Off-the-grid data-driven optimization of sampling schemes in MRI

TL;DR

This paper introduces a learning-based algorithm for designing efficient, physically plausible MRI sampling patterns that operate off-the-grid and incorporate arbitrary physical constraints, enhancing flexibility and scanner utilization.

Contribution

It presents a novel off-the-grid, constraint-aware learning algorithm for MRI sampling pattern optimization, surpassing existing methods in versatility.

Findings

Enables off-the-grid sampling pattern generation

Handles arbitrary physical constraints effectively

Improves MRI sampling efficiency

Abstract

We propose a novel learning based algorithm to generate efficient and physically plausible sampling patterns in MRI. This method has a few advantages compared to recent learning based approaches: i) it works off-the-grid and ii) allows to handle arbitrary physical constraints. These two features allow for much more versatility in the sampling patterns that can take advantage of all the degrees of freedom offered by an MRI scanner. The method consists in a high dimensional optimization of a cost function defined implicitly by an algorithm. We propose various numerical tools to address this numerical challenge.