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

2026-03-02

AI Summary

This work addresses the challenge of high-quality reconstruction in low-field MRI, which suffers from low signal-to-noise ratio, distorted tissue contrast, and the absence of paired high-field data. To overcome these limitations, the authors propose the DACT framework, which integrates pre-trained high-field diffusion priors with a physics-driven adaptive forward model under an unpaired supervision setting. Notably, DACT introduces a differentiable Sinkhorn optimal transport mechanism into zero-shot MRI enhancement for the first time, enabling dynamic correction of nonlinear intensity distribution shifts between low- and high-field images during the reverse diffusion process. By explicitly modeling contrast transfer while preserving topological consistency, the method achieves state-of-the-art performance on both simulated and real clinical low-field datasets, significantly improving structural detail fidelity and tissue contrast accuracy.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

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.

Problem

• Low-field MRI
• zero-shot enhancement
• contrast distortion
• blind inverse problem
• tissue contrast recovery

Innovation

• zero-shot MRI enhancement
• diffusion prior
• optimal transport
• contrast adaptation
• low-field MRI