一种基于卷积神经网络从3导联心电图推导标准12导联心电图的新方法

王露笛; 周葳; 邢颖; 刘娜; Mahmood MOVAHEDIPOUR; 周晓光

doi:10.1631/FITEE.1700413

Your Location：

Home >

Browse articles >

一种基于卷积神经网络从3导联心电图推导标准12导联心电图的新方法

常规文章 | Updated：2022-05-19

- 一种基于卷积神经网络从3导联心电图推导标准12导联心电图的新方法
- A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG
- 信息与电子工程前沿（英文） 2019年20卷第3期页码：405-413
- Affiliations：
  
  Automation School, Beijing University of Posts and Telecommunications, Beijing 100876, China
  Department of Neuroscience, Uppsala University, Uppsala 75105, Sweden
  School of Economic and Management, Beijing University of Posts and Telecommunications, Beijing 100876, China
  Academic Center for Education, Culture and Research (ACECR), Tehran 14155-4364, Iran
- Author bio：
  
  Xiao-guang ZHOU, E-mail: zxg_bupt@126.com
- Funds：
  
  Project supported by the National Natural Science Foundation of China (No. 6170204), the Fundamental Research Funds for the Central Universities, China (No. 2017RC27), and the BUPT Excellent Ph.D. Students Foundation
- DOI：10.1631/FITEE.1700413
  中图分类号： TP18;R540.4+1
- 收稿：2017-06-22，
  
  修回：2019-;3-14，
  
  纸质出版：2019-03
- Accepted：
Scan QR Code
王露笛, 周葳, 邢颖, 等. 一种基于卷积神经网络从3导联心电图推导标准12导联心电图的新方法[J]. 信息与电子工程前沿（英文）, 2019,20(3):405-413.

Lu-di WANG, Wei ZHOU, Ying XING, et al. A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(3): 405-413.
王露笛, 周葳, 邢颖, 等. 一种基于卷积神经网络从3导联心电图推导标准12导联心电图的新方法[J]. 信息与电子工程前沿（英文）, 2019,20(3):405-413. DOI： 10.1631/FITEE.1700413.

Lu-di WANG, Wei ZHOU, Ying XING, et al. A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(3): 405-413. DOI： 10.1631/FITEE.1700413.

摘要

为满足人们佩戴舒适性和行走环境的需求，研究人员对从3导联心电图重建12导联心电图（electrocardiogram，ECG）方法进行了一系列研究。然而，传统方法精度和实时性有待提高。本文提出一种基于卷积神经网络（convolutional neural network，CNN）的导联重构方法。使用PTB数据库进行实验分析，结果表明，该方法重构的心电信号与真实信号之间具有较高相似性和训练效率。该方法在重建病理性心电信号时的表现优于传统算法，对心脏诊断具有重要意义。该方法能够在院外环境下部署，并且能够从较少导联心电图合成标准12导联心电图，对于心脏护理具有重要意义。

Abstract

Reconstruction of a 12-lead electrocardiogram (ECG) from a serial 3-lead ECG has been researched in the past to satisfy the need for more wearing comfort and ambulatory situations. The accuracy and real-time performance of traditional methods need to be improved. In this study

we present a novel method based on convolutional neural networks (CNNs) for the synthesis of missing precordial leads. The results show that the proposed method receives better similarity and consumes less time using the PTB database. Particularly

the presented method shows outstanding performance in reconstructing the pathological ECG signal

which is crucial for cardiac diagnosis. Our CNN-based method is shown to be more accurate and time-saving for deployment in non-hospital situations to synthesize a standard 12-lead ECG from a reduced lead-set ECG recording. This is promising for real cardiac care.

关键词

Keywords

references

PS Addison . . Wavelet transforms and the ECG: a review . . Physiol Meas , , 2005 . . 26 ( ( 5 ): ): R155 - - R199 . . DOI: 10.1088/0967-3334/26/5/R01 http://doi.org/10.1088/0967-3334/26/5/R01 . .

H Atoui , , , J Fayn , , , P Rubel . . A neural network approach for patient-specific 12-lead ECG synthesis in patient monitoring environments . . Proc Computers in Cardiology , , 2004 . . p.161 - - 164 . . DOI: 10.1109/CIC.2004.1442896 http://doi.org/10.1109/CIC.2004.1442896 . .

H Atoui , , , J Fayn , , , P Rubel . . A novel neural-network model for deriving standard 12-lead ECGs from serial three-lead ECGs: application to self-care . . IEEE Trans Inform Technol Biomed , , 2010 . . 14 ( ( 3 ): ): 883 - - 890 . . DOI: 10.1109/TITB.2010.2047754 http://doi.org/10.1109/TITB.2010.2047754 . .

M Bojarski , , , Testa D Del , , , D Dworakowski , , , 等 . . End to end learning for self-driving cars , , 2016 . . https://arxiv.org/abs/1604.07316 https://arxiv.org/abs/1604.07316 , , . .

R Bousseljot , , , D Kreiseler , , , A Schnabel . . Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet . . Biomedizinische Technik, Band 40, Ergänzungsband , , 1995 . . 1 S 317 . .

