用合成数据提升儿科超低场MRI清晰度，无需真实配对数据
ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging
- 从高场MRI生成逼真超低场图像，构建大规模训练数据
- 在空间频域优化，显著恢复脑部细微结构细节
- 仅用合成数据训练即可在真实64mT设备上表现优异
超低场（ULF）MRI具有便携性和可及性优势，但相比高场（HF）系统信噪比更低、空间分辨率受限。在资源有限地区获取成对的ULF-HF数据常不可行。我们提出ULF-Synth框架：(i) 基于采集过程合成真实感ULF图像，构建大规模成对训练数据；(ii) 采用空间-频率域目标函数，优先恢复高频解剖细节。该方法与架构无关，在编码器-解码器、对抗式及扩散模型中均稳定提升结构相似性和感知保真度。仅使用合成数据训练的模型在真实64mT ULF数据上表现出色，显著改善多类别脑组织分割性能，并在盲法阅片研究中获得更高放射科医生偏好与诊断可接受性。结果表明，合成配对监督为提升ULF MRI提供了可行且可扩展的路径。
原文摘要 · Abstract (English)
Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution compared to high-field (HF) systems. Acquiring paired ULF-HF data for supervised enhancement is often difficult, particularly in resource-limited settings. We introduce ULF-Synth, a framework that combines: (i) acquisition-based synthesis of realistic ULF images from HF volumes to create large-scale paired training data, (ii) a spatial-frequency domain objective that prioritizes recovery of high-frequency anatomical detail. This formulation is architecture-agnostic, consistently improving structural similarity and perceptual fidelity across encoder-decoder, adversarial, and diffusion-based translation models. When trained exclusively on synthetic data, the resulting models generalize effectively to real 64mT ULF acquisitions, improving downstream multiclass brain segmentation and achieving higher radiologist preference and diagnostic acceptability in a blinded reader study. These findings demonstrate that synthetic paired supervision provides a practical and scalable pathway for enhancing ULF MRI without requiring real paired acquisitions. Code, Models and Dataset: https://github.com/toufiqmusah/ULF-Synth
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。