DMD-augmented Unpaired Neural Schrödinger Bridge for Ultra-Low Field MRI Enhancement
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_ | 1866910041452314624 |
|---|---|
| author | Kim, Youngmin Shin, Jaeyun Kim, Jeongchan Lee, Taehoon Kim, Jaemin Hsu, Peter Veraart, Jelle Ye, Jong Chul |
| author_facet | Kim, Youngmin Shin, Jaeyun Kim, Jeongchan Lee, Taehoon Kim, Jaemin Hsu, Peter Veraart, Jelle Ye, Jong Chul |
| contents | Ultra Low Field (64 mT) brain MRI improves accessibility but suffers from reduced image quality compared to 3 T. As paired 64 mT - 3 T scans are scarce, we propose an unpaired 64 mT $\rightarrow$ 3 T translation framework that enhances realism while preserving anatomy. Our method builds upon the Unpaired Neural Schrödinge Bridge (UNSB) with multi-step refinement. To strengthen target distribution alignment, we augment the adversarial objective with DMD2-style diffusion-guided distribution matching using a frozen 3T diffusion teacher. To explicitly constrain global structure beyond patch-level correspondence, we combine PatchNCE with an Anatomical Structure Preservation (ASP) regularizer that enforces soft foreground background consistency and boundary aware constraints. Evaluated on two disjoint cohorts, the proposed framework achieves an improved realism structure trade-off, enhancing distribution level realism on unpaired benchmarks while increasing structural fidelity on the paired cohort compared to unpaired baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03769 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DMD-augmented Unpaired Neural Schrödinger Bridge for Ultra-Low Field MRI Enhancement Kim, Youngmin Shin, Jaeyun Kim, Jeongchan Lee, Taehoon Kim, Jaemin Hsu, Peter Veraart, Jelle Ye, Jong Chul Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Ultra Low Field (64 mT) brain MRI improves accessibility but suffers from reduced image quality compared to 3 T. As paired 64 mT - 3 T scans are scarce, we propose an unpaired 64 mT $\rightarrow$ 3 T translation framework that enhances realism while preserving anatomy. Our method builds upon the Unpaired Neural Schrödinge Bridge (UNSB) with multi-step refinement. To strengthen target distribution alignment, we augment the adversarial objective with DMD2-style diffusion-guided distribution matching using a frozen 3T diffusion teacher. To explicitly constrain global structure beyond patch-level correspondence, we combine PatchNCE with an Anatomical Structure Preservation (ASP) regularizer that enforces soft foreground background consistency and boundary aware constraints. Evaluated on two disjoint cohorts, the proposed framework achieves an improved realism structure trade-off, enhancing distribution level realism on unpaired benchmarks while increasing structural fidelity on the paired cohort compared to unpaired baselines. |
| title | DMD-augmented Unpaired Neural Schrödinger Bridge for Ultra-Low Field MRI Enhancement |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.03769 |