Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Pseudocapsule status combined with pathological parameters predicts prognosis in renal cell carcinoma.

Frontiers in oncology·2026
Same author

A regulatory 24-bp insertion at the BCO2 gene region is associated with yellow skin in chickens.

Genetics, selection, evolution : GSE·2026
Same author

Neutrophil EMR3 dynamics in critically ill patients with sepsis: an ICU experience.

Critical care (London, England)·2026
Same author

Decision-analytic models in the economic evaluation of community health worker programmes globally: a systematic review.

BMJ global health·2026
Same author

MMTF-DTI: Drug-target interaction prediction via multimodal feature extraction and dynamic fusion.

Journal of biomedical informatics·2026
Same author

Reduced left dorsolateral prefrontal activation and right inferior frontal de-oxygenation differ between psychotic and non-psychotic adolescent depression during verbal fluency.

Frontiers in psychiatry·2026

相关实验视频

Updated: Feb 28, 2026

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
09:57

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

3.7K

基于EEG的发作检测多尺度内核和电极注意网络.

Zheng Hu1, Renhui Yi2, Yuting Li3

  • 1Department of Neurosurgery, The First Affiliated Hospital of Gannan Medical University, Ganzhou, 341000, Jiangxi, China; First Clinical Medical College, Gannan Medical University, Ganzhou, 341000, Jiangxi, China.

Computers in biology and medicine
|February 26, 2026
PubMed
概括

一个新的深度学习模型,多尺度内核和电极注意网络 (MKEANet),使用全电脑图 (EEG) 信号准确检测发作. 这种方法避免了信息丢失,并提高了神经系统疾病的诊断效率.

关键词:
频道注意力 频道注意力这是一个EEGEEGEEGEEGEEG.发作检测的检测方法多个尺度的卷积.

更多相关视频

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.4K
Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

8.4K

相关实验视频

Last Updated: Feb 28, 2026

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
09:57

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

3.7K
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.4K
Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

8.4K

科学领域:

  • 神经学 神经学
  • 人工智能的人工智能
  • 生物医学工程 生物医学工程

背景情况:

  • 是一种常见的神经系统疾病,需要有效的诊断工具.
  • 使用脑电图 (EEG) 进行自动发作检测对于临床实践至关重要.
  • 目前用于EEG分析的深度学习方法面临信息丢失或高计算成本等局限性.

研究的目的:

  • 开发一个新的深度学习网络,以准确有效地检测发作.
  • 通过处理全通道EEG信号而没有减少或转换来克服现有方法的局限性.
  • 增强特征表示和歧视能力,以改善发作检测.

主要方法:

  • 提出了多尺度内核和电极注意网络 (MKEANet),这是一个基于原始,全频道EEG数据运行的端到端网络.
  • 利用多尺度的卷积结构来捕捉不同的电极通道组合,并适应时间波形变化.
  • 引入了电极注意模块 (EAM) 来适应加重通道并增强空间建模.

主要成果:

  • 在两个公共数据集 (CHB-MIT和Siena Scalp) 上,MKEANet实现了最先进的性能.
  • 在CHB-MIT数据集上实现了99.29%的准确性,98.29%的灵敏性和99.59%的特异性.
  • 在锡耶纳头皮数据集上实现了99.42%的准确性,98.69%的灵敏性和99.54%的特异性.

结论:

  • MKEANet有效地检测发作使用原始,全通道EEG信号,没有信息丢失.
  • 网络的设计,包括多尺度的核心和电极注意力,增强了空间和时间特征的提取.
  • 在资源有限的环境中表现出卓越的性能,为诊断提供了一个有前途的工具.