Skip to main navigation Skip to search Skip to main content

Measurement-Consistent Low-Field MRI Enhancement via k-Space Noise Modeling

  • Yutao Hu
  • , Qi Liu
  • , Tao Zhou
  • , Ziru Li
  • , Ping Liang
  • , Jichang Zhang*
  • , Rongsheng Lu
  • , Xiaojian Lou
  • , Jianjun Zheng
  • , Jian Yang
  • , Yang Chen*
  • *Corresponding author for this work
  • Southeast University, Nanjing
  • Xingaoyi Medical Equipment Company Ltd.
  • The University of Nottingham Ningbo China
  • Ningbo University
  • Wenzhou Medical University
  • Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

Abstract

Low-field magnetic resonance imaging (MRI) has gained increasing attention as a cost-effective and portable alternative to high-field MRI, particularly in resource-limited conditions. However, its inherently low magnetic field strength leads to reduced signal intensity and a low signal-to-noise ratio (SNR), resulting in severe image degradation. To address these challenges, this work proposes a framework for low-field MRI enhancement that jointly considers data synthesis, model design, and performance evaluation in a measurement-consistent manner. In particular, we first propose a realistic low-field MRI synthesis strategy that estimates noise statistics from k-space measurements and injects noise into high-field k-space. By separately modeling the real and imaginary components, the proposed pipeline enables more faithful generation of paired low- and high-field MRI data for supervised learning. Second, we establish a unified benchmark that supports reliable performance evaluation, which includes a wide range of representative restoration methods, together with a real-world dataset consisting of low-field MRI scans and corresponding high-field References acquired from the same subjects. Finally, we develop the noise-aware guidance network (NAGNet), which incorporates an adaptive noise awareness (ANA) branch to explicitly predict spatially variant noise and guide the denoising process in a plug-and-play manner. Extensive experiments demonstrate that NAGNet achieves state-of-the-art performance, which exhibits strong generalization across different datasets and various magnetic field strengths. Code and datasets are available at https://github.com/6767lq/NAGNET

Original languageEnglish
Article number4014316
JournalIEEE Transactions on Instrumentation and Measurement
Volume75
DOIs
Publication statusPublished - 2026
Externally publishedYes

Keywords

  • Image enhancement
  • low-field magnetic resonance imaging (MRI) image
  • noise estimation

Fingerprint

Dive into the research topics of 'Measurement-Consistent Low-Field MRI Enhancement via k-Space Noise Modeling'. Together they form a unique fingerprint.

Cite this