基于AI提升的分子MRI实现帕金棃病的定量多代谢物成像
医学物理
2025-12-24 v1 人工智能
摘要
传统方法对于体内帕金棃病（PD）的分子成像需要放射性同位素、耗时的扫描时间，或仅提供低空间分辨率。最近的饱和传递型PD磁共振成像（MRI）技术已提供了生化学见解，尽管图像对比度为准定性且非特异。本文结合快速分子MRI获取范式与深度学习重建技术，对急性MPTP（1-甲基-4-苯基-1,2,3,6-四氢吡啶）小鼠模型中的谷氨酰胺、可移动蛋白质、半固体以及可移动大分子实现多代谢物定量化。定量参数图总体上与组织学和MR谱学一致，表明半固体磁化传递（MT）、肾脂和醇烷中继核偶合效应（rNOE）质子体积分数可能作为PD生物标志物。
引用
@article{arxiv.2507.11329,
title = {Quantitative multi-metabolite imaging of Parkinson's disease using AI boosted molecular MRI},
author = {Hagar Shmuely and Michal Rivlin and Or Perlman},
journal= {arXiv preprint arXiv:2507.11329},
year = {2025}
}
备注
This project was funded by the European Union (ERC, BabyMagnet, project no. 101115639). Views and opinions expressed are, however, those of the authors only and do not necessarily reflect those of the European Union or the European Research Council. Neither the European Union nor the granting authority can be held responsible for them