Research on noninvasive electrophysiologic imaging based on cardiac electrophysiology simulation and deep learning methods for the inverse problem

• Published in: BMC cardiovascular disorders Vol. 25; no. 1; pp. 335 - 13
• Main Authors: Chang, Yi, Dong, Ming, Fan, Lihong, Kang, Bochao, Sun, Weikai, Li, Xiaofeng, Yang, Zhang, Ren, Ming
• Format: Journal Article
• Language: English
• Published: London BioMed Central 28.04.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Action Potentials; Algorithms; Analysis; Angiology; Arrhythmia; Arrhythmias, Cardiac - diagnosis; Arrhythmias, Cardiac - diagnostic imaging; Arrhythmias, Cardiac - physiopathology; Blood Transfusion Medicine; Body Surface Potential Mapping; Cardiac arrhythmia; Cardiac electrophysiologic imaging; Cardiac Surgery; Cardiology; Cardiovascular diseases; Care and treatment; Computer Simulation; Coronary artery disease; Deep Learning; Diagnosis; ECG inverse problem; EKG; Electrocardiogram; Electrocardiography; Electrodes; Electrophysiologic Techniques, Cardiac; Electrophysiology; Heart; Heart diseases; Heart Rate; Humans; Internal Medicine; Inverse problems; Long short-term memory; Machine learning; Mapping; Mathematical optimization; Medicine; Medicine & Public Health; Methods; Models, Cardiovascular; Neural networks; Neural Networks, Computer; Patients; Predictive Value of Tests; Prognosis; Propagation; Regularization methods; Reproducibility of Results; Simulation; Software; China; Deep learning; ECG inverse problem; Arrhythmia; Cardiac electrophysiologic imaging; Body surface potential mapping
• ISSN: 1471-2261; 1471-2261
• DOI: 10.1186/s12872-025-04728-2

Background The risk stratification and prognosis of cardiac arrhythmia depend on the individual condition of patients, while invasive diagnostic methods may be risky to patient health, and current non-invasive diagnostic methods are applicable to few disease types without sensitivity and specificity. Cardiac electrophysiologic imaging (ECGI) technology reflects cardiac activities accurately and non-invasively, which is of great significance for the diagnosis and treatment of cardiac diseases. This paper aims to provide a new solution for the realization of ECGI by combining simulation model and deep learning methods. Methods A complete three-dimensional bidomain cardiac electrophysiologic activity model was constructed, and simulated electrocardiogram data were obtained as training samples. Particle swarm optimization-back propagation neural network, convolutional neural network, and long short-term memory network were used respectively to reconstruct the cardiac surface potential. Results The correlation coefficients between the simulation results and the clinical data range from 75.76 to 84.61%. The P waves, PR intervals, QRS complex, and T waves in the simulated waveforms were within the normal clinical range, and the distribution trend of the simulated body surface potential mapping was consistent with the clinical data. The coefficient of determination R 2 between the reconstruction results of all the algorithms and the true value is above 0.80, and the mean absolute error is below 2.1 mV, among which the R 2 of long short-term memory network is about 0.99 and the mean absolute error about 0.5 mV. Conclusions The electrophysiologic model constructed in this study can reflect cardiac electrical activity, and contains the mapping relationship between the cardiac potential and the body surface potential. In cardiac potential reconstruction, long short-term memory network has significant advantages over other algorithms. Clinical trial number Not applicable.