Real-Time Multilead Convolutional Neural Network for Myocardial Infarction Detection

• Published in: IEEE journal of biomedical and health informatics Vol. 22; no. 5; pp. 1434 - 1444
• Main Authors: Liu, Wenhan, Zhang, Mengxin, Zhang, Yidan, Liao, Yuan, Huang, Qijun, Chang, Sheng, Wang, Hao, He, Jin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Artificial neural networks; Convolution; Convolutional neural network (CNN); Diagnostic systems; Echocardiography; EKG; electrocardiogram (ECG); Electrocardiography; Granulation; Health care; Heart; Heart attacks; lead asymmetric pooling (LAP); Medical services; Mobile communication; Myocardial infarction; Myocardial Infarction (MI); Myocardium; Neural networks; Real time; real-time application; Real-time systems; Segmentation; sub 2-D convolution; Two dimensional models
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2017.2771768

In this paper, a novel algorithm based on a convolutional neural network (CNN) is proposed for myocardial infarction detection via multilead electrocardiogram (ECG). A beat segmentation algorithm utilizing multilead ECG is designed to obtain multilead beats, and fuzzy information granulation is adopted for preprocessing. Then, the beats are input into our multilead-CNN (ML-CNN), a novel model that includes sub two-dimensional (2-D) convolutional layers and lead asymmetric pooling (LAP) layers. As different leads represent various angles of the same heart, LAP can capture multiscale features of different leads, exploiting the individual characteristics of each lead. In addition, sub 2-D convolution can utilize the holistic characters of all the leads. It uses 1-D kernels shared among the different leads to generate local optimal features. These strategies make the ML-CNN suitable for multilead ECG processing. To evaluate our algorithm, actual ECG datasets from the PTB diagnostic database are used. The sensitivity of our algorithm is 95.40%, the specificity is 97.37%, and the accuracy is 96.00% in the experiments. Targeting lightweight mobile healthcare applications, real-time analyses are performed on both MATLAB and ARM Cortex-A9 platforms. The average processing times for each heartbeat are approximately 17.10 and 26.75 ms, respectively, which indicate that this method has good potential for mobile healthcare applications.