用基础函数分离解剖、增强和运动，提升动态增强MRI重建质量
Primitive Representation Learning for Unsupervised Dynamic Contrast Enhanced MRI Reconstruction
- 将解剖、动态增强和运动分解为独立的时间基函数
- 在高欠采样下重建质量媲美传统方法，器官增强曲线更准确
- 模块化设计可扩展至更多动态因素，适合医学影像重建研究者
动态对比增强 MRI 的可靠定量分析需要在高欠采样率下获得高质量的时空重建。基于高斯和伽柏基函数的扫描特定重建虽无需大规模训练数据且表现良好，但未考虑动态对比增强的额外维度。本文提出一种多维、基于基函数的动态对比增强 MRI 重建框架，将潜在解剖结构、动态对比增强和残余运动分别建模为独立的时间基函数，从而实现表示的几何可解释性。实验表明，该架构在重建质量及提取主动脉和肾脏增强曲线的准确性上均达到与传统方法相当的水平。模块化层级设计天然支持更多动态因素和更高加速率。代码已公开于 https://github.com/compai-lab/2026-GaborDCE-spieker。
原文摘要 · Abstract (English)
Reliable quantitative analysis of dynamic contrast-enhanced MRI requires high-quality spatiotemporal reconstructions at high undersampling rates. Scan-specific reconstructions using Gaussian and Gabor primitives have shown promising results without the need for large training datasets, but have not addressed the additional dimension of dynamic contrast. We propose a multi-dimensional, primitive based framework for dynamic contrast-enhanced MRI reconstruction that disentangles the underlying anatomy, the dynamic contrast enhancement, and residual motion into separate temporal basis functions, thereby enabling a geometrical interpretation of the representation. We show that this architecture achieves performance competitive with conventional reconstruction methods, both in reconstruction quality and in the accuracy of extracted aorta and kidney enhancement curves. The modular tier design extends naturally to additional dynamic factors and higher acceleration rates. Code available at https://github.com/compai-lab/2026-GaborDCE-spieker.
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。