Classification of Arrhythmias Using a Pre-trained Deep Learning Model with Binary Images of Segmented ECG
https://doi.org/10.32603/1993-8985-2023-26-2-120-127
Abstract
Introduction. Arrhythmia or irregular heartbeat occur when the heart’s electrical system is disorganized or out of sync, which may cause strokes, sudden cardiac death, and other complications. The introduction of an automated classification of arrhythmias based on deep learning could facilitate the decision-making process by saving time and labor resources.
Aim. To study the performance of a modified arrhythmia classification improved by using binary images of segmented ECG signals with combinations of orthogonal and surface signals.
Materials and methods. This article studies an arrhythmia classification based on binary images of surface and orthogonal ECG signals. The data labeling was automated using the Python programming language. Initially, all signals are subjected to preprocessing followed by their plotting and segmenting in 2-second windows. Next, those segments are saved as RGB images followed by their conversion into binary images, where the signal is white, and the background is black. Finally, the pre-trained Alexnet model is used to classify nine classes, where each surface ECG and orthogonal lead is classified separately.
Results. The performance of the model is evaluated by the mean accuracy, precision, F1-score, and confusion matrix of all leads. The results of a parallel classification of 12 lead ECG are better than those for the orthogonal leads. All leads with accuracy, precision, and F1-score equal to 0.84, 0.78, and 0.71, respectively.
Conclusion. The performance of the model was evaluated for three cases: 12 surface ECG leads, orthogonal leads, and all leads. The calculated mean values of accuracy, precision, and F1-score for each case confirmed the sufficiency of the 12-lead surface ECG for classifying nine different types of arrhythmia using binary images of ECG segments.
About the Authors
H. Solieman
Saint Petersburg Electrotechnical Universit; Tishreen University
Russian Federation
Russian Federation
Hanadi Solieman, Bachelor in Electromechanics – Mechatronics (2018, Tishreen University, Syria), Master in Bioengineering Systems and Technologies (2020), 3rd year Postgraduate student, Assistant at the Department of Bioengineering Systems of Saint Petersburg Electrotechnical University. Assistant at the Mechatronics program for Distinguished at Tishreen University. The author of more than 10 scientific publications. Area of expertise: medical instrumentation; medical informatics; processing and analysis of biomedical signals and data.
197022, St Petersburg, Professor Popov St., 5 F
S. Sali
Saint Petersburg Electrotechnical Universit; Tishreen University
Russian Federation
Russian Federation
Salar Sali, Bachelor in Electromechanics – Mechatronics (2020, Tishreen University, Syria), 2rd year Master's student at the Department of Bioengineering Systems of Saint Petersburg Electrotechnical University. Area of expertise: medical instrumentation; medical informatics; processing and analysis of biomedical signals and data.
197022, St Petersburg, Professor Popov St., 5 F
References
1. Smoot K. Heart Rhythm and Arrythmias. Johns Hopkins Medicine. Available at: https://www.hopkinsmedicine.org/heart_vascular_institute/cardiovascular-research/heart-rhythm-andarrythmias.html (accessed 22.10.2022)
2. Cardiovascular diseases (CVDs). World Health Organization. Available at: https://www.who.int/newsroom/fact-sheets/detail/cardiovascular-diseases-(cvds) (accessed 24.10.2022)
3. Bousseljot R. D., Kreiseler D., Schnabel A. The PTB Diagnostic ECG Database. doi:10.13026/C28C71. Available at: https://physionet.org/content/ptbdb/ (accessed 15.10.2022)
4. Moody G., Mark R. MIT-BIH Arrhythmia Database. doi:10.13026/C2F305. Available at: https://physionet.org/content/mitdb/ (accessed 15.10.2022)
5. Zhao Y., Cheng J., Zhang P., Peng X. ECG Classification Using Deep CNN Improved by Wavelet Transform. Computers, Materials & Continua. 2020, vol. 64, no. 3, pp. 1615–1628. doi:10.32604/cmc.2020.09938
6. Ari S., Das M. K., Chacko A. ECG Signal Enhancement Using S-Transform. Computers in Biology and Medicine. 2013, vol. 43, no. 6, pp. 649–660. doi:10.1016/j.compbiomed.2013.02.015
7. Fernandes F. C. A., van Spaendonck R. L. C., Burrus C. S. A New Framework for Complex Wavelet Transforms. IEEE Transactions on Signal Processing. 2003, vol. 51, no. 7, pp. 1825–1837. doi:10.1109/TSP.2003.812841
8. Yi X., Walia E., Babyn P. Generative Adversarial Network in Medical Imaging: A review. Medical Image Analysis. 2019, vol. 58, p. 101552. doi:10.1016/j.media.2019.101552
9. Baowaly M. K., Lin Ch.-Ch., Liu Ch.-L., Chen K.-T. Synthesizing Electronic Health Records Using Improved Generative Adversarial Networks. J. of the American Medical Informatics Association. 2019, vol. 26, no. 3, pp. 228–241. doi:10.1093/jamia/ocy142
10. Shaker A. M., Tantawi M., Shedeed H. A., Tolba M. F. Generalization of Convolutional Neural Networks for ECG Classification Using Generative Adversarial Networks. IEEE Access. 2020, vol. 8, pp. 35592–35605. doi:10.1109/ACCESS.2020.2974712
11. Lu Y., Jiang M., Wei L., Zhang J., Wang Zh., Wei B., Xia L. Automated Arrhythmia Classification Using Depthwise Separable Convolutional Neural Network with Focal Loss. Biomedical Signal Processing and Control. 2021, vol. 69, p. 102843. doi:10.1016/j.bspc.2021.102843
12. Weimann K., Conrad T. O. F. Transfer Learning for ECG Classification. Sci Rep. 2021, vol. 11, no. 1, p. 5251. doi:10.1038/s41598-021-84374-8
13. Manilo L. A., Nemirko A. P., Evdakova E. G., Tatarinova A. A. ECG Database for Evaluating the Efficiency of Recognizing Dangerous Arrhythmias. Proc. of the 2021 IEEE Ural-Siberian Conf. on Computational Technologies in Cognitive Science, Genomics and Biomedicine. 2021, pp. 120–123. doi:10.1109/CSGB53040.2021.9496029
14. Nemirko A., Manilo L., Tatarinova A., Alekseev B., Evdakova E. ECG Fragment Database for the Exploration of Dangerous Arrhythmia. doi:10.13026/kpfg-xs25. Available at: https://physionet.org/content/ecg-fragment-high-risk-label/1.0.0/ (accessed 15.10.2022)
15. Ba Mahel A. S., Harold N., Solieman H. Arrhythmia Classification Using Alexnet Model Based on Orthogonal Leads and Different Time Segments. Proc. of the 2022 Conf. of Russian Young Researchers in Electrical and Electronic Engineering. 2022, pp. 1312–1315. doi:10.1109/ElConRus54750.2022.9755708
Review
For citations:
Solieman H., Sali S. Classification of Arrhythmias Using a Pre-trained Deep Learning Model with Binary Images of Segmented ECG. Journal of the Russian Universities. Radioelectronics. 2023;26(2):120-127. (In Russ.) https://doi.org/10.32603/1993-8985-2023-26-2-120-127
Views:
420
Email this article 