IEEE J Biomed Health Inform. 2024 Nov;28(11):6486-6497. doi: 10.1109/JBHI.2024.3443651. Epub 2024 Nov 6.
Annotated electroencephalogram (EEG) data is the prerequisite for artificial intelligence-driven EEG autoanalysis. However, the scarcity of annotated data due to its high-cost and the resulted insufficient training limits the development of EEG autoanalysis. Generative self-supervised learning, represented by masked autoencoder, offers potential but struggles with non-Euclidean structures. To alleviate these challenges, this work proposes a self-supervised graph masked autoencoder for EEG representation learning, named GMAEEG. Concretely, a pretrained model is enriched with temporal and spatial representations through a masked signal reconstruction pretext task. A learnable dynamic adjacency matrix, initialized with prior knowledge, adapts to brain characteristics. Downstream tasks are achieved by finetuning pretrained parameters, with the adjacency matrix transferred based on task functional similarity. Experimental results demonstrate that with emotion recognition as the pretext task, GMAEEG reaches superior performance on various downstream tasks, including emotion, major depressive disorder, Parkinson's disease, and pain recognition. This study is the first to tailor the masked autoencoder specifically for EEG representation learning considering its non-Euclidean characteristics. Further, graph connection analysis based on GMAEEG may provide insights for future clinical studies.
带注释的脑电图 (EEG) 数据是人工智能驱动的 EEG 自动分析的前提。然而，由于其成本高，注释数据的稀缺以及由此导致的训练不足限制了 EEG 自动分析的发展。生成式自监督学习以掩蔽自动编码器为代表，具有潜力，但在处理非欧几里得结构时存在困难。为了缓解这些挑战，本工作提出了一种用于 EEG 表示学习的自监督图掩蔽自动编码器，称为 GMAEEG。具体来说，通过掩蔽信号重建的预备任务，在预训练模型中丰富了时间和空间表示。一个可学习的动态邻接矩阵，通过先验知识初始化，适应大脑特征。通过微调预训练参数来实现下游任务，邻接矩阵根据任务功能相似性进行转移。实验结果表明，以情绪识别作为预备任务，GMAEEG 在各种下游任务（包括情绪、重度抑郁症、帕金森病和疼痛识别）上都取得了优异的性能。本研究首次针对 EEG 表示学习专门设计了掩蔽自动编码器，考虑到其非欧几里得特征。此外，基于 GMAEEG 的图连接分析可能为未来的临床研究提供见解。
