Subject-Specific Low-Field MRI Synthesis via a Neural Operator

Ziqi Gao; Nicha Dvornek; Xiaoran Zhang; Gigi Galiana; Hemant Tagare; Todd Constable

eess.IVMar 26, 2026

Subject-Specific Low-Field MRI Synthesis via a Neural Operator

Authors: Ziqi Gao, Nicha Dvornek, Xiaoran Zhang, Gigi Galiana, Hemant Tagare, Todd Constable

Organizations: Departments of Biomedical Engineering, Yale University · Department of Radiology & Biomedical Imaging, Yale University

Abstract

Low-field (LF) magnetic resonance imaging (MRI) improves accessibility and reduces costs but generally has lower signal-to-noise ratios and degraded contrast compared to high field (HF) MRI, limiting its clinical utility. Simulating LF MRI from HF MRI enables virtual evaluation of novel imaging devices and development of LF algorithms. Existing low field simulators rely on noise injection and smoothing, which fail to capture the contrast degradation seen in LF acquisitions. To this end, we introduce an end-to-end LF-MRI synthesis framework that learns HF to LF image degradation directly from a small number of paired HF-LF MRIs. Specifically, we introduce a novel HF to LF coordinate-image decoupled neural operator (H2LO) to model the underlying degradation process, and tailor it to capture high-frequency noise textures and image structure. Experimental results in T1w and T2w MRI demonstrate that H2LO produces more faithful simulated low-field images than existing parameterized noise synthesis models and popular image-to-image translation models. Furthermore, it improves performance in downstream image enhancement tasks, showcasing its potential to enhance LF MRI diagnostic capabilities.

Figures & tables

Figure 1: Overview of the High-to-Low field Operator (H2LO) framework. The architecture maps HF MRI volumes to a continuous LF representation using a branch-trunk network optimized via pointwise intensity fidelity and gradient regularization.

Figure 2: Visualization of generated LF MRIs and ablation studies. (a) Generated T1w (upper rows) and T2w (lower rows) LF images using multiple methods. Even rows visualize the absolute differences between simulated and real LF images. (b) Ablation of multiple components in our model. (c) Testing results of the 5-fold ablation study. (d) Comparison of histograms for LF images generated by Arnold et al. [ 1 ] and our method.

T1
Method	PSNR(dB) $\uparrow$	SSIM(%) $\uparrow$	NCC $\uparrow$	WASS $\downarrow$	HNCC $\uparrow$	BHAT $\downarrow$	JS $\downarrow$	Param.
HF Image	23.52 $\pm$ 0.44	89.96 $\pm$ 0.34	0.9222 $\pm$ 0.0035	0.1211 $\pm$ 0.0107	0.5130 $\pm$ 0.0436	0.2148 $\pm$ 0.0218	0.1495 $\pm$ 0.0130	–
Arnold et. al. [ 1 ]	14.97 $\pm$ 1.16	87.80 $\pm$ 1.56	0.9466 $\pm$ 0.0069	0.1099 $\pm$ 0.0103	0.5759 $\pm$ 0.0423	0.1009 $\pm$ 0.0231	0.0823 $\pm$ 0.0160	4
Pix2Pix [ 7 ]	26.46 $\pm$ 0.33	92.25 $\pm$ 0.27	0.9561 $\pm$ 0.0032	0.0403 $\pm$ 0.0046	0.8302 $\pm$ 0.0530	0.0448 $\pm$ 0.0106	0.0358 $\pm$ 0.0080	4.86M
DiffI2I [ 23 ]	27.16 $\pm$ 0.54	92.50 $\pm$ 0.83	0.9609 $\pm$ 0.0054	0.0330 $\pm$ 0.0046	0.9028 $\pm$ 0.0145	0.0364 $\pm$ 0.0065	0.0287 $\pm$ 0.0047	16.39M
Conditional INR [ 22 ]	27.59 $\pm$ 0.33	93.90 $\pm$ 0.32	0.9650 $\pm$ 0.0029	0.0327 $\pm$ 0.0031	0.8642 $\pm$ 0.0132	0.0426 $\pm$ 0.0055	0.0342 $\pm$ 0.0043	0.85M

Table 1: Quantitative results of LF MRI synthesis. The mean ± standard deviation across five-fold cross-validation are reported. The best and second-best methods are highlighted in bold and underline, respectively.

