# Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis

arXiv: https://arxiv.org/abs/2510.13735 · HTML: https://mlsanity.com/paper/2510.13735/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Score-based diffusion models for accelerated MRI](https://mlsanity.com/paper/2110.05243/) (2021)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://mlsanity.com/paper/2207.08208/) (2022)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [Medical Image Synthesis with Context-Aware Generative Adversarial Networks](https://mlsanity.com/paper/1612.05362/) (2016)
- [Low-field magnetic resonance image enhancement via stochastic image quality transfer](https://mlsanity.com/paper/2304.13385/) (2023)
- [CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation](https://mlsanity.com/paper/2110.06400/) (2021)
- [One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstruction](https://mlsanity.com/paper/2307.13220/) (2023)
- [Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis](https://mlsanity.com/paper/2406.18967/) (2024)

## Built on by (most cited first, 1 of 1)

- [ReDiff: Reliability-Guided Diffusion for Trustworthy Ultra-Low-Field to High-Field MRI Synthesis](https://mlsanity.com/paper/2603.11325/) (2026)

## Abstract (arXiv)

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.