用于无监督动态对比增强MRI重建的基元表示学习
Primitive Representation Learning for Unsupervised Dynamic Contrast Enhanced MRI Reconstruction
另 4 家 · 查看机构详情
- Helmholtz Munich（亥姆霍兹慕尼黑）
- Technical University of Munich（慕尼黑工业大学）
- Boston Children’s Hospital（波士顿儿童医院）
- Harvard Medical School（哈佛医学院）
- Munich Center for Machine Learning（慕尼黑机器学习中心）
- Imperial College London（伦敦帝国理工学院）
- King’s College London（伦敦国王学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对无监督动态对比增强MRI重建，提出多维度基元框架解耦动态因素，性能与传统方法相当，可扩展至更高加速率，代码公开。
中文摘要 AI 辅助
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结果。使用高斯基元（Gaussian primitives）和伽柏基元（Gabor primitives）的扫描特异性重建已取得良好效果，且无需大型训练数据集，但尚未解决动态对比这一额外维度的问题。我们提出一种基于多维度基元的动态对比增强MRI重建框架，该框架将基础解剖结构、动态对比增强及残余运动解耦为独立的时间基函数，从而实现对表示的几何解释。结果表明，该架构在重建质量以及提取主动脉和肾脏增强曲线的准确性方面，均达到了与传统重建方法相当的性能。其模块化分层设计可自然扩展至更多动态因素及更高加速率。代码可在该https URL获取：2026-GaborDCE-spieker。
英文摘要
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.
