基于卷积神经网络重建十二导联心电图

朱晓铭; 陈林海; 张帅; 王云峰

Chinese

您当前的位置：

首页 >

文章列表页 >

基于卷积神经网络重建十二导联心电图

更新时间：2026-09-04

- 基于卷积神经网络重建十二导联心电图
- 12-lead ECG reconstruction using convolutional neural network
- 微电子学与计算机 2019年36卷第9期页码：12-15
- 作者机构：
  
  1. 中国科学院微电子研究所,北京,100029
  2. 中国科学院大学机构,北京,101408
  3. 新一代通信射频芯片技术北京市重点实验室,北京,100029
- 作者简介：
- 基金信息：
  
  国家重点研发计划 2018YFC200230国家自然基金 61571437可穿戴智能心电分析诊断系统 19SYXHZ0058
- DOI：
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
朱晓铭, 陈林海, 张帅, 王云峰. 基于卷积神经网络重建十二导联心电图[J]. 微电子学与计算机, 2019, 36(9): 12-15.

ZHU Xiao-ming, CHEN Lin-hai, ZHANG Shuai, et al. 12-lead ECG reconstruction using convolutional neural network[J]. 2019, 36(9): 12-15.
朱晓铭, 陈林海, 张帅, 王云峰. 基于卷积神经网络重建十二导联心电图[J]. 微电子学与计算机, 2019, 36(9): 12-15. DOI：

ZHU Xiao-ming, CHEN Lin-hai, ZHANG Shuai, et al. 12-lead ECG reconstruction using convolutional neural network[J]. 2019, 36(9): 12-15. DOI：

摘要

由矢量心电图衍生标准十二导联心电图的传统方法是Dower转换

由于模型过于简单

在心电图细节方面重建效果不佳.为了提高衍生效果

提出一种基于卷积神经网络的衍生方法.首先采用卷积自编码器获取Frank正交导联心电图的高级语义

然后利用卷积神经网络实现从编码层重建标准十二导联心电图.最后采用R2和相关系数作为评判标准来分析结果

均明显优于传统算法

这充分证明了采用卷积神经网络衍生心电图这一方法的有效性和优异性.

Abstract

The tradition reconstruction of the convolutional 12-lead electrocardiography(ECG) is Dower transform

but the model is too simple that the performance about detail is poor. To improve the performance

we raise a new way for reconstruction based on convolutional neural networks(CNN). At first

in order to get the high semantic of the Frank XYZ-lead ECG

we train one auto-encoder model (AE) based on convolutional neural networks. Then we train an CNN model for reconstructing 12-lead of which the input layer is the encoder layer of the AE. At last

to judge the performance of the model

R2 and percent correlation are adopted for evaluating the results. The result proves that CNN model is quite suitable and outstanding.

关键词

Keywords

references

DAWSON D, YANG H, MALSHE M, et al. Linear affine transformations between 3-lead (Frank XYZ leads) vectorcardiogram and 12-lead electrocardiogram signals[J]. Journal of Electrocardiology, 2009, 42(6):622-630. DOI: 622

HECHT NIELSEN. Theory of the backpropagation neural network[C]// International 1989 Joint Conference on Neural Networks. San Diego, California, IEEE, 1989.

MAHESHWARI S, ACHARYYA A, SCHIARITI M, et al. Frank vectorcardiographic system from standard 12 lead ECG: An effort to enhance cardiovascular diagnosis[J]. Journal of Electrocardiology, 2016, 49(2):231-242. DOI: 231

TSOURI G R, OSTERTAG M H. Patient-Specific 12-Lead ECG reconstruction from sparse electrodes using independent component analysis[J]. IEEE Journal of Biomedical and Health Informatics, 2014, 18(2):476-482. DOI: 476

DOWER G E. A lead synthesizer for the Frank system to simulate the standard 12-lead electrocardiogram.[J]. Journal of Electrocardiology, 1968, 1(1):101-116. DOI: 101

陈岩, 李洋洋, 余乐, et al.基于卷积神经网络的手写体数字识别系统[J].微电子学与计算机, 2018, 35(2):71-74. DOI: 71

朱锡祥, 刘凤山, 张超, 等.基于一维卷积神经网络的车载语音识别研究[J].微电子学与计算机, 2017(11):21-25. DOI: 21

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006(313):504 - 507. DOI: 504

ACHARYA U R, FUJITA H, LIH O S, et al. Automated detection of arrhythmias using different intervals of tachycardia ecg segments with convolutional neural network[J]. Information Sciences, 2017: 405. DOI:10.1016/j.ins.2017.04.012

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. USA, Curran Associates Inc. 2012.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

结合经度加权的球形感知全景图像显著性预测算法

基于分块子图的CNN推理任务划分与存储调度算法

应用于锂电池SOC估计的PCNN_LSTM硬件加速器设计

基于U-Net网络结构的SAR图像去噪算法研究

轻量级(2+1)D卷积结构的动态手势识别研究