近年来,自动分析脑电图(EEG)经历了一次范式转变。变压器架构和自监督预训练(SSL)的引入导致了EEG基础模型的发展。这些模型在大量未标记数据上进行预训练,可以适应各种下游任务。本系统综述总结了最近通过多通道EEG学习全脑表示的SSL训练EEG基础模型,而不是从单个通道导出的表示。我们通过2025年7月21日搜索了PubMed、IEEE Xplore、Scopus和arXiv。十九篇预印本和同行评审文章符合纳入标准。我们提取了有关预训练数据集、模型架构、预训练SSL目标和下游任务应用的信息。尽管预训练数据严重依赖Temple University EEG数据集,但各研究在模型架构和训练目标上存在显著异质性。变压器架构被识别为最主要的预训练架构,状态空间模型如MAMBA和S4作为新兴替代方案。关于SSL目标,掩码自动编码最为常见,其他研究采用对比学习。下游任务差异很大,实施了多样的微调策略,这使得直接比较具有挑战性。此外,大多数研究使用单任务微调,通用的EEG基础模型仍然缺乏。总之,该领域发展迅速,但仍受到数据集多样性和缺乏标准化基准的限制。进步可能依赖于更大更多样化的预训练数据集、标准化评估协议和多任务验证。发展将使EEG基础模型朝着稳健且通用的相关于基础和临床应用的方向前进。
英文摘要:
Automated analysis of electroencephalography (EEG) has recently undergone a paradigm shift. The introduction of transformer architectures and self-supervised pretraining (SSL) has led to the development of EEG foundation models. These models are pretrained on large amounts of unlabeled data and can be adapted to a range of downstream tasks. This systematic review summarizes recent SSL-trained EEG foundation models that learn whole-brain representations from multichannel EEG rather than representations derived from a single channel. We searched PubMed, IEEE Xplore, Scopus, and arXiv through July 21, 2025. Nineteen preprints and peer-reviewed articles met inclusion criteria. We extracted information regarding pretraining datasets, model architectures, pretraining SSL objectives, and downstream task applications. While pretraining data heavily relied on the Temple University EEG corpus, there was significant heterogeneity in model architecture and training objectives across studies. Transformer architectures were identified as the predominant pretraining architecture with state-space models such as MAMBA and S4 as emerging alternatives. Concerning SSL objectives, masked auto-encoding was most common, and other studies incorporate contrastive learning. Downstream tasks varied widely and implemented diverse fine-tuning strategies, which made direct comparison challenging. Furthermore, most studies used single-task fine-tuning, and a generalizable EEG foundation model remains lacking. In conclusion, the field is advancing rapidly but still limited by limited dataset diversity and the absence of standardized benchmarks. Progress will likely depend on larger and more diverse pretraining datasets, standardized evaluation protocols, and multi-task validation. The development will advance EEG foundation models towards robust and general-purpose relevant to both basic and clinical applications.
Integration of Simultaneous Resting-State Electroencephalography, Functional Magnetic Resonance Imaging, and Eye-Tracker Methods to Determine and Verify Electroencephalography Vigilance Measure
Comparison of Epilepsy Induced by Ischemic Hypoxic Brain Injury and Hypoglycemic Brain Injury using Multilevel Fusion of Data Features
Dijlah University College(迪吉拉大学学院);Mazaya University College(马扎亚大学学院);South Valley University(南谷大学);Buraydah Private Colleges(布赖代私立学院);Gulf University(海湾大学);Northampton University(北安普顿大学);Alturath University College(图拉斯大学学院);Alfarahidi University(法拉希迪大学);The Islamic University(伊斯兰大学);Al-Kitab University(基塔布大学);Al-Mustaqbal University College(穆斯塔克巴尔大学学院);Universiti Teknikal Malaysia Melaka(马六甲马来西亚技术大学);National University of Science and Technology(国立科技大学)
Non-Invasive Reconstruction of Intracranial EEG Across the Deep Temporal Lobe from Scalp EEG based on Conditional Normalizing Flow
School of Artificial Intelligence, Chongqing University of Technology(重庆理工大学人工智能学院);School of Smart Health, Chongqing Polytechnic University of Electronic Technology(重庆电子工程职业大学智能健康学院)
Brain-DiT: A Universal Multi-state fMRI Foundation Model with Metadata-Conditioned Pretraining
Department of Biomedical Engineering, Southern University of Science and Technology, China(南方科技大学生物医学工程系,中国);School of Biomedical Engineering, Shenzhen University, China(深圳大学生物医学工程学院,中国)
SLIM-Brain: A Data- and Training-Efficient Foundation Model for fMRI Data Analysis
Department of Biomedical Engineering, Southern University of Science and Technology, China(南方科技大学生物医学工程系);Department of Computer Science, University of Warwick, The UK(沃里克大学计算机科学系);Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, China(复旦大学脑启发式智能科学技术研究所)
BrainSymphony: A parameter-efficient multimodal foundation model for brain dynamics with limited data
Turner Institute for Brain and Mental Health(大脑与心理健康Turner研究所);School of Psychological Sciences, Monash University(墨尔本大学心理学科学学院);Cortical Labs(皮层实验室);CIFAR Azrieli Global Scholars Program(CIFAR阿兹里埃利全球学者计划)
BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait Prediction
Department of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术系);School of Intelligence Science and Engineering, College of Artificial Intelligence, Harbin Institute of Technology(哈尔滨工业大学智能科学与工程学院);School of Biomedical Engineering, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical, Measurements and Ultrasound Imaging, Shenzhen University Medical School, Shenzhen University(深圳大学医学院生物医学工程学院);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
BrainCSD 提出层次一致性驱动的 MoE 基础模型,通过 ROI 特异性、编码-激活和网络感知细化三个组件联合合成 FC/SC 并支持多任务预测,在缺失模态下取得 SOTA 性能。
BrainWave: A Brain Signal Foundation Model for Clinical Applications
Computer Science and Technology(计算机科学与技术);Zhejiang University(浙江大学);Chinese Academy of Sciences(中国科学院);INSIDE Institute for Biological and Artificial Intelligence(生物与人工智能研究所);Research Institute of Intelligent and Complex Systems(智能与复杂系统研究所);Fudan University(复旦大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Chicago(芝加哥大学)
Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
Hertie Institute for AI in Brain Health, University of Tübingen(图宾根大学脑健康人工智能研究所);Tübingen AI Center, University of Tübingen(图宾根大学图宾根人工智能中心);Charité – Universitätsmedizin Berlin, Department of Psychiatry and Psychotherapy(柏林夏里特医学院心理治疗系)
CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Sun Yat-sen University(中山大学);The Chinese University of Hong Kong(香港中文大学);Karlsruher Institut fur Technologie(卡尔斯鲁厄理工学院)