Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis
- 20 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP (02780062) , 1
Abstract
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 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 ± 2.70 dB in PSNR, 0.943± 0.102 in SSIM, and 0.0864 ± 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. The code is available at: https://github.com/ayanglab/CSS-Diff.Keywords
All Related Versions
Funding Information
- Wellcome Leap Dynamic Resilience program
- UKRI guarantee funding for Horizon Europe MSCA Postdoctoral Fellowships (EP/Z002206/1)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (220785)
- NVIDIA Academic Hardware Grant Program
- Royal Society (IEC11235)
- Boehringer Ingelheim Ltd (SABER)
- NIHR Imperial Biomedical Research Centre (RDA01)
- ERC IMI (101005122)
- Horizon 2020 Framework Programme (952172)
- MRC (MC/PC/21013)
- MRC (MR/U506710/1)
- MRC (MR/V023799/1)
This publication has 34 references indexed in Scilit:
- Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis2024
- UNITY: A low-field magnetic resonance neuroimaging initiative to characterize neurodevelopment in low and middle-income settingsDevelopmental Cognitive Neuroscience, 2024
- Synthesized 7T MPRAGE From 3T MPRAGE Using Generative Adversarial Network and Validation in Clinical Brain Imaging: A Feasibility StudyJournal of Magnetic Resonance Imaging, 2023
- Low‐field MRI: Clinical promise and challengesJournal of Magnetic Resonance Imaging, 2022
- Magnetic field strength dependent SNR gain at the center of a spherical phantom and up to 11.7TMagnetic Resonance in Medicine, 2022
- Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis2019
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks2019
- Low‐field MRI: An MR physics perspectiveJournal of Magnetic Resonance Imaging, 2019
- Medical Image Synthesis with Context-Aware Generative Adversarial Networks2017
- Fast free-form deformation using graphics processing unitsComputer Methods and Programs in Biomedicine, 2010