A Convolutional Neural Network Model for Classifying Cardiac Membrane Potential Patterns
E Jun-liang1, MA Li-yuan2, ZHANG Hong1, GUO Ping3
1. School of Electrical Engineering, Xi'an, Jiaotong University, Xi'an 710049, China; 2. School of Life Science and Technology, Xi'an Jiaotong Uniwversity, Xi'an 710049, China; 3. School of Basic Medical Science, Xi'an Jiaotong University, Xi'an 710049, China
A Convolutional Neural Network Model for Classifying Cardiac Membrane Potential Patterns
E Jun-liang1, MA Li-yuan2, ZHANG Hong1, GUO Ping3
1. School of Electrical Engineering, Xi'an, Jiaotong University, Xi'an 710049, China; 2. School of Life Science and Technology, Xi'an Jiaotong Uniwversity, Xi'an 710049, China; 3. School of Basic Medical Science, Xi'an Jiaotong University, Xi'an 710049, China
摘要Investigation of the electrophysiological mechanisms that induce arrhythmias is one of the most important issues in scientific research. Since computational cardiology allows the systematic dissection of causal mechanisms of observed effects, simulations based on the ionic channel mathematical models have . become one of the most widely used methods. To reduce themanual classification of different types of membrane potential patterns produced during simulations, a convolutional neural network is developed in this paper. The model includes 4 convolution layers, 4 pooling layers and a fully connected layer. An activation function of ReLU is used. Before machine learning, all the pattems are calibrated, cut, and normalized to a uniform format with a size of 256x256. The contour boundary of each pattern is extracted using the maximum between-class variance method. In the examination, the proposed learning algorithm shows a recognition accuracy of 97% on test data set after training.
Abstract：Investigation of the electrophysiological mechanisms that induce arrhythmias is one of the most important issues in scientific research. Since computational cardiology allows the systematic dissection of causal mechanisms of observed effects, simulations based on the ionic channel mathematical models have . become one of the most widely used methods. To reduce themanual classification of different types of membrane potential patterns produced during simulations, a convolutional neural network is developed in this paper. The model includes 4 convolution layers, 4 pooling layers and a fully connected layer. An activation function of ReLU is used. Before machine learning, all the pattems are calibrated, cut, and normalized to a uniform format with a size of 256x256. The contour boundary of each pattern is extracted using the maximum between-class variance method. In the examination, the proposed learning algorithm shows a recognition accuracy of 97% on test data set after training.
E Jun-liang, MA Li-yuan, ZHANG Hong, GUO Ping. A Convolutional Neural Network Model for Classifying Cardiac Membrane Potential Patterns[J]. 中国生物医学工程学报(英文版）, 2021, 30(4): 178-184.
E Jun-liang, MA Li-yuan, ZHANG Hong, GUO Ping. A Convolutional Neural Network Model for Classifying Cardiac Membrane Potential Patterns. Chinese Journal of Biomedical Engineering, 2021, 30(4): 178-184.
[1] Moss R, Sachse FB, Moreno-Galindo EG, et al. Modeling effects of voltage dependent properties of the cardiac muscarinic receptor on human sinus node function[J]. PLoS Comput Biol, 2018, 14: e1006438. [2] Severi S, Rodriguez B, Zaza A. Computational cardiac electrophysiology is ready for prime time [J]. Europace, 2014, 16(3): 382-383. [3] Karpaev AA, Syunyaev RA, Aliev RR.Effects of fibroblast-myocyte coupling on the sinoatrial node activity: a computational study[J]. International Journal for Numerical Methods in Engineering, 2018, 34:e2966. [4] Trayanova NA. Mathematical approaches to understanding and imaging atrial fibrillation significance for mechanisms and management[J]. Circulation Research, 2014, 114(9): 1516-1531. [5] Xu L, He XM, Li XX, et al. A machine-vision inspection system for conveying attitudes of columnar objects in packing processes[J]. Measurement, 2016, 87:255-273. [6] Li HQ, Yu QC, Fang M.Application of Otsu thresholding method on Canny operator[J]. Computer Engineering and Design, 2008, 29(9): 2297-2299. [7] Saishanmuga Raja V, Rajagopalan SP.A comparative analysis of optimization techniques forartificial neural network in bio-medical applications[J]. Joumal of Computer Science, 2014, 10(1):106-114. [8] Rana S, Jasola S, Kumar R.A review on particle swarm optimization algorithms and their applications to data clustering[J]. Artificial Intelligence Review, 2011, 35 :211-222. [9] Kora P, Swaraja K, Meenakshi K, et al. Bio-medical signal processing using deep learning [J]. Bioscience Biotechnology Research Communications, 2020, 13(2):26-29. [10] Wilson AC, Roelofs R, Stern M, et al. The marginal value of adaptive gradient methods in machine learning[J]. Advances in Neural Information Processing Systems, 2017, 30:4148-4158. [11] Laughner JI, Ng FS, Sulkin MS, et al. Processing and analysis of cardiac optical mapping data obtained with potentiometric dyes[J]. American Jourmal of Physiology-Heart and Circulatory Physiology, 2012, 303(7):H753-H765.
