Delta2Gamma：面向阿尔茨海默病检测的脑电信号频带自适应对比学习
Delta2Gamma: Band-Wise Adaptive Contrastive Learning of EEG for Alzheimer's Disease Detection
- Korea University（高丽大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Delta2Gamma是一种自监督EEG表征学习框架，通过分解EEG为5个神经节律并自适应平衡各频带，在ADFTD队列上以92.4%的准确率实现阿尔茨海默病检测，性能优于相关方法。
AI中文摘要：
痴呆症的低成本、可扩展筛查仍是未解决的问题，基于成像的诊断成本高昂且难以广泛部署。脑电信号（EEG）便携且成本低，但其记录存在噪声、跨受试者差异大且临床标签少。我们提出Delta2Gamma，这是一种自监督框架，通过对比每个信号的增强视图从未标记数据中学习EEG表征。该框架不将EEG视为单一数据流，而是将每个记录分解为五个典型神经节律（delta、theta、alpha、beta、gamma），每个频带拥有独立的编码器和投影头，还会在对比训练期间自适应预测温度，自动平衡具有不同信号统计特性的频带。在ADFTD队列采用严格的留一受试者协议下，Delta2Gamma以92.4%的准确率区分阿尔茨海默病患者与认知正常对照，超过了监督骨干网络和近期专用EEG方法。
英文摘要：
Low-cost, scalable screening for dementia remains an open problem. Imaging-based diagnosis is costly and hard to deploy widely. Electroencephalography (EEG) is portable and inexpensive, but its recordings are noisy, vary widely across subjects, and carry few clinical labels. We tackle this with Delta2Gamma, a self-supervised framework that learns EEG representations from unlabeled data by contrasting augmented views of each signal. Rather than treat EEG as a single stream, Delta2Gamma decomposes every recording into the five canonical neural rhythms (delta, theta, alpha, beta, gamma). Each band gets its own encoder and projection head. Each also gets a temperature that is predicted adaptively during contrastive training, so bands with different signal statistics are balanced automatically. On the ADFTD cohort under a strict leave-one-subject-out protocol, Delta2Gamma separates Alzheimer's disease from cognitively normal controls with 92.4\% accuracy. This exceeds both supervised backbones and recent dedicated EEG methods.
