Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UniField: A Unified Field-Aware MRI Enhancement Framework

Yiyang Lin, Chenhui Wang, Zhihao Peng, Yixuan Yuan

TL;DR

To overcome MRI data scarcity and capture continuous anatomical structures, \methodname departs from conventional methods that treat 3D MRI volumes as independent 2D slices and directly exploit comprehensive 3D volumetric information by leveraging pre-trained 3D foundation models, thereby embedding generalized and robust structural representations to significantly boost enhancement performance.

Abstract

Magnetic Resonance Imaging (MRI) field-strength enhancement holds immense value for both clinical diagnostics and advanced research. However, existing methods typically focus on isolated enhancement tasks, such as specific 64mT-to-3T or 3T-to-7T transitions using limited subject cohorts, thereby failing to exploit the shared degradation patterns inherent across different field strengths and severely restricting model generalization. To address this challenge, we propose \methodname, a unified framework integrating multiple modalities and enhancement tasks to mutually promote representation learning by exploiting these shared degradation characteristics. Specifically, our main contributions are threefold. Firstly, to overcome MRI data scarcity and capture continuous anatomical structures, \methodname departs from conventional methods that treat 3D MRI volumes as independent 2D slices. Instead, we directly exploit comprehensive 3D volumetric information by leveraging pre-trained 3D foundation models, thereby embedding generalized and robust structural representations to significantly boost enhancement performance. In addition, to mitigate the spectral bias of mainstream flow-matching models that often over-smooth high-frequency details, we explicitly incorporate the physical mechanisms of magnetic fields to introduce a Field-Aware Spectral Rectification Mechanism (FASRM), tailoring customized spectral corrections to distinct field strengths. Finally, to resolve the fundamental data bottleneck, we organize and publicly release a comprehensive paired multi-field MRI dataset, which is an order of magnitude larger than existing datasets. Extensive experiments demonstrate our method's superiority over state-of-the-art approaches, achieving an average improvement of approximately 1.81 dB in PSNR and 9.47\% in SSIM. Code will be released upon acceptance.

UniField: A Unified Field-Aware MRI Enhancement Framework

TL;DR

To overcome MRI data scarcity and capture continuous anatomical structures, \methodname departs from conventional methods that treat 3D MRI volumes as independent 2D slices and directly exploit comprehensive 3D volumetric information by leveraging pre-trained 3D foundation models, thereby embedding generalized and robust structural representations to significantly boost enhancement performance.

Abstract

Magnetic Resonance Imaging (MRI) field-strength enhancement holds immense value for both clinical diagnostics and advanced research. However, existing methods typically focus on isolated enhancement tasks, such as specific 64mT-to-3T or 3T-to-7T transitions using limited subject cohorts, thereby failing to exploit the shared degradation patterns inherent across different field strengths and severely restricting model generalization. To address this challenge, we propose \methodname, a unified framework integrating multiple modalities and enhancement tasks to mutually promote representation learning by exploiting these shared degradation characteristics. Specifically, our main contributions are threefold. Firstly, to overcome MRI data scarcity and capture continuous anatomical structures, \methodname departs from conventional methods that treat 3D MRI volumes as independent 2D slices. Instead, we directly exploit comprehensive 3D volumetric information by leveraging pre-trained 3D foundation models, thereby embedding generalized and robust structural representations to significantly boost enhancement performance. In addition, to mitigate the spectral bias of mainstream flow-matching models that often over-smooth high-frequency details, we explicitly incorporate the physical mechanisms of magnetic fields to introduce a Field-Aware Spectral Rectification Mechanism (FASRM), tailoring customized spectral corrections to distinct field strengths. Finally, to resolve the fundamental data bottleneck, we organize and publicly release a comprehensive paired multi-field MRI dataset, which is an order of magnitude larger than existing datasets. Extensive experiments demonstrate our method's superiority over state-of-the-art approaches, achieving an average improvement of approximately 1.81 dB in PSNR and 9.47\% in SSIM. Code will be released upon acceptance.
Paper Structure (10 sections, 2 equations, 4 figures, 4 tables)

This paper contains 10 sections, 2 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Overall Architecture of UniField
  4. Unified Modeling via Video Super-Resolution Prior
  5. Field-Aware Spectral Rectification Mechanism (FASRM)
  6. Experiments
  7. Dataset and Experimental Details
  8. Comparative Experiments
  9. Ablation Experiments
  10. Conclusion

Figures (4)

  • Figure 1: Comparison of existing MRI enhancing method and our framework. (Left) Existing methods train isolated networks for specific modalities and tasks. (Right) Our method unifies all modalities and tasks within a single framework.
  • Figure 2: Overview of our proposed UniField. Within the framework, the encoder and decoder utilize frozen pre-trained FlashVSR weights, while the central unified network is fine-tuned using LoRA.
  • Figure 3: Visual comparison with competing methods. Error maps show the absolute difference from the ground truth, where darker colors indicate larger errors (mean pixel error at bottom right). Red annotations highlight defects in competing methods.
  • Figure 4: Visualization of ablation experiments on FASRM. Results for both 64mT-to-3T and 3T-to-7T tasks demonstrate the module's effectiveness. Red boxes highlight severe defects in the baselines without FASRM.