dorsal/arxiv
View SchemaFrequency Error-Guided Under-sampling Optimization for Multi-Contrast MRI Reconstruction
| Authors | Xinming Fang, Chaoyan Huang, Juncheng Li, Jun Wang, Jun Shi, Guixu Zhang |
|---|---|
| Categories | |
| ArXiv ID | 2601.09316vv1 |
| URL | https://arxiv.org/abs/2601.09316 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
Magnetic resonance imaging (MRI) plays a vital role in clinical diagnostics, yet it remains hindered by long acquisition times and motion artifacts. Multi-contrast MRI reconstruction has emerged as a promising direction by leveraging complementary information from fully-sampled reference scans. However, existing approaches suffer from three major limitations: (1) superficial reference fusion strategies, such as simple concatenation, (2) insufficient utilization of the complementary information provided by the reference contrast, and (3) fixed under-sampling patterns. We propose an efficient and interpretable frequency error-guided reconstruction framework to tackle these issues. We first employ a conditional diffusion model to learn a Frequency Error Prior (FEP), which is then incorporated into a unified framework for jointly optimizing both the under-sampling pattern and the reconstruction network. The proposed reconstruction model employs a model-driven deep unfolding framework that jointly exploits frequency- and image-domain information. In addition, a spatial alignment module and a reference feature decomposition strategy are incorporated to improve reconstruction quality and bridge model-based optimization with data-driven learning for improved physical interpretability. Comprehensive validation across multiple imaging modalities, acceleration rates (4-30x), and sampling schemes demonstrates consistent superiority over state-of-the-art methods in both quantitative metrics and visual quality. All codes are available at https://github.com/fangxinming/JUF-MRI.
{
"annotation_id": "4e3ee771-eda0-4a50-a682-7c450297df27",
"date_created": "2026-02-17T05:53:19.896000Z",
"date_modified": "2026-02-17T05:53:19.896000Z",
"file_hash": "4e7d2d1652d061645f7e2ddf14e3f5611dd9133fc4ae7ef820c9eb355db10206",
"private": false,
"record": {
"abstract": "Magnetic resonance imaging (MRI) plays a vital role in clinical diagnostics, yet it remains hindered by long acquisition times and motion artifacts. Multi-contrast MRI reconstruction has emerged as a promising direction by leveraging complementary information from fully-sampled reference scans. However, existing approaches suffer from three major limitations: (1) superficial reference fusion strategies, such as simple concatenation, (2) insufficient utilization of the complementary information provided by the reference contrast, and (3) fixed under-sampling patterns. We propose an efficient and interpretable frequency error-guided reconstruction framework to tackle these issues. We first employ a conditional diffusion model to learn a Frequency Error Prior (FEP), which is then incorporated into a unified framework for jointly optimizing both the under-sampling pattern and the reconstruction network. The proposed reconstruction model employs a model-driven deep unfolding framework that jointly exploits frequency- and image-domain information. In addition, a spatial alignment module and a reference feature decomposition strategy are incorporated to improve reconstruction quality and bridge model-based optimization with data-driven learning for improved physical interpretability. Comprehensive validation across multiple imaging modalities, acceleration rates (4-30x), and sampling schemes demonstrates consistent superiority over state-of-the-art methods in both quantitative metrics and visual quality. All codes are available at https://github.com/fangxinming/JUF-MRI.",
"arxiv_id": "2601.09316",
"authors": [
"Xinming Fang",
"Chaoyan Huang",
"Juncheng Li",
"Jun Wang",
"Jun Shi",
"Guixu Zhang"
],
"categories": [
"cs.CV"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Frequency Error-Guided Under-sampling Optimization for Multi-Contrast MRI Reconstruction",
"url": "https://arxiv.org/abs/2601.09316",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "30dd3fab-cb40-4538-a2af-9338f89b1fb1",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}