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

Electrocardiogram01:29

Electrocardiogram

2.3K
An electrocardiogram (ECG or EKG) is a critical diagnostic tool that records the electrical signals produced by the heart during each heartbeat. This recording is achieved through electrodes placed strategically on the arms, legs, and chest. The electrocardiograph amplifies these signals and produces 12 distinct tracings, offering a comprehensive understanding of the heart's electrical activity.
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
2.3K

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

Masked autoencoder pretraining for peripheral nerve segmentation in ultrasound images.

Scientific reports·2026
Same author

SleepPACNet: new convolutional neural network considering phase-amplitude coupling for automatic sleep stage classification using single-channel electroencephalogram.

Scientific reports·2026
Same author

Deep Learning-Based Segmentation of the Ulnar Nerve in Ultrasound Images.

Medicina (Kaunas, Lithuania)·2026
Same author

The Effect of Comprehensive and Integrative Medical Services on Patients with Degenerative Lumbar Spinal Stenosis: A Randomized Controlled Study.

Medicina (Kaunas, Lithuania)·2026
Same author

Self-supervised autoencoder network for robust heart rate extraction from noisy photoplethysmogram: Applying blind source separation to biosignal analysis.

Computers in biology and medicine·2025
Same author

Scalable ion concentration polarization dialyzer for peritoneal dialysate regeneration.

Journal of nanobiotechnology·2025

相关实验视频

Updated: Jul 4, 2025

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.8K

基于电心图的光电脉冲图的验证,使用基于U-Net的生成对抗网络生成.

Jangjay Sohn1,2, Heean Shin3, Joonnyong Lee4

  • 1Institute of Medical & Biological Engineering, Medical Research Center, Seoul National University College of Medicine, Seoul, Korea.

Journal of healthcare informatics research
|January 26, 2024
PubMed
概括

这项研究引入了一个生成对抗网络 (GAN),用于创建合成光电图 (PPG) 信号,用于检测心房动 (AF). 生成的PPG数据有效地增加了真实数据,改善了AF分类模型的性能.

关键词:
在心房动的情况下,心房动.数据增强的数据增强.生成性的对抗性网络.摄影电磁共振图 (Photoplethysmogram) 是一种光电共振图.这就是U-Net.可穿戴式医疗保健服务

更多相关视频

Human iPSC-Derived Cardiomyocyte Networks on Multiwell Micro-electrode Arrays for Recurrent Action Potential Recordings
08:53

Human iPSC-Derived Cardiomyocyte Networks on Multiwell Micro-electrode Arrays for Recurrent Action Potential Recordings

Published on: July 15, 2019

11.6K
Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
10:17

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Published on: April 11, 2025

575

相关实验视频

Last Updated: Jul 4, 2025

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

1.8K
Human iPSC-Derived Cardiomyocyte Networks on Multiwell Micro-electrode Arrays for Recurrent Action Potential Recordings
08:53

Human iPSC-Derived Cardiomyocyte Networks on Multiwell Micro-electrode Arrays for Recurrent Action Potential Recordings

Published on: July 15, 2019

11.6K
Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
10:17

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Published on: April 11, 2025

575

科学领域:

  • 生物医学工程 生物医学工程
  • 医疗保健中的人工智能
  • 心血管信号处理系统

背景情况:

  • 光电流图 (PPG) 对于检测心房动 (AF) 是至关重要的.
  • 一个显著的局限性是公开可用的AF PPG数据集的稀缺性.
  • 这种数据缺口阻碍了AF检测算法的开发和验证.

研究的目的:

  • 开发一种新的生成对抗网络 (GAN),用于从心电图 (ECG) 数据中合成现实的PPG信号.
  • 与参考数据相比,评估生成的PPG信号的形态相似性和生理相关性.
  • 评估合成PPG数据在增强真实AF PPG数据集中的实用性,以提高AF分类模型的性能.

主要方法:

  • 基于U-net的生成对抗网络 (GAN) 用于从配对的心电图记录中合成PPG信号.
  • 使用百分根平均平方差 (PRD) 和皮尔森相关系数来量化形态相似性.
  • 进行了心率变化 (HRV) 分析,以比较生成的PPG与参考心电图.
  • 经过训练,分类模型使用现实和生成的AF PPG数据的各种组合来评估性能.

主要成果:

  • 生成的PPG信号与参考PPG具有很高的形态相似性,平均PRD为27%,Pearson相关性为0.94.
  • 在参考AF心电图和生成PPG (p=0.248) 之间没有观察到心率变化 (HRV) 的显著差异.
  • 使用增强数据集 (真实+生成的PPG) 训练的AF分类模型实现了高测试准确率 (0.962) 和F1得分 (0.969),与仅在真实数据上训练的模型 (准确率0.961) 相比.
  • 仅在生成的AF PPG数据上训练的模型表现出0.945的测试准确性,证实了合成数据的价值.

结论:

  • 提出的基于GAN的方法成功地从ECG中合成了生理上相关的AF PPG信号.
  • 生成的AF PPG数据可以有效地增强有限的现实世界数据集.
  • 合成数据对于训练强大的AF检测分类器非常有价值,解决了数据稀缺的挑战.