CortexBridge：面向基础模型的EEG导联布局皮层对齐
CortexBridge: Cortical Alignment of EEG Montages for Foundation Models
浏览论文内容
中文总结 AI 辅助
CortexBridge通过结合EEG特征与电极及图谱坐标的轻量适配器，将任意导联布局映射到共享皮层空间，在MOABB五个数据集上以三个冻结基础模型验证，15项评估中13项性能提升，确立可学习的解剖路由机制。
中文摘要 AI 辅助
脑电图（EEG）基础模型通常使用固定的通道词汇表或有限的导联布局进行预训练，当电极布局发生变化时，迁移变得困难。我们提出CortexBridge，一种轻量级适配器，将EEG特征与电极和图谱坐标相结合，将任意导联布局映射到共享的皮层潜在空间。在来自“所有BCI基准之母”（MOABB）的五个脑机接口（BCI）数据集上，使用三个冻结的基础模型进行评估，CortexBridge在15项评估中的13项中提升了性能。平衡准确率的提升平均为：EEGPT为0.80%，LaBraM为0.70%，CBraMod为3.26%，在12类稳态视觉诱发电位（SSVEP）分类中最大提升达13.02%。对学习到的图谱表示的可视化揭示了任务相关的空间模式，其中SSVEP在Yeo视觉网络中的表示比听觉P300更为集中。这些结果确立了皮层对齐作为一种可学习的、基于解剖学的路由机制，可将异构EEG导联布局连接到预训练基础模型。
英文摘要
Electroencephalography (EEG) foundation models are often pretrained with a fixed channel vocabulary or a limited set of montages, making transfer difficult when electrode layouts change. We propose CortexBridge, a lightweight adapter that combines EEG features with electrode and atlas coordinates to map arbitrary montages into a shared cortical latent space. Evaluated with three frozen foundation models on five brain-computer interface (BCI) datasets from the Mother of All BCI Benchmarks (MOABB), CortexBridge improves performance in 13 of 15 evaluations. The gains in balanced accuracy average 0.80% for EEGPT, 0.70% for LaBraM, and 3.26% for CBraMod, with a maximum gain of 13.02% on 12-class steady-state visual evoked potential (SSVEP) classification. Visualizations of the learned atlas representations reveal task-dependent spatial patterns, with SSVEP showing a more concentrated representation in the Yeo Visual network than auditory P300. These results establish cortical alignment as a learnable and anatomically grounded routing mechanism from heterogeneous EEG montages to pretrained foundation models.
发表机构
- Rutgers University（罗格斯大学）
机构由 AI 辅助整理，请以论文原文为准。
