通过自监督对比学习，用脑电波频段差异提升阿尔茨海默病检测准确率
Delta2Gamma: Band-Wise Adaptive Contrastive Learning of EEG for Alzheimer's Disease Detection
- 将脑电信号按五种频段分解，分别建模并自适应调节对比学习温度
- 在独立受试者留一法验证下，诊断准确率达92.4%，优于现有方法
- 适合需要高精度、低成本筛查的临床场景，尤其适用于资源有限地区
低成本、可扩展的痴呆症筛查仍是未解难题。影像学诊断成本高且难广泛部署。脑电图（EEG）便携且廉价，但其记录噪声大、个体差异显著，且缺乏充分临床标签。我们提出Delta2Gamma，一种自监督框架，通过对比同一信号的不同增强视图来学习脑电表示。不同于将脑电视为单一数据流，该方法将每条记录分解为五种经典神经节律（delta、theta、alpha、beta、gamma）。每个频段配备独立编码器与投影头，并在对比训练中自适应预测温度，自动平衡不同频段的统计差异。在严格留一受试者分割的ADFTD队列上，该模型实现阿尔茨海默病与认知正常对照组92.4%的分类准确率，超越了监督基线与近期专用脑电方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。