Scholarlink

<p>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 16 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 best. We then improve its performance by employing residual connections and data augmentation strategies combining amplitude scaling, Gaussian noise injection, and signal inversion to enhance cross-subject generalization. Our proposed model, AugUNet1D, achieves an average F1-score of 0.90 with balanced precision (0.91) and recall (0.90), representing a 29% relative improvement over the “Twin Peaks” algorithmic baseline and exceptional cross-subject performance. AugUNet1D, pretrained on our manually annotated data, along with the dataset itself, is made public for other users.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Combining residual U-Net and data augmentation for dense temporal segmentation of spike wave discharges in single-channel EEG

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月21日

查看全文
  • Saurav Sengupta,
  • Scott Kilianski,
  • Suchetha Sharma,
  • Sakina Lashkeri,
  • Ashley McHugh,
  • Mark Beenhakker,
  • Donald E. Brown

摘要

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 16 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 best. We then improve its performance by employing residual connections and data augmentation strategies combining amplitude scaling, Gaussian noise injection, and signal inversion to enhance cross-subject generalization. Our proposed model, AugUNet1D, achieves an average F1-score of 0.90 with balanced precision (0.91) and recall (0.90), representing a 29% relative improvement over the “Twin Peaks” algorithmic baseline and exceptional cross-subject performance. AugUNet1D, pretrained on our manually annotated data, along with the dataset itself, is made public for other users.