	T1		T2
Method	PSNR(dB)	SSIM(%)	PSNR(dB)	SSIM(%)	Subjects	Epoch
Real LF	30.12	92.93	29.26	92.61	13	200
Flip & Rotate	29.49	92.06	28.50	91.98	13 (*8)	400
Arnold et. al. [ 1 ]	30.37	93.48	29.39	92.75	13+147	150+50
Pix2Pix [ 7 ]	30.39	93.77	29.59	93.17	13+147	150+50
DiffI2I [ 23 ]	30.27	93.33	29.52	93.01	13+147	150+50

Table 2: Quantitative result of LF MRI enhancement augmented with synthetic data. The best and second-best methods are highlighted in bold and underline, respectively.

Explore similar work

ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging
May 23, 2026Toufiq Musah, Salvatore Calcagno, Federica Proietto Salanitri +3Medical Image Super-Resolution Magnetic Resonance Imaging
Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · University of Catania, Catania, Italy · The Hong Kong University of Science and Technology, Hong Kong SAR, China +1
ReDiff: Reliability-Guided Diffusion for Trustworthy Ultra-Low-Field to High-Field MRI Synthesis
Mar 11, 2026Zhenxuan Zhang, Peiyuan Jing, Ruicheng Yuan +9Medical Image Synthesis Magnetic Resonance Imaging
Department of Bioengineering and Imperial-X, Imperial College London, London, UK · Department of Electrical and Computer Systems Engineering, Monash University, Melbourne, Australia · National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK +2
Zero-shot Low-Field MRI Enhancement via Diffusion-Based Adaptive Contrast Transport
Mar 2, 2026Muyu Liu, Chenhe Du, Xuanyu Tian +5Magnetic Resonance Imaging Diffusion Models for Image Restoration
School of Information Science and Technology, ShanghaiTech University, Shanghai, China · School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China

May 23, 2026J/K move · Enter open · S save

ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging

Toufiq Musah, Salvatore Calcagno, Federica Proietto Salanitri, Xiaomeng Li+2

Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · University of Catania, Catania, Italy · The Hong Kong University of Science and Technology, Hong Kong SAR, China+1

Medical Image Super-Resolution Magnetic Resonance Imaging Medical Image Synthesis Neuroimaging

Open paper AskPDF arXiv

Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution compared to high-field (HF) systems. Acquiring paired ULF-HF data for supervised enhancement is often difficult, particularly in resource-limited settings. We introduce ULF-Synth, a framework that combines: (i) acquisition-based synthesis of realistic ULF images from HF volumes to create large-scale paired training data, (ii) a spatial-frequency domain objective that prioritizes recovery of high-frequency anatomical detail. This formulation is architecture-agnostic, consistently improving structural similarity and perceptual fidelity across encoder-decoder, adversarial, and diffusion-based translation models. When trained exclusively on synthetic data, the resulting models generalize effectively to real 64mT ULF acquisitions, improving downstream multiclass brain segmentation and achieving higher radiologist preference and diagnostic acceptability in a blinded reader study. These findings demonstrate that synthetic paired supervision provides a practical and scalable pathway for enhancing ULF MRI without requiring real paired acquisitions. Code, Models and Dataset: https://github.com/toufiqmusah/ULF-Synth

Abstract

Explore similar work

ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging

ReDiff: Reliability-Guided Diffusion for Trustworthy Ultra-Low-Field to High-Field MRI Synthesis

Zero-shot Low-Field MRI Enhancement via Diffusion-Based Adaptive Contrast Transport