发表机构
Gnosis Neurodynamics Co. Ltd; School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University; University of California, Davis; Advanced Innovation Center for Human Brain Protection, Capital Medical University（格诺西斯神经动力学有限公司; 清华大学医学院生物医学工程系; 加州大学戴维斯分校; 首都医科大学人类脑保护前沿创新中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
NeuroDyn-EEG通过整合神经动力学生成先验的预训练框架，将头皮EEG映射到解剖学索引的动力学参数，在临床基准上取得竞争性能，并揭示疾病特异性区域改变。
AI 中文摘要
临床头皮脑电图（EEG）为神经精神疾病的神经动力学提供了非侵入性窗口。然而，判别性深度模型往往缺乏解剖学索引的生理可解释性。我们提出了NeuroDyn-EEG，一个整合神经动力学生成先验的预训练框架。它耦合了扩展的Jansen-Rit神经质量模型、基于导联场的源投影和基于模拟的参数反演。在生理范围内的合成参数-EEG对上训练，NeuroDyn-EEG从标准19导联EEG中估计90个AAL区域上的11个区域参数族加上一个全局参数，仅使用约243万可训练参数。我们在三个层面评估该框架。首先，受控模拟证明了在多种噪声条件下的鲁棒参数恢复，而真实静息态EEG评估在逆-正闭环中确认了频谱和相位一致性。其次，在四个临床基准（AD65、PD31、Figshare MDD和TUAB）上，NeuroDyn-EEG取得了有竞争力的分类性能，在PD31和MDD上获得最高的BACC、AUROC和AUCPR，在AD65上获得最高的BACC。第三，事后区域分析揭示了疾病特异性改变：局部突触连接C_1涉及AD65中改变最多的区域，而放电阈值theta在MDD中排名第一，提供了可检验的机制性假设。总体而言，NeuroDyn-EEG将头皮EEG映射到解剖学索引的动力学参数，弥合了表征学习与机制神经生理学之间的鸿沟。代码：此https URL。
英文摘要
Clinical scalp electroencephalography (EEG) offers a noninvasive window into neural dynamics of neuropsychiatric disorders. However, discriminative deep models often lack anatomically indexed physiological interpretability. We propose NeuroDyn-EEG, a pretraining framework integrating generative priors from neural dynamics. It couples an extended Jansen-Rit neural mass model, leadfield-based source projection, and simulation-based parameter inversion. Trained on synthetic parameter-EEG pairs within physiological ranges, NeuroDyn-EEG estimates 11 regional parameter families across 90 AAL regions plus one global parameter from standard 19-channel EEG, using only ~2.43M trainable parameters. We evaluate the framework across three levels. First, controlled simulations demonstrate robust parameter recovery under diverse noise conditions, while real resting-state EEG evaluations confirm spectral and phase consistency in an inverse-forward closed loop. Second, on four clinical benchmarks (AD65, PD31, Figshare MDD, and TUAB), NeuroDyn-EEG achieves competitive classification performance, securing the highest BACC, AUROC, and AUCPR on PD31 and MDD, and highest BACC on AD65. Third, post hoc regional analyses reveal disease-specific alterations: local synaptic connectivity C_1 involves the most altered regions in AD65, whereas the firing threshold theta ranks first in MDD, offering testable mechanistic hypotheses. Overall, NeuroDyn-EEG maps scalp EEG to anatomically indexed dynamical parameters, bridging representation learning and mechanistic neurophysiology. Code: https://github.com/Gnosis-Neurodynamics/NeuroDyn-EEG.
CommentsYi Cui and Tong Zhao contributed equally. Corresponding authors: Ling Zhang, Yuxiang Yan, and Bo Hong
