Skip to main content
SpringerLink
Log in

Dual temporal convolutional network for single-lead fibrillation waveform extraction

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The f-wave extraction (FE) is essential for analysis of atrial fibrillations. However, the state-of-the-art FE methods are model-based, and they cannot well adapt to the QRST complexes with high morphological variabilities which often appear in clinical electrocardiogram (ECG). Recently, the encoder-decoder based deep learning networks have been successfully applied to separate variable speech waveforms. However, how these networks are exploited to extract f-waves from ECG recordings is still unclear. Moreover, these networks require different sources to share the common encoder and decoder, which restricts the effectiveness of source representations. To address these issues, a dual temporal convolutional network called DT-FENet is proposed for single lead FE, which integrates the source-specific encoder-decoder mappings and the information fused attention mechanism to respectively learn the latent masks of f-waves and QRST complexes. The proposed DT-FENet can be considered as a dual-stream extension of the famous Conv-TasNet. Compared to Conv-TasNet, the source-specific encoder-decoder mappings of the DT-FENet can obtain more representative bases and sparser activations in latent feature spaces to facilitate the FE task. To the best of our knowledge, this is the first deep learning method for single-lead FE. Extensive experiments were conducted on the clinical ECG records, and the experimental results show that the proposed DT-FENet performs significantly better than the state-of-the-art FE methods with less than one tenth of unnormalized ventricular residuals and about twice spectral concentrations. The proposed DT-FENet can provide accurate f-wave information for atrial fibrillations detection using single-lead ECGs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Chugh SS, Roth GA, Gillum RF, Mensah GA (2014) Global burden of atrial fibrillation in developed and developing nations. Glob Heart 9(1):113–119

    Article  Google Scholar 

  2. Chugh SS, Blackshear JL, Win-Kuang S, Hammill SC, Gersh BJ (2001) Epidemiology and natural history of atrial fibrillation: clinical implications. J Am Coll Cardiol 37(2):371–378

    Article  Google Scholar 

  3. Daniela H, Martin S, Leif S, Christoph G, Klein HU, Bertil OS, Andreas B (2005) Time-frequency analysis of the surface electrocardiogram for monitoring antiarrhythmic drug effects in atrial fibrillation. Am J Cardiol 95(4):526–528

    Article  Google Scholar 

  4. Raygor VP, Jason N, Goldberger JJ (2015) Surface ECG f wave analysis of dofetilide drug effect in the atrium. J Cardiovasc Electrophysiol 26(6):644–648

    Article  Google Scholar 

  5. Lankveld T, Zeemering S, Scherr D, Kuklik P, Hoffmann BA, Willems S, Pieske B, Haïssaguerre M, Jaïs P, Crijns HJ et al (2016) Atrial fibrillation complexity parameters derived from surface ECGs predict procedural outcome and long-term follow-up of stepwise catheter ablation for atrial fibrillation. Circ Arrhythm Electrophysiol 9(2):e003354

    Article  Google Scholar 

  6. Raúl A, Fernando H, Rieta JJ (2016) Electrocardiographic spectral features for long-term outcome prognosis of atrial fibrillation catheter ablation. Ann Biomed Eng 44(11):3307–3318

    Article  Google Scholar 

  7. Kheirati RE, Roberto S (2016) An extended Bayesian framework for atrial and ventricular activity separation in atrial fibrillation. IEEE J Biomed Health Inform 21(6):1573–1580

    Google Scholar 

  8. Joaquín RJ, Francisco C, César S, Vicente Z, José M (2004) Atrial activity extraction for atrial fibrillation analysis using blind source separation. IEEE Trans Biomed Eng 51(7):1176–1186

    Article  Google Scholar 

  9. Francisco C, Joaquín RJ, José M, Vicente Z (2005) Spatiotemporal blind source separation approach to atrial activity estimation in atrial tachyarrhythmias. IEEE Trans Biomed Eng 52(2):258–267

    Article  Google Scholar 

  10. Carlos V, Rieta José J, César S, David M (2007) Convolutive blind source separation algorithms applied to the electrocardiogram of atrial fibrillation: study of performance. IEEE Trans Biomed Eng 54(8):1530–1533

    Article  Google Scholar 

  11. Raul L, Jorge I (2009) Application of constrained independent component analysis algorithms in electrocardiogram arrhythmias. Artif Intell Med 47(2):121–133

    Article  Google Scholar 

  12. Martin S, Sornmo L (2001) Spatiotemporal QRST cancellation techniques for analysis of atrial fibrillation. IEEE Trans Biomed Eng 48(1):105–111

    Article  Google Scholar 

  13. Lemay M, Jacquemet V, Forclaz A, Vesin JM, Kappenberger L (2005) Spatiotemporal QRST cancellation method using separate QRS and T-waves templates. In: Computers in cardiology, 2005. IEEE, pp 611–614

  14. Mathieu L, Jean-Marc V, Adriaan VO, Vincent J, Lukas K (2007) Cancellation of ventricular activity in the ECG: evaluation of novel and existing methods. IEEE Trans Biomed Eng 54(3):542–546

    Article  Google Scholar 

  15. Huhe D, Shouda J, Ye L (2013) Atrial activity extraction from single lead ECG recordings: evaluation of two novel methods. Comput Biol Med 43(3):176–183

    Article  Google Scholar 

  16. John M, Neil R, Chun-Li W, Hau-tieng W (2017) Single-lead f-wave extraction using diffusion geometry. Physiol Meas 38(7):1310

    Article  Google Scholar 

  17. Dinggang S, Guorong W, Heung-Il S (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248

    Article  Google Scholar 

  18. Şaban Ö (2020) Stacked auto-encoder based tagging with deep features for content-based medical image retrieval. Expert Syst Appl 161:113693

    Article  Google Scholar 

  19. Ebrahimi Z, Loni M, Daneshtalab M, Gharehbaghi A (2020) A review on deep learning methods for ECG arrhythmia classification. Expert Syst Appl X:100033

    Google Scholar 

  20. Şaban Ö, Bayram A (2019) Cell-type based semantic segmentation of histopathological images using deep convolutional neural networks. Int J Imaging Syst Technol 29(3):234–246

    Article  Google Scholar 

  21. Bahareh P, Javan RM, Khashayar K (2018) Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients. IEEE Trans Syst Man Cybern Syst 48(12):2095–2104

    Article  Google Scholar 

  22. Xiaomao F, Qihang Y, Yunpeng C, Fen M, Fangmin S, Ye L (2018) Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings. IEEE J Biomed Health Inform 22(6):1744–1753

    Article  Google Scholar 

  23. Saeed S, Mohammadhosein O, Matin H (2019) LSTM-based ECG classification for continuous monitoring on personal wearable devices. IEEE J Biomed Health Inform 24(2):515–523

    Google Scholar 

  24. Yi L, Nima M (2019) Conv-TasNet: surpassing ideal time-frequency magnitude masking for speech separation. IEEE/ACM Trans Audio Speech Lang Process 27(8):1256–1266

    Article  Google Scholar 

  25. Luo Y, Mesgarani N (2018) TasNet: time-domain audio separation network for real-time, single-channel speech separation. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 696–700

  26. Pandey A, Wang D (2019) TCNN: temporal convolutional neural network for real-time speech enhancement in the time domain. In: ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 6875–6879

  27. Yu D, Kolbæk M, Tan Z-H, Jensen J (2017) Permutation invariant training of deep models for speaker-independent multi-talker speech separation. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 241–245

  28. Şaban Ö, Bayram A (2018) Phase classification of mitotic events using selective dictionary learning for stem cell populations. Comput Electr Eng 67:25–37

    Article  Google Scholar 

  29. Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271

  30. Chia-Hung L (2008) Frequency-domain features for ECG beat discrimination using grey relational analysis-based classifier. Comput Math Appl 55(4):680–690

    Article  MathSciNet  Google Scholar 

  31. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  32. Raúl A, Leif S, Rieta JJ (2019) Reference database and performance evaluation of methods for extraction of atrial fibrillatory waves in the ECG. Physiol Meas 40(7):075011

    Article  Google Scholar 

  33. Reza S, Clifford GD, Jutten C, Shamsollahi MB (2007) Multichannel ECG and noise modeling: application to maternal and fetal ECG signals. EURASIP J Adv Signal Process 1:043407

    MATH  Google Scholar 

  34. Andrius P, Vaidotas M, Andrius S, Raimondas K, Jurgita S, Julien O, Leif S (2017) Electrocardiogram modeling during paroxysmal atrial fibrillation: application to the detection of brief episodes. Physiol Meas 38(11):2058

    Article  Google Scholar 

  35. Bousseljot R, Kreiseler D, Schnabel A (1995) Nutzung der ekg-signaldatenbank cardiodat der ptb über das internet. Biomed Eng 40(s1):317–318

    Google Scholar 

  36. Moody G (1983) A new method for detecting atrial fibrillation using RR intervals. Comput Cardiol 10:227–230

    Google Scholar 

  37. Clifford GD, Liu C, Moody B, Li-wei HL, Silva I, Li Q, Johnson AE, Mark RG (2017) AF classification from a short single lead ECG recording: the physionet/computing in cardiology challenge 2017. In: 2017 computing in cardiology (CinC). IEEE, pp 1–4

  38. Raúl A, Joaquín RJ (2008) Adaptive singular value cancelation of ventricular activity in single-lead atrial fibrillation electrocardiograms. Physiol Meas 29(12):1351

    Article  Google Scholar 

  39. Warmerdam GJJ, Rik V, Lars S, Van Laar JOEH, Bergmans JWM (2018) Hierarchical probabilistic framework for fetal r-peak detection, using ECG waveform and heart rate information. IEEE Trans Signal Process 66(16):4388–4397

    Article  MathSciNet  Google Scholar 

Download references

Funding

Funding was provided by National Natural Science Foundation of China (Grant No. 62073086, No. 61973087 and No. U1911401).

Author information

Authors and Affiliations

  1. School of Automation, Guangdong University of Technology, Guangzhou, 510006, China

    Jun Lu, Jie Luo, Zhuoyan Xie, Kan Xie & Shengli Xie

  2. The Third Affiliated Hospital of Southern Medical University, Guangzhou, 510630, China

    Yuanxiong Cheng

  3. Key Laboratory of Intelligent Information Processing and System Integration of IoT (GDUT), Ministry of Education, Guangzhou, 510006, China

    Jun Lu

  4. Guangdong Key Laboratory of IoT Information Technology (GDUT), Guangzhou, 510006, China

    Kan Xie

  5. Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing (GDUT), Guangzhou, 510006, China

    Shengli Xie

Authors
  1. Jun Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhuoyan Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kan Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuanxiong Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shengli Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shengli Xie.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lu, J., Luo, J., Xie, Z. et al. Dual temporal convolutional network for single-lead fibrillation waveform extraction. Neural Comput & Applic 33, 15281–15292 (2021). https://doi.org/10.1007/s00521-021-06148-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06148-7

Keywords

Search

Navigation