CRUNet-MR-Univ: A Foundation Model for Diverse Cardiac MRI Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912810131259392 |
|---|---|
| author | Lyu, Donghang Staring, Marius Lamb, Hildo Doneva, Mariya |
| author_facet | Lyu, Donghang Staring, Marius Lamb, Hildo Doneva, Mariya |
| contents | In recent years, deep learning has attracted increasing attention in the field of Cardiac MRI (CMR) reconstruction due to its superior performance over traditional methods, particularly in handling higher acceleration factors, highlighting its potential for real-world clinical applications. However, current deep learning methods remain limited in generalizability. CMR scans exhibit wide variability in image contrast, sampling patterns, scanner vendors, anatomical structures, and disease types. Most existing models are designed to handle only a single or narrow subset of these variations, leading to performance degradation when faced with distribution shifts. Therefore, it is beneficial to develop a unified model capable of generalizing across diverse CMR scenarios. To this end, we propose CRUNet-MR-Univ, a foundation model that leverages spatio-temporal correlations and prompt-based priors to effectively handle the full diversity of CMR scans. Our approach consistently outperforms baseline methods across a wide range of settings, highlighting its effectiveness and promise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04428 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CRUNet-MR-Univ: A Foundation Model for Diverse Cardiac MRI Reconstruction Lyu, Donghang Staring, Marius Lamb, Hildo Doneva, Mariya Computer Vision and Pattern Recognition Artificial Intelligence In recent years, deep learning has attracted increasing attention in the field of Cardiac MRI (CMR) reconstruction due to its superior performance over traditional methods, particularly in handling higher acceleration factors, highlighting its potential for real-world clinical applications. However, current deep learning methods remain limited in generalizability. CMR scans exhibit wide variability in image contrast, sampling patterns, scanner vendors, anatomical structures, and disease types. Most existing models are designed to handle only a single or narrow subset of these variations, leading to performance degradation when faced with distribution shifts. Therefore, it is beneficial to develop a unified model capable of generalizing across diverse CMR scenarios. To this end, we propose CRUNet-MR-Univ, a foundation model that leverages spatio-temporal correlations and prompt-based priors to effectively handle the full diversity of CMR scans. Our approach consistently outperforms baseline methods across a wide range of settings, highlighting its effectiveness and promise. |
| title | CRUNet-MR-Univ: A Foundation Model for Diverse Cardiac MRI Reconstruction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.04428 |