Skip to content
Preprint

Physics-informed denoising method for image reconstruction in quantitative low-field MRI

Sep 2026 · 0 citations · 34 references
Engineering

TL;DR

The proposed modular unrolled end-to-end deep learning method and its underlying method offer an efficient and flexible solution to denoise low-field MR data and make quantitative low-field MRI a feasible diagnostic tool for clinical applications.

Abstract

Low-field magnetic resonance imaging (MRI) is becoming increasingly important for medical imaging because it can reduce healthcare costs while ensuring high diagnostic output. Nevertheless, quantitative imaging in low-field MRI faces challenges, such as low signal-to-noise ratio and long scan durations. Deep learning approaches have been proposed for image reconstruction to overcome these challenges. Still, deep learning often requires large high-quality training datasets which are usually not available for low-field applications. Here we propose a modular unrolled end-to-end deep learning method for the denoised reconstruction of quantitative parameter maps directly from k-space data for low-field MRI. It consists of three sub-networks that are iteratively applied. They are used for the regularization of the quantitative parameter estimation, as well as for the signal estimation that is based on simulated signal curves. It generalises well and can be applied to different field strengths and even different quantitative MR sequences without the need for new training data. We applied the presented method to noisy data of knees acquired at 0.55 T for the reconstruction of $T_2$-maps and compared it to other classical and deep learning methods. We also applied the proposed approach to $T_1$-mapping of knees at 72 mT and $T_2$-mapping of brains at 0.6 T. The presented approach outperforms the other reconstruction methods with a median difference below 4 ms to the ground truth $T_2$-map. Even though the network was trained with $T_2$-maps acquired at 0.55 T, it successfully denoised data acquired at different field strengths, sequences, and of different anatomies. As a result, the proposed network and its underlying method offer an efficient and flexible solution to denoise low-field MR data and make quantitative low-field MRI a feasible diagnostic tool for clinical applications.

View source

Similar papers

Deep Learning-Based Denoising Techniques for Low-Field Knee MRI

Self-supervised methods showed superior performance over supervised and classical methods for low-field knee MR images, and validation in a larger dataset of knee at 0.55T is needed to further support this conclusion.

José Ignacio Menéndez Olave · 0 citations
Open access Oct 2026

Deep Learning-Based Enhancement of Low-Field MRI Using CNN-GAN for High-Quality Image Reconstruction

Magnetic Resonance Imaging (MRI) is one of the most common non-invasive imaging modalities with the capacity to visualize internal human anatomical structures such as soft tissues and organs with high resolution. High-field MRI (i.e., 1.5 T and above) provides better image quality, but its high cost and expensive infra...

K. S. Deepashri, H. Vinutha · 0 citations
2026

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

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 i...

Yutao Hu, Qi Liu, Tao Zhou et al. · 1 citation
Open access Oct 2026

Enhanced Parallel MRI Reconstruction Using PCA-Based Machine Learning Denoising

By combining global sparsity constraints (CS) with local low-rank learning (PCA), the method provides a robust and efficient solution for noise-resilient accelerated MRI reconstruction, with strong potential for practical and clinical applications.

B. Bao, Hung Dang Phan, Quang-Huy Tran et al. · 0 citations
Aug 2026

Deep learning-based image domain reconstruction of undersampled low-field brain MRI: A comparative benchmark study of U-Net architectures.

A comprehensive comparative evaluation of six U-Net variants, including U-Net, Attention U-Net, Residual U-Net, Recurrent-Residual (R2) U-Net, Residual-Attention U-Net (RAU-Net), and U-Net++, for image domain reconstruction of low-field MRI data from the M4RAW dataset is presented.

Akif Ahmed Nasif Purno, K. M. T. K. Siddiki, S. M. Chapal Hossain · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.