用改进的U-Net与数据增强，提升单导联脑电中棘波放电的自动识别准确率。
Combining Residual U-Net and Data Augmentation for Dense Temporal Segmentation of Spike Wave Discharges in Single-Channel EEG
- 引入残差连接与信号幅度缩放、噪声注入等数据增强策略
- 在961小时小鼠脑电上实现平均F1分数0.90，比基线高29%
- 模型公开可用，适合癫痫电生理研究者快速部署
人工标注棘波放电（SWDs）是长期脑电监测研究中的繁重任务。尽管机器学习方法在自动化检测方面展现出潜力，但因个体间发作形态和信号特征差异大，常面临跨受试者泛化能力差的问题。本研究在自建的961小时小鼠脑电数据集（含22,637个标注的SWDs）上评估了15种机器学习分类器，发现一维U-Net表现最佳。通过引入残差连接并结合幅度缩放、高斯噪声注入和信号翻转的数据增强策略，进一步提升了模型跨受试者泛化性能。所提出的AugUNet1D方法在相同数据集上优于近期发表的基于时频分析的“Twin Peaks”算法。无论是否预训练，AugUNet1D均已公开，供其他研究者使用。
原文摘要 · Abstract (English)
Manual annotation of spike-wave discharges (SWDs), the electrographic hallmark of absence seizures, is labor-intensive for long-term electroencephalography (EEG) monitoring studies. While machine learning approaches show promise for automated detection, they often struggle with cross-subject generalization due to high inter-individual variability in seizure morphology and signal characteristics. In this study we compare the performance of 15 machine learning classifiers on our own manually annotated dataset of 961 hours of EEG recordings from C3H/HeJ mice, including 22,637 labeled SWDs and find that a 1D U-Net performs the best. We then improve its performance by employing residual connections and data augmentation strategies combining amplitude scaling, Gaussian noise injection, and signal inversion during training to enhance cross-subject generalization. We also compare our method, named AugUNet1D, to a recently published time- and frequency-based algorithmic approach called "Twin Peaks" and show that AugUNet1D performs better on our dataset. AugUNet1D, pretrained on our manually annotated data or untrained, is made public for other users.
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。