Myocardial infarction detection based on deep neural network on imbalanced data

被引:0
作者
Mohamed Hammad
Monagi H. Alkinani
B. B. Gupta
Ahmed A. Abd El-Latif
机构
[1] Menoufia University,Information Technology Department, Faculty of Computers and Information
[2] University of Jeddah,Department of Computer Science and Artificial Intelligence, College of Computer Sciences and Engineering
[3] National Institute of Technology,Department of Computer Engineering
[4] Asia University,Department of Computer Science and Information Engineering
[5] Menoufia University,Mathematics and Computer Science Department, Faculty of Science
来源
Multimedia Systems | 2022年 / 28卷
关键词
CNN; Myocardial infarction; End-to-end; PTB; Focal loss; Imbalanced data;
D O I
暂无
中图分类号
学科分类号
摘要
Myocardial infarction (MI) is an acute interruption of blood flow to the heart, which causes the heart to suffer from a deficiency of blood and ischemia, so the heart muscle is damaged, and cells can die and lose their function. Despite the low incidence of MI in the world, it is still a common disease-causing death. Therefore, detecting the MI signals early can reduce mortality. This paper presented a method based on a deep convolutional neural network (CNN) for the detection of MI automatically. The proposed CNN is an end-to-end model without requiring any stages of machine learning and requires only one stage to detect MI from the input signals. In the case of imbalanced data, we optimize our deep model with a new loss function named the focal loss to deal with this case by constituting the loss indirectly the focus in those difficult classes. The Physikalisch-Technische Bundesanstalt (PTB) dataset was employed in the validation to classify the signals to normal and MI. The performance of our technique alongside state-of-the-art in the area shows an increase in terms of average accuracy and F1 score. Results show that focal loss improves the detection accuracy by 9% for detecting MI signals. In summary, the proposed method achieved an overall accuracy, precision, F1 score, and recall of 98.84%, 98.31%, 97.92%, and 97.63, respectively using focal loss and overall accuracy of 89.72%, a precision of 88.52%, a recall of 81.11% and F1 score of 83.02% without using focal loss. Our method using focal loss is an effective tool to perform a fast and reliable MI diagnosis to assist the cardiologists in detecting MI early.
引用
收藏
页码:1373 / 1385
页数:12
相关论文
共 226 条
[1]  
Yang H(2010)Multiscale recurrence quantification analysis of spatial cardiac vectorcardiogram signals IEEE Trans. Biomed. Eng. 58 339-347
[2]  
Vogel B(2019)ST-segment elevation myocardial infarction Nat. Rev. Dis. Prim. 5 1-20
[3]  
Claessen BE(2016)Predictors of stroke, myocardial infarction or death within 30 days of carotid artery stenting: results from the International Carotid Stenting Study Eur. J. Vasc. Endovasc. Surg. 51 327-334
[4]  
Arnold SV(2006)Significance of a fragmented QRS complex versus a Q wave in patients with coronary artery disease Circulation 113 2495-2501
[5]  
Chan D(2020)Visual saliency guided complex image retrieval Pattern Recogn. Lett. 130 64-72
[6]  
Cohen DJ(2019)Automated detection and localization of myocardial infarction with staked sparse autoencoder and treebagger IEEE Access 7 70634-70642
[7]  
Giannitsis E(2019)Localization of myocardial infarction with multi-lead bidirectional gated recurrent unit neural network IEEE Access 7 161152-161166
[8]  
Doig D(2020)Parallel implementation