D Ciregan , , , U Meier , , , J Schmidhuber . . Multi-column deep neural networks for image classification . . Proc IEEE Conf on Computer Vision and Pattern Recognition , , 2012 . . p.3642 - - 3649 . . DOI: 10.1109/CVPR.2012.6248110 http://doi.org/10.1109/CVPR.2012.6248110 . .

BJ Drew , , , MM Pelter , , , SF Wung , , , 等 . . Accuracy of the EASI 12-lead electrocardiogram compared to the standard 12-lead electrocardiogram for diagnosing multiple cardiac abnormalities . . J Electrocardiol , , 1999 . . 32 ( ( S1 ): ): 38 - - 47 . . DOI: 10.1016/S0022-0736(99)90033-X http://doi.org/10.1016/S0022-0736(99)90033-X . .

RPW Duin . . Learned from neural networks . . Proc 6 th Annual Conf of the Advanced School for Computing and Imaging , , 2000 . . p.9 - - 13 . . . .

S Ettl , , , J Kaminski , , , MC Knauer , , , 等 . . Shape reconstruction from gradient data . . Appl Opt , , 2008 . . 47 ( ( 12 ): ): 2091 - - 2097 . . DOI: 10.1364/AO.47.002091 http://doi.org/10.1364/AO.47.002091 . .

E Frank . . An accurate, clinically practical system for spatial vectorcardiography . . Circulation , , 1956 . . 13 ( ( 5 ): ): 737 - - 749 . . DOI: 10.1161/01.CIR.13.5.737 http://doi.org/10.1161/01.CIR.13.5.737 . .

A Gacsádi , , , P Szolgay . . Variational computing based segmentation methods for medical imaging by using CNN . . Proc 12 th Int Workshop on Cellular Nanoscale Networks and Their Applications , , 2010 . . p.1 - - 6 . . DOI: 10.1109/CNNA.2010.5430256 http://doi.org/10.1109/CNNA.2010.5430256 . .

AL Goldberger , , , LAN Amaral , , , L Glass , , , 等 . . Physio- Bank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals . . Circulation , , 2000 . . 101 ( ( 23 ): ): e215 - - e220 . . DOI: 10.1161/01.CIR.101.23.e215 http://doi.org/10.1161/01.CIR.101.23.e215 . .

RM Gulrajani . . The forward and inverse problems of electrocardiography . . IEEE Eng Med Biol Mag , , 1998 . . 17 ( ( 5 ): ): 84 - - 101 . . DOI: 10.1109/51.715491 http://doi.org/10.1109/51.715491 . .

BM Horácek , , , JW Warren , , , DQ Feild , , , 等 . . Statistical and deterministic approaches to designing transformations of electrocardiographic leads . . J Electrocardiol , , 2002 . . 35 ( ( 4 ): ): 41 - - 52 . . DOI: 10.1054/jelc.2002.37154 http://doi.org/10.1054/jelc.2002.37154 . .

DH Hubel , , , TN Wiesel . . Receptive fields of single neurones in the catos striate cortex . . J Physiol , , 1959 . . 148 ( ( 3 ): ): 574 - - 591 . . DOI: 10.1113/jphysiol.1959.sp006308 http://doi.org/10.1113/jphysiol.1959.sp006308 . .

JA Kors , , , G van Herpen . . Computer analysis of the electrocardiogram . . In: Macfarlane PW, van Oosterom A, Pahlm O, et al. (Eds.), Comprehensive Electrocardiology. Springer, London , , 2010 . . 1721 - - 1765 . . DOI: 10.1007/978-1-84882-046-3_37 http://doi.org/10.1007/978-1-84882-046-3_37 . .

A Krizhevsky , , , I Sutskever , , , GE Hinton . . ImageNet classification with deep convolutional neural networks . . Proc 25 th Int Conf on Neural Information Processing Systems , , 2012 . . 1097 - - 1105 . . . .

Y LeCun , , , B Boser , , , JS Denker , , , 等 . . Handwritten digit recognition with a back-propagation network . . In: Touretzky DS (Ed.), Advances in Neural Information Processing Systems. Morgan Kaufmann Publishers Inc., San Francisco, USA , , 1990 . . p.396 - - 404 . . . .

H Lee , , , R Grosse , , , R Ranganath , , , 等 . . Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations . . Proc 26 th Annual Int Conf on Machine Learning , , 2009 . . p.609 - - 616 . . DOI: 10.1145/1553374.1553453 http://doi.org/10.1145/1553374.1553453 . .

C Lu , , , ZY Wang , , , B Zhou . . Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification . . Adv Eng Inform , , 2017 . . 32 139 - - 151 . . DOI: 10.1016/j.aei.2017.02.005 http://doi.org/10.1016/j.aei.2017.02.005 . .

R Modre , , , M Seger , , , G Fischer , , , 等 . . Cardiac anisotropy: is it negligible regarding noninvasive activation time imaging . . IEEE Trans Biomed Eng , , 2006 . . 53 ( ( 4 ): ): 569 - - 580 . . DOI: 10.1109/TBME.2006.870253 http://doi.org/10.1109/TBME.2006.870253 . .

