Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915556149428224 |
|---|---|
| author | Zhang, Zhenxuan Jing, Peiyuan Wang, Zi Briski, Ula Beitone, Coraline Yang, Yue Wu, Yinzhe Wang, Fanwen Yang, Liutao Huang, Jiahao Gao, Zhifan Chen, Zhaolin Islam, Kh Tohidul Yang, Guang Lally, Peter J. |
| author_facet | Zhang, Zhenxuan Jing, Peiyuan Wang, Zi Briski, Ula Beitone, Coraline Yang, Yue Wu, Yinzhe Wang, Fanwen Yang, Liutao Huang, Jiahao Gao, Zhifan Chen, Zhaolin Islam, Kh Tohidul Yang, Guang Lally, Peter J. |
| contents | Synthesizing high-quality images from low-field MRI holds significant potential. Low-field MRI is cheaper, more accessible, and safer, but suffers from low resolution and poor signal-to-noise ratio. This synthesis process can reduce reliance on costly acquisitions and expand data availability. However, synthesizing high-field MRI still suffers from a clinical fidelity gap. There is a need to preserve anatomical fidelity, enhance fine-grained structural details, and bridge domain gaps in image contrast. To address these issues, we propose a \emph{cyclic self-supervised diffusion (CSS-Diff)} framework for high-field MRI synthesis from real low-field MRI data. Our core idea is to reformulate diffusion-based synthesis under a cycle-consistent constraint. It enforces anatomical preservation throughout the generative process rather than just relying on paired pixel-level supervision. The CSS-Diff framework further incorporates two novel processes. The slice-wise gap perception network aligns inter-slice inconsistencies via contrastive learning. The local structure correction network enhances local feature restoration through self-reconstruction of masked and perturbed patches. Extensive experiments on cross-field synthesis tasks demonstrate the effectiveness of our method, achieving state-of-the-art performance (e.g., 31.80 $\pm$ 2.70 dB in PSNR, 0.943 $\pm$ 0.102 in SSIM, and 0.0864 $\pm$ 0.0689 in LPIPS). Beyond pixel-wise fidelity, our method also preserves fine-grained anatomical structures compared with the original low-field MRI (e.g., left cerebral white matter error drops from 12.1$\%$ to 2.1$\%$, cortex from 4.2$\%$ to 3.7$\%$). To conclude, our CSS-Diff can synthesize images that are both quantitatively reliable and anatomically consistent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13735 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis Zhang, Zhenxuan Jing, Peiyuan Wang, Zi Briski, Ula Beitone, Coraline Yang, Yue Wu, Yinzhe Wang, Fanwen Yang, Liutao Huang, Jiahao Gao, Zhifan Chen, Zhaolin Islam, Kh Tohidul Yang, Guang Lally, Peter J. Computer Vision and Pattern Recognition Synthesizing high-quality images from low-field MRI holds significant potential. Low-field MRI is cheaper, more accessible, and safer, but suffers from low resolution and poor signal-to-noise ratio. This synthesis process can reduce reliance on costly acquisitions and expand data availability. However, synthesizing high-field MRI still suffers from a clinical fidelity gap. There is a need to preserve anatomical fidelity, enhance fine-grained structural details, and bridge domain gaps in image contrast. To address these issues, we propose a \emph{cyclic self-supervised diffusion (CSS-Diff)} framework for high-field MRI synthesis from real low-field MRI data. Our core idea is to reformulate diffusion-based synthesis under a cycle-consistent constraint. It enforces anatomical preservation throughout the generative process rather than just relying on paired pixel-level supervision. The CSS-Diff framework further incorporates two novel processes. The slice-wise gap perception network aligns inter-slice inconsistencies via contrastive learning. The local structure correction network enhances local feature restoration through self-reconstruction of masked and perturbed patches. Extensive experiments on cross-field synthesis tasks demonstrate the effectiveness of our method, achieving state-of-the-art performance (e.g., 31.80 $\pm$ 2.70 dB in PSNR, 0.943 $\pm$ 0.102 in SSIM, and 0.0864 $\pm$ 0.0689 in LPIPS). Beyond pixel-wise fidelity, our method also preserves fine-grained anatomical structures compared with the original low-field MRI (e.g., left cerebral white matter error drops from 12.1$\%$ to 2.1$\%$, cortex from 4.2$\%$ to 3.7$\%$). To conclude, our CSS-Diff can synthesize images that are both quantitatively reliable and anatomically consistent. |
| title | Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.13735 |