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

Low-field (LF) magnetic resonance imaging (MRI) democratizes access to diagnostic imaging but is fundamentally limited by low signal-to-noise ratio and significant tissue contrast distortion due to field-dependent relaxation dynamics. Reconstructing high-field (HF) quality images from LF data is a blind inverse problem, severely challenged by the scarcity of paired training data and the unknown, non-linear contrast transformation operator. Existing zero-shot methods, which assume simplified linear degradation, often fail to recover authentic tissue contrast. In this paper, we propose DACT(Diffusion-Based Adaptive Contrast Transport), a novel zero-shot framework that restores HF-quality images without paired supervision. DACT synergizes a pre-trained HF diffusion prior to ensure anatomical fidelity with a physically-informed adaptive forward model. Specifically, we introduce a differentiable Sinkhorn optimal transport module that explicitly models and corrects the intensity distribution shift between LF and HF domains during the reverse diffusion process. This allows the framework to dynamically learn the intractable contrast mapping while preserving topological consistency. Extensive experiments on simulated and real clinical LF datasets demonstrate that DACT achieves state-of-the-art performance, yielding reconstructions with superior structural detail and correct tissue contrast.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-03-02

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  arXiv 2603.01913
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Ultra-Low-Field MRI Enhancement via INR-Based Style Transfer

  2025cited by this paper
• Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction

  2025cited by this paper
• Zero-Shot Low-Field MRI Enhancement via Denoising Diffusion Driven Neural Representation

  2024cited by this paper
• Super-Field MRI Synthesis for Infant Brains Enhanced by Dual Channel Latent Diffusion

  2024cited by this paper
• Whole-body magnetic resonance imaging at 0.05 Tesla

  2024cited by this paper
• DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction

  2024cited by this paper
• Test-Time Degradation Adaptation for Open-Set Image Restoration

  2023cited by this paper
• Generative Diffusion Prior for Unified Image Restoration and Enhancement

  2023cited by this paper
• Deep learning enabled fast 3D brain MRI at 0.055 tesla

  2023cited by this paper
• Denoising Diffusion Models for Plug-and-Play Image Restoration

  2023cited by this paper
• Low-field magnetic resonance image enhancement via stochastic image quality transfer

  2023cited by this paper
• Quantitative Brain Morphometry of Portable Low-Field-Strength MRI Using Super-Resolution Machine Learning.

  2022cited by this paper
• Diffusion Posterior Sampling for General Noisy Inverse Problems

  2022cited by this paper
• Solving Inverse Problems in Medical Imaging with Score-Based Generative Models

  2021cited by this paper
• Score-Based Generative Modeling through Stochastic Differential Equations

  2020cited by this paper
• Denoising Diffusion Probabilistic Models

  2020cited by this paper
• Assessment of Brain Injury Using Portable, Low-Field Magnetic Resonance Imaging at the Bedside of Critically Ill Patients.

  2020cited by this paper
• Denoising Diffusion Implicit Models

  2020cited by this paper
• Low‐field MRI: An MR physics perspective

  2019cited by this paper
• Opportunities in Interventional and Diagnostic Imaging by Using High-performance Low-Field-Strength MRI.

  2019cited by this paper
• Deep Learning for Low-Field to High-Field MR: Image Quality Transfer with Probabilistic Decimation Simulator

  2019cited by this paper
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

  2017cited by this paper
• Learning Deep CNN Denoiser Prior for Image Restoration

  2017cited by this paper
• Sinkhorn Distances: Lightspeed Computation of Optimal Transport

  2013influential reference
• Making a “Completely Blind” Image Quality Analyzer

  2013cited by this paper
• The WU-Minn Human Connectome Project: An overview

  2013cited by this paper
• No-Reference Image Quality Assessment in the Spatial Domain

  2012cited by this paper
• Magnetic field and tissue dependencies of human brain longitudinal 1H2O relaxation in vivo

  2007cited by this paper
• Polar Factorization and Monotone Rearrangement of Vector-Valued Functions

  1991cited by this paper
• A review of normal tissue hydrogen NMR relaxation times and relaxation mechanisms from 1-100 MHz: dependence on tissue type, NMR frequency, temperature, species, excision, and age.

  1984cited by this paper

• No citing papers are available for this paper.