SP Nelwan . . Evaluation of 12-Lead Electrocardiogram Reconstruction Methods for Patient Monitoring . . PhD Thesis, Erasmus University Rotterdam, Rotterdam, Holland. , , 2005 . . .

SP Nelwan , , , SH Meij . . Derived 12-lead ECG systems . . J Electrocardiol , , 2006 . . 39 ( ( 1 ): ): 29 - - 30 . . DOI: 10.1016/j.jelectrocard.2005.06.013 http://doi.org/10.1016/j.jelectrocard.2005.06.013 . .

SP Nelwan , , , JA Kors , , , SH Meij , , , 等 . . Reconstruction of the 12-lead electrocardiogram from reduced lead sets . . J Electrocardiol , , 2004 . . 37 ( ( 1 ): ): 11 - - 18 . . DOI: 10.1016/j.jelectrocard.2003.10.004 http://doi.org/10.1016/j.jelectrocard.2003.10.004 . .

RB Palm . . Prediction as a Candidate for Learning Deep Hierarchical Models of Data . . MS Thesis, Technical University of Denmark, Lyngby, Denmark. , , 2012 . . .

JP Pan , , , WJ Tompkins . . A real-time QRS detection algorithm . . IEEE Trans Biomed Eng , , 1985 . . BME-32 ( ( 3 ): ): 230 - - 236 . . DOI: 10.1109/TBME.1985.325532 http://doi.org/10.1109/TBME.1985.325532 . .

JA Scherer , , , JM Jenkins , , , JM Nicklas . . Synthesis of the 12-lead electrocardiogram from a 3-lead subset using patient-specific transformation vectors: an algorithmic approach to computerized signal synthesis . . J Electrocardiol , , 1990 . . 22 ( ( S1 ): ): 128 DOI: 10.1016/S0022-0736(07)80112-9 http://doi.org/10.1016/S0022-0736(07)80112-9 . .

T Serre , , , L Wolf , , , S Bileschi , , , 等 . . Robust object recognition with cortex-like mechanisms . . IEEE Trans Patt Anal Mach Intell , , 2007 . . 29 ( ( 3 ): ): 411 - - 426 . . DOI: 10.1109/TPAMI.2007.56 http://doi.org/10.1109/TPAMI.2007.56 . .

HC Shin , , , HR Roth , , , MC Gao , , , 等 . . Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning . . IEEE Trans Med Imag , , 2016 . . 35 ( ( 5 ): ): 1285 - - 1298 . . DOI: 10.1109/TMI.2016.2528162 http://doi.org/10.1109/TMI.2016.2528162 . .

N Srivastava , , , G Hinton , , , A Krizhevsky , , , 等 . . Dropout: a simple way to prevent neural networks from overfitting . . J Mach Learn Res , , 2014 . . 15 ( ( 1 ): ): 1929 - - 1958 . . . .

I Tomašić , , , R Trobec . . Electrocardiographic systems with reduced numbers of leadsjsynthesis of the 12-lead ECG . . IEEE Rev Biomed Eng , , 2014 . . 7 126 - - 142 . . DOI: 10.1109/RBME.2013.2264282 http://doi.org/10.1109/RBME.2013.2264282 . .

QX Zhang , , , D Zhou , , , X Zeng . . A novel machine learning-enabled framework for instantaneous heart rate monitoring from motion-artifact-corrupted electrocardiogram signals . . Physiol Meas , , 2016 . . 37 ( ( 11 ): ): 1945 - - 1967 . . DOI: 10.1088/0967-3334/37/11/1945 http://doi.org/10.1088/0967-3334/37/11/1945 . .

QX Zhang , , , X Zeng , , , WC Hu , , , 等 . . A machine learning- empowered system for long-term motion-tolerant wearable monitoring of blood pressure and heart rate with ear-ECG/PPG . . IEEE Access , , 2017a . . 5 10547 - - 10561 . . DOI: 10.1109/ACCESS.2017.2707472 http://doi.org/10.1109/ACCESS.2017.2707472 . .

QX Zhang , , , D Zhou , , , X Zeng . . HeartID: a multiresolution convolutional neural network for ECG-based biometric human identification in smart health applications . . IEEE Access , , 2017b . . 5 11805 - - 11816 . . DOI: 10.1109/ACCESS.2017.2707460 http://doi.org/10.1109/ACCESS.2017.2707460 . .

QX Zhang , , , D Zhou , , , X Zeng . . Machine learning- empowered biometric methods for biomedicine applications . . AIMS Med Sci , , 2017c . . 4 ( ( 3 ): ): 274 - - 290 . . DOI: 10.3934/medsci.2017.3.274 http://doi.org/10.3934/medsci.2017.3.274 . .

QX Zhang , , , D Zhou , , , X Zeng . . A novel framework for motion-tolerant instantaneous heart rate estimation by phase-domain multiview dynamic time warping . . IEEE Trans Biomed Eng , , 2017d . . 64 ( ( 11 ): ): 2562 - - 2574 . . DOI: 10.1109/TBME.2016.2640309 http://doi.org/10.1109/TBME.2016.2640309 . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据