accurate MRI reconstruction without parameter tuning.

Works across various sampling schemes and rates.

Demonstrates low-latency performance.

Abstract

In this work, we develop novel MRI reconstruction approaches that are accurate, fast and low-latency for a large number of dynamic MRI applications, sampling schemes and sampling rates; without any problem-specific parameter tuning. We refer to this property of a single algorithm, without parameter tuning, being accurate and fast for many settings as generalizability. Generalizability is possible only for simple (few parameter) models such as low-rank (LR) or LR plus sparse (L plus S), and for simple few parameter algorithms based on these models, which is what we develop and evaluate in this work.