Advertisement

A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG

  • Lu-di Wang
  • Wei Zhou
  • Ying Xing
  • Na Liu
  • Mahmood Movahedipour
  • Xiao-guang ZhouEmail author
Article
  • 60 Downloads

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.

Key words

Convolutional neural networks (CNNs) Electrocardiogram (ECG) synthesis E-health 

CLC number

TP18 R540.4+1 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Addison PS, 2005. Wavelet transforms and the ECG: a review. Physiol Meas, 26(5):R155–R199. https://doi.org/10.1088/0967-3334/26/5/R01 CrossRefGoogle Scholar
  2. Atoui H, Fayn J, Rubel P, 2004. A neural network approach for patient-specific 12-lead ECG synthesis in patient monitoring environments. Proc Computers in Cardiology, p.161–164.  https://doi.org/10.1109/CIC.2004.1442896
  3. Atoui H, Fayn J, Rubel P, 2010. 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, 14(3):883–890.  https://doi.org/10.1109/TITB.2010.2047754 CrossRefGoogle Scholar
  4. Bojarski M, Del Testa D, Dworakowski D, et al., 2016. End to end learning for self-driving cars. https://doi.org/arxiv.org/abs/1604.07316
  5. Bousseljot R, Kreiseler D, Schnabel, A, 1995. Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomedizinische Technik, Band 40, Ergänzungsband sa1, S 317.Google Scholar
  6. Ciregan D, Meier U, Schmidhuber J, 2012. Multi-column deep neural networks for image classification. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.3642–3649.  https://doi.org/10.1109/CVPR.2012.6248110
  7. Drew BJ, Pelter MM, Wung SF, et al., 1999. Accuracy of the EASI 12-lead electrocardiogram compared to the standard 12-lead electrocardiogram for diagnosing multiple cardiac abnormalities. J Electrocardiol, 32(S1):38–47.  https://doi.org/10.1016/S0022-0736(99)90033-X CrossRefGoogle Scholar
  8. Duin RPW, 2000. Learned from neural networks. Proc 6th Annual Conf of the Advanced School for Computing and Imaging, p.9–13.Google Scholar
  9. Ettl S, Kaminski J, Knauer MC, et al., 2008. Shape reconstruction from gradient data. Appl Opt, 47(12):2091–2097.  https://doi.org/10.1364/AO.47.002091 CrossRefGoogle Scholar
  10. Frank E, 1956. An accurate, clinically practical system for spatial vectorcardiography. Circulation, 13(5):737–749.  https://doi.org/10.1161/01.CIR.13.5.737 CrossRefGoogle Scholar
  11. Gacsádi A, Szolgay P, 2010. Variational computing based segmentation methods for medical imaging by using CNN. Proc 12th Int Workshop on Cellular Nanoscale Networks and Their Applications, p.1–6.  https://doi.org/10.1109/CNNA.2010.5430256
  12. Goldberger AL, Amaral LAN, Glass L, et al., 2000. Physio-Bank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 101(23):e215–e220.  https://doi.org/10.1161/01.CIR.101.23.e215 CrossRefGoogle Scholar
  13. Gulrajani RM, 1998. The forward and inverse problems of electrocardiography. IEEE Eng Med Biol Mag, 17(5): 84–101.  https://doi.org/10.1109/51.715491 CrossRefGoogle Scholar
  14. Horácek BM, Warren JW, Feild DQ, et al., 2002. Statistical and deterministic approaches to designing transformations of electrocardiographic leads. J Electrocardiol, 35(4):41–52.  https://doi.org/10.1054/jelc.2002.37154 CrossRefGoogle Scholar
  15. Hubel DH, Wiesel TN, 1959. Receptive fields of single neurones in the cat’s striate cortex. JPhysiol, 148(3):574–591.  https://doi.org/10.1113/jphysiol.1959.sp006308 Google Scholar
  16. Kors JA, van Herpen G, 2010. Computer analysis of the electrocardiogram. In: Macfarlane PW, van Oosterom A, Pahlm O, et al. (Eds.), Comprehensive Electrocardiology. Springer, London, p.1721–1765.  https://doi.org/10.1007/978-1-84882-046-3_37 CrossRefGoogle Scholar
  17. Krizhevsky A, Sutskever I, Hinton GE, 2012. ImageNet classification with deep convolutional neural networks. Proc 25th Int Conf on Neural Information Processing Systems, p.1097–1105.Google Scholar
  18. LeCun Y, Boser B, Denker JS, et al., 1990. 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, p.396–404.Google Scholar
  19. Lee H, Grosse R, Ranganath R, et al., 2009. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. Proc 26th Annual Int Conf on Machine Learning, p.609–616.  https://doi.org/10.1145/1553374.1553453
  20. Lu C, Wang ZY, Zhou B, 2017. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification. Adv Eng Inform, 32: 139–151.  https://doi.org/10.1016/j.aei.2017.02.005 CrossRefGoogle Scholar
  21. Modre R, Seger M, Fischer G, et al., 2006. Cardiac anisotropy: is it negligible regarding noninvasive activation time imaging. IEEE Trans Biomed Eng, 53(4):569–580.  https://doi.org/10.1109/TBME.2006.870253 CrossRefGoogle Scholar
  22. Nelwan SP, 2005. Evaluation of 12-Lead Electrocardiogram Reconstruction Methods for Patient Monitoring. PhD Thesis, Erasmus University Rotterdam, Rotterdam, Holland.Google Scholar
  23. Nelwan SP, Meij SH, 2006. Derived 12-lead ECG systems. J Electrocardiol, 39(1):29–30.  https://doi.org/10.1016/j.jelectrocard.2005.06.013 CrossRefGoogle Scholar
  24. Nelwan SP, Kors JA, Meij SH, et al., 2004. Reconstruction of the 12-lead electrocardiogram from reduced lead sets. J Electrocardiol, 37(1):11–18.  https://doi.org/10.1016/j.jelectrocard.2003.10.004 CrossRefGoogle Scholar
  25. Palm RB, 2012. Prediction as a Candidate for Learning Deep Hierarchical Models of Data. MS Thesis, Technical University of Denmark, Lyngby, Denmark.Google Scholar
  26. Pan JP, Tompkins WJ, 1985. A real-time QRS detection algorithm. IEEE Trans Biomed Eng, BME-32(3):230–236.  https://doi.org/10.1109/TBME.1985.325532 CrossRefGoogle Scholar
  27. Scherer JA, Jenkins JM, Nicklas JM, 1990. 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, 22(S1):128.  https://doi.org/10.1016/S0022-0736(07)80112-9 CrossRefGoogle Scholar
  28. Serre T, Wolf L, Bileschi S, et al., 2007. Robust object recognition with cortex-like mechanisms. IEEE Trans Patt Anal Mach Intell, 29(3):411–426.  https://doi.org/10.1109/TPAMI.2007.56 CrossRefGoogle Scholar
  29. Shin HC, Roth HR, Gao MC, et al., 2016. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imag, 35(5):1285–1298.  https://doi.org/10.1109/TMI.2016.2528162 CrossRefGoogle Scholar
  30. Srivastava N, Hinton G, Krizhevsky A, et al., 2014. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res, 15(1):1929–1958.MathSciNetzbMATHGoogle Scholar
  31. Tomašić I, Trobec R, 2014. Electrocardiographic systems with reduced numbers of leads—synthesis of the 12-lead ECG. IEEE Rev Biomed Eng, 7:126–142.  https://doi.org/10.1109/RBME.2013.2264282 CrossRefGoogle Scholar
  32. Zhang QX, Zhou D, Zeng X, 2016. A novel machine learning-enabled framework for instantaneous heart rate monitoring from motion-artifact-corrupted electrocardiogram signals. Physiol Meas, 37(11):1945–1967.  https://doi.org/10.1088/0967-3334/37/11/1945 CrossRefGoogle Scholar
  33. Zhang QX, Zeng X, Hu WC, et al., 2017a. A machine learning-empowered system for long-term motion-tolerant wearable monitoring of blood pressure and heart rate with ear-ECG/PPG. IEEE Access, 5:10547–10561.  https://doi.org/10.1109/ACCESS.2017.2707472 CrossRefGoogle Scholar
  34. Zhang QX, Zhou D, Zeng X, 2017b. HeartID: a multiresolution convolutional neural network for ECG-based biometric human identification in smart health applications. IEEE Access, 5:11805–11816.  https://doi.org/10.1109/ACCESS.2017.2707460 CrossRefGoogle Scholar
  35. Zhang QX, Zhou D, Zeng X, 2017c. Machine learning-empowered biometric methods for biomedicine applications. AIMS Med Sci, 4(3):274–290.  https://doi.org/10.3934/medsci.2017.3.274 CrossRefGoogle Scholar
  36. Zhang QX, Zhou D, Zeng X, 2017d. A novel framework for motion-tolerant instantaneous heart rate estimation by phase-domain multiview dynamic time warping. IEEE Trans Biomed Eng, 64(11):2562–2574.  https://doi.org/10.1109/TBME.2016.2640309 CrossRefGoogle Scholar

Copyright information

© Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Automation SchoolBeijing University of Posts and TelecommunicationsBeijingChina
  2. 2.Department of NeuroscienceUppsala UniversityUppsalaSweden
  3. 3.School of Economic and ManagementBeijing University of Posts and TelecommunicationsBeijingChina
  4. 4.Academic Center for Education, Culture and Research (ACECR)TehranIran

Personalised recommendations