Learning Optimal K-space Acquisition and Reconstruction using Physics-Informed Neural Networks

TL;DR

This paper introduces a physics-informed neural network framework that optimizes k-space sampling trajectories as an ODE problem, leading to improved MRI image reconstruction efficiency and quality over traditional methods.

Contribution

It presents a novel neural ODE-based approach to learn and optimize k-space sampling trajectories considering MRI physics, enabling joint trajectory and image reconstruction learning.

Findings

Generated better image quality than conventional schemes

Effective across different in-vivo datasets and sequences

Improved MRI acceleration performance

Abstract

The inherent slow imaging speed of Magnetic Resonance Image (MRI) has spurred the development of various acceleration methods, typically through heuristically undersampling the MRI measurement domain known as k-space. Recently, deep neural networks have been applied to reconstruct undersampled k-space data and have shown improved reconstruction performance. While most of these methods focus on designing novel reconstruction networks or new training strategies for a given undersampling pattern, e.g., Cartesian undersampling or Non-Cartesian sampling, to date, there is limited research aiming to learn and optimize k-space sampling strategies using deep neural networks. This work proposes a novel optimization framework to learn k-space sampling trajectories by considering it as an Ordinary Differential Equation (ODE) problem that can be solved using neural ODE. In particular, the sampling of k-space data is framed as a dynamic system, in which neural ODE is formulated to approximate the system with additional constraints on MRI physics. In addition, we have also demonstrated that trajectory optimization and image reconstruction can be learned collaboratively for improved imaging efficiency and reconstruction performance. Experiments were conducted on different in-vivo datasets (e.g., brain and knee images) acquired with different sequences. Initial results have shown that our proposed method can generate better image quality in accelerated MRI than conventional undersampling schemes in Cartesian and Non-Cartesian acquisitions.