面向信号级、脑状态及脑健康任务的广谱脑电分析：以不变性为导向的预训练驯服基础模型
Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks
浏览论文内容
中文总结 AI 辅助
研究针对EEG模型的局限性，提出以不变性为导向的EEG基础模型INCEPT，经超11000小时临床EEG训练，在广谱EEG任务基准中多数指标领先，验证了不变性学习构建可复用EEG基础模型的潜力。
中文摘要 AI 辅助
脑电图（EEG）是探究人类脑功能的常用窗口，但多数EEG模型仍局限于“一个数据集对应一个模型”的监督范式。近期EEG基础模型为可复用表征提供了途径，但多数以重构为中心，假设局部上下文可预测的EEG内容必然是可迁移的神经信息。本文提出INCEPT，一种以不变性为导向的EEG基础模型，基于超过11000小时的未标记临床EEG训练。INCEPT不仅优先考虑信号恢复，而是在相关EEG观测中学习表征层面的稳定性，将稳定的神经结构和关键的受试者敏感信息与头皮记录中占主导的干扰变异性分离，同时保留受试者、状态及条件的判别信息。我们在涵盖采集后EEG分析三个层级的10个数据集组成的广谱基准上评估INCEPT：信号级评估、脑状态解码和脑健康评估。INCEPT在30个线性探测指标中26个排名第一，在30个微调指标中24个排名第一，且在多种下游场景中优于强大的任务专用专用编码器。客观消融实验和表征分析进一步表明，以不变性为导向的预训练在重构之外提升了可迁移性并组织了受试者敏感的神经表征。这些结果确立了不变性学习是构建可复用EEG基础模型的有前景原则。
英文摘要
Electroencephalography (EEG) is a widely used window into human brain function, but most EEG models remain tied to a one-dataset-one-model supervised paradigm. Recent EEG foundation models offer a route toward reusable representations, but most remain reconstruction-centered, assuming that EEG content predictable from local context is necessarily transferable neural information. Here we present INCEPT, an invariance-oriented EEG foundation model trained on over 11,000 hours of unlabelled clinical EEG. Rather than prioritizing signal recovery alone, INCEPT learns representation-level stability across correlated EEG observations, separating stable neural structure and essential subject-sensitive information from the nuisance variability that dominates scalp recordings while preserving subject-, state- and condition-discriminative information. We evaluate INCEPT on a broad-spectrum benchmark of ten datasets spanning three levels of post-acquisition EEG analysis: signal-level assessment, brain-state decoding, and brain-health evaluation. INCEPT ranks first among recent EEG foundation models on 26 of 30 linear-probing metrics and 24 of 30 fine-tuning metrics, and also surpasses strong task-specific specialist encoders across diverse downstream settings. Objective ablations and representation analyses further show that invariance-oriented pre-training improves transfer and organizes subject-sensitive neural representations beyond reconstruction alone. These results establish invariance learning as a promising principle for building reusable EEG foundation models.
发表机构
- ShanghaiTech University（上海科技大学）
- Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司）
- Shanghai Clinical Research and Trial Center（上海临床研究与试验中心）
机构由 AI 辅助整理，请以论文原文为准。
