利用无生物物理模型的深度MRI芯片框架解码人脑组织对射频激发的响应
医学物理
2025-12-24 v2 人工智能
神经元与认知
摘要
磁共振成像(MRI)依赖于对质子自旋的射频(RF)激发。临床诊断需要通过一系列RF序列获取多种MRI对比度,从而全面收集生物物理数据,这导致检查时间冗长。在这里,我们开发了一个基于视觉变换器的框架,该框架捕获时空磁信号演化并解码脑组织对RF激发的响应,构成了一个MRI芯片。在每位受试者进行快速校准扫描(28.2秒)后,可以自动生成各种图像对比度,包括全定量分子图、水弛豫图和磁场图。该方法在两个不同成像站点对健康受试者和一名癌症患者进行了验证,并被证明比替代方案快94%。深度MRI芯片(DeepMonC)框架可能揭示多种病理状态下人脑组织的分子组成,同时提供临床上有吸引力的扫描时间。
引用
@article{arxiv.2408.08376,
title = {Decoding the human brain tissue response to radiofrequency excitation using a biophysical-model-free deep MRI on a chip framework},
author = {Dinor Nagar and Moritz Zaiss and Or Perlman},
journal= {arXiv preprint arXiv:2408.08376},
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