Advancing low-field MRI with a universal denoising imaging transformer: Towards fast and high-quality imaging

TL;DR

This paper introduces ImT-MRD, a universal complex-valued imaging transformer that significantly improves low-field MRI denoising, enabling faster scans and higher image quality across diverse clinical settings.

Contribution

The study presents a novel complex-valued transformer model trained on extensive clinical MRI data, offering universal denoising capabilities for low-field MRI systems.

Findings

Outperforms multiple-repetition averaging in image quality.

Reduces scan time by enabling fewer repetitions.

Provides high-quality denoising suitable for various MRI applications.

Abstract

Recent developments in low-field (LF) magnetic resonance imaging (MRI) systems present remarkable opportunities for affordable and widespread MRI access. A robust denoising method to overcome the intrinsic low signal-noise-ratio (SNR) barrier is critical to the success of LF MRI. However, current data-driven MRI denoising methods predominantly handle magnitude images and rely on customized models with constrained data diversity and quantity, which exhibit limited generalizability in clinical applications across diverse MRI systems, pulse sequences, and organs. In this study, we present ImT-MRD: a complex-valued imaging transformer trained on a vast number of clinical MRI scans aiming at universal MR denoising at LF systems. Compared with averaging multiple-repeated scans for higher image SNR, the model obtains better image quality from fewer repetitions, demonstrating its capability for accelerating scans under various clinical settings. Moreover, with its complex-valued image input, the model can denoise intermediate results before advanced post-processing and prepare high-quality data for further MRI research. By delivering universal and accurate denoising across clinical and research tasks, our model holds great promise to expedite the evolution of LF MRI for accessible and equal biomedical applications.