Abstract
In the reverse electrocardiography (ECG) problem, the objective is to reconstruct the heart’s electrical activity from a set of body surface potentials by solving the direct model and the geometry of the torso. Over the years, researchers have used various approaches to solve this problem, from direct, iterative, probabilistic, and those based on deep learning. The interest of the latter, among the wide range of techniques, is because the complexity of the problem can be significantly reduced while increasing the precision of the estimation. In this article, we evaluate the performance of a deep learning-based neural network compared to the Tikhonov method of zero order (ZOT), first (FOT), and second (SOT). Preliminary results show an improvement in performance over real data when Pearson’s correlation coefficient (CC) and (RMSE) are calculated. The CC’s mean value and standard deviation for the proposed method were 0.960 (0.065), well above ZOT, which was 0.864 (0.047).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aras, K., et al.: Experimental data and geometric analysis repository - EDGAR. J. Electrocardiol. 48(6), 975–981 (2015). https://doi.org/10.1016/j.jelectrocard.2015.08.008
Bear, L.R., et al.: How accurate is inverse electrocardiographic mapping? Circ. Arrhythm. Electrophysiol. 11(5), 6108 (2018). https://doi.org/10.1161/CIRCEP.117.006108. https://www.ahajournals.org/doi/10.1161/CIRCEP.117.006108
Cluitmans, M., et al.: Validation and opportunities of electrocardiographic imaging: from technical achievements to clinical applications. Front. Physiol. 9, 1305 (2018). https://doi.org/10.3389/fphys.2018.01305. https://www.frontiersin.org/article/10.3389/fphys.2018.01305/full
Cluitmans, M.J.M., Clerx, M., Vandersickel, N., Peeters, R.L.M., Volders, P.G.A., Westra, R.L.: Physiology-based regularization of the electrocardiographic inverse problem. Med. Biol. Eng. Comput. 55(8), 1353–1365 (2017). https://doi.org/10.1007/s11517-016-1595-5, https://drive.google.com/_le/d/199s6HPwSYF1WCWHiYBkJdt3ZAD99EeW/view?usp=sharing
Cluitmans, M., et al.: In vivo validation of electrocardiographic imaging. JACC: Clin. Electrophysiol. 3(3), 232–242 (2017). https://doi.org/10.1016/j.jacep.2016.11.012
Figuera, C., et al.: Regularization techniques for ECG imaging during atrial fibrillation: a computational study. Front. Physiol. 7, 466 (2016). https://doi.org/10.3389/fphys.2016.00466. http://journal.frontiersin.org/article/10.3389/fphys.2016.00466/full
Milanič, M., Jazbinšek, V., MacLeod, R.S., Brooks, D.H., Hren, R.: Assessment of regularization techniques for electrocardiographic imaging. J. Electrocardiol. 47(1), 20–28 (2014). https://doi.org/10.1007/978-3-031-10450-3_20. https://linkinghub.elsevier.com/retrieve/pii/S0022073613005566
Potyagaylo, D., Dossel, O., van Dam, P.: Influence of modeling errors on the initial estimate for nonlinear myocardial activation times imaging calculated with fastest route algorithm. IEEE Trans. Biomed. Eng. 63(12), 2576–2584 (2016). https://doi.org/10.1109/TBME.2016.2561973. http://ieeexplore.ieee.org/document/7464310/
Rajagopal, A., Radzicki, V., Lee, H., Chandrasekaran, S.: Nonlinear electrocardiographic imaging using polynomial approximation networks. APL Bioeng. 2(4), 046101 (2018). https://doi.org/10.1063/1.5038046. http://aip.scitation.org/doi/10.1063/1.5038046
Rodríguez-Sotelo, J.L., Peluffo-Ordoñez, D., Cuesta-Frau, D., Castellanos-Domínguez, G.: Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering. Comput. Methods Programs Biomed. 108(1), 250–261 (2012). https://doi.org/10.1016/J.CMPB.2012.04.007, https://pubmed.ncbi.nlm.nih.gov/22672933/
Sanchez-Pozo, N.N., Mejia-Ordonez, J.S., Chamorro, D.C., Mayorca-Torres, D., Peluffo-Ordonez, D.H.: Predicting high school students’ academic performance: a comparative study of supervised machine learning techniques. Future of Educational Innovation Workshop Series - Machine Learning-Driven Digital Technologies for Educational Innovation Workshop 2021 (2021). https://doi.org/10.1109/IEEECONF53024.2021.9733756
Wang, L., Gharbia, O.A., Horáček, B.M., Sapp, J.L.: Noninvasive epicardial and endocardial electrocardiographic imaging of scar-related ventricular tachycardia. J. Electrocardiol. 49(6), 887–893 (2016). https://doi.org/10.1016/j.jelectrocard.2016.07.026. https://linkinghub.elsevier.com/retrieve/pii/S0022073616301042
Zhou, Z., Han, C., Yang, T., He, B.: Noninvasive imaging of 3-dimensional myocardial infarction from the inverse solution of equivalent current density in pathological hearts. IEEE Trans. Biomed. Eng. 62(2), 468–476 (2 2015). https://doi.org/10.1109/TBME.2014.2358618. http://ieeexplore.ieee.org/document/6901202/
Acknowledgments
The authors would like to acknowledge the valuable support given by the SDAS Research Group (https://sdas-group.com/).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mayorca-Torres, D., León-Salas, A.J., Peluffo-Ordoñez, D.H. (2023). Neural Networks on Noninvasive Electrocardiographic Imaging Reconstructions: Preliminary Results. In: Botto-Tobar, M., Gómez, O.S., Rosero Miranda, R., Díaz Cadena, A., Luna-Encalada, W. (eds) Trends in Artificial Intelligence and Computer Engineering. ICAETT 2022. Lecture Notes in Networks and Systems, vol 619. Springer, Cham. https://doi.org/10.1007/978-3-031-25942-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-25942-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25941-8
Online ISBN: 978-3-031-25942-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)