LSST: Learned Single-Shot Trajectory and Reconstruction Network for MR Imaging

TL;DR

This paper introduces a learned single-shot MR imaging method that optimizes k-space trajectories within a physics-constrained end-to-end framework, significantly improving image quality and speed in fast MRI acquisitions.

Contribution

It proposes a novel trajectory optimization approach integrated into a learning framework, enhancing single-shot MR image reconstruction under physical constraints.

Findings

Improved image sharpness and quality in reconstructed MR images.

Effective acceleration of MRI acquisition with fewer samples.

Radiologist evaluation shows superior reconstruction quality.

Abstract

Single-shot magnetic resonance (MR) imaging acquires the entire k-space data in a single shot and it has various applications in whole-body imaging. However, the long acquisition time for the entire k-space in single-shot fast spin echo (SSFSE) MR imaging poses a challenge, as it introduces T2-blur in the acquired images. This study aims to enhance the reconstruction quality of SSFSE MR images by (a) optimizing the trajectory for measuring the k-space, (b) acquiring fewer samples to speed up the acquisition process, and (c) reducing the impact of T2-blur. The proposed method adheres to physics constraints due to maximum gradient strength and slew-rate available while optimizing the trajectory within an end-to-end learning framework. Experiments were conducted on publicly available fastMRI multichannel dataset with 8-fold and 16-fold acceleration factors. An experienced radiologist's evaluation on a five-point Likert scale indicates improvements in the reconstruction quality as the ACL fibers are sharper than comparative methods.