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

• URL: http://arxiv.org/abs/2605.24625v1
• Date: Sat, 23 May 2026 15:33:44 GMT
• Title: ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging
• Abstract summary: Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution.<n>We introduce ULF- Synth, a framework that combines acquisition-based synthesis of realistic ULF images from HF volumes to create large-scale paired training data.<n>When trained exclusively on synthetic data, the resulting models generalize effectively to real 64mT ULF acquisitions.
• Score: 11.389464090273849
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning [0.0]
  Multimodal MRI provides complementary information for neuroimaging analysis, where different imaging modalities capture distinct anatomical, tissue, and pathological features.<n>Large-scale structural MRI resources are increasingly available, but their modality coverage is often uneven across public and pooled neuroimaging datasets.<n>Our approach combines a Wavelet-Fusion variational autoencoder (WF-VAE) latent compressor with a conditional 3D U-Net diffusion model trained in the learned latent space.
  arXiv  Detail & Related papers  (2026-05-30T11:57:27Z)
• Subject-Specific Low-Field MRI Synthesis via a Neural Operator [6.717142673853984]
  Low-field (LF) magnetic resonance imaging (MRI) improves accessibility and reduces costs but has lower signal-to-noise ratios and degraded contrast compared to high field (HF) MRI.<n>Existing low field simulators rely on noise injection and smoothing, which fail to capture the contrast degradation seen in LF acquisitions.<n>We introduce an end-to-end LF-MRI framework that learns HF to LF image degradation directly from a small number of paired HF-LF MRIs.
  arXiv  Detail & Related papers  (2026-03-26T03:01:03Z)
• IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model [3.4718032510023438]
  Retrospective MRI harmonization is limited by poor scalability across modalities and reliance on traveling subject datasets.<n>IHF-Harmony is a unified invertible hierarchy flow framework for multi-modality harmonization using unpaired data.<n> Experiments across multiple MRI modalities demonstrate that IHF-Harmony outperforms existing methods in both anatomical fidelity and downstream task performance.
  arXiv  Detail & Related papers  (2026-02-25T03:46:12Z)
• NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models [66.91449452840318]
  We introduce NeuroRVQ, a scalable Large Brainwave Model (LBM) centered on a codebook-based tokenizer.<n>Our tokenizer integrates: (i) multi-scale feature extraction modules that capture the full frequency neural spectrum; (ii) hierarchical residual vector quantization (RVQ) codebooks for high-resolution encoding; and, (iii) an EEG signal phase- and amplitude-aware loss function for efficient training.<n>Our empirical results demonstrate that NeuroRVQ achieves lower reconstruction error and outperforms existing LBMs on a variety of downstream tasks.
  arXiv  Detail & Related papers  (2025-10-15T01:26:52Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• T2I-Diff: fMRI Signal Generation via Time-Frequency Image Transform and Classifier-Free Denoising Diffusion Models [10.21645911536505]
  We introduce T2I-Diff, an fMRI generation framework that leverages time-frequency representation of BOLD signals.<n>We demonstrate improved accuracy and generalization in downstream fMRI-based brain network classification.
  arXiv  Detail & Related papers  (2025-09-25T07:08:19Z)
• High-Fidelity Functional Ultrasound Reconstruction via A Visual Auto-Regressive Framework [58.07923338080814]
  Functional neurotemporal imaging provides exceptional resolution for mapping.<n>However, its practical application is hampered by critical challenges.<n>These include data scarcity, ethical considerations and signal degradation.
  arXiv  Detail & Related papers  (2025-05-23T15:27:17Z)
• Brain Network Diffusion-Driven fMRI Connectivity Augmentation for Enhanced Autism Spectrum Disorder Diagnosis [12.677178802864029]
  Due to the high cost of fMRI data acquisition and labeling, the amount of fMRI data is usually small. With the rise of generative models, especially diffusion models, the ability to generate realistic samples close to the real data distribution has been widely used for data augmentations.
  arXiv  Detail & Related papers  (2024-09-11T08:02:57Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• Transferring Ultrahigh-Field Representations for Intensity-Guided Brain Segmentation of Low-Field Magnetic Resonance Imaging [51.92395928517429]
  The use of 7T MRI is limited by its high cost and lower accessibility compared to low-field (LF) MRI. This study proposes a deep-learning framework that fuses the input LF magnetic resonance feature representations with the inferred 7T-like feature representations for brain image segmentation tasks.
  arXiv  Detail & Related papers  (2024-02-13T12:21:06Z)
• A Generative Self-Supervised Framework using Functional Connectivity in fMRI Data [15.211387244155725]
  Deep neural networks trained on Functional Connectivity (FC) networks extracted from functional Magnetic Resonance Imaging (fMRI) data have gained popularity. Recent research on the application of Graph Neural Network (GNN) to FC suggests that exploiting the time-varying properties of the FC could significantly improve the accuracy and interpretability of the model prediction. High cost of acquiring high-quality fMRI data and corresponding labels poses a hurdle to their application in real-world settings. We propose a generative SSL approach that is tailored to effectively harnesstemporal information within dynamic FC.
  arXiv  Detail & Related papers  (2023-12-04T16:14:43Z)
• Model-based Deep Learning Receiver Design for Rate-Splitting Multiple Access [65.21117658030235]
  This work proposes a novel design for a practical RSMA receiver based on model-based deep learning (MBDL) methods. The MBDL receiver is evaluated in terms of uncoded Symbol Error Rate (SER), throughput performance through Link-Level Simulations (LLS) and average training overhead. Results reveal that the MBDL outperforms by a significant margin the SIC receiver with imperfect CSIR.
  arXiv  Detail & Related papers  (2022-05-02T12:23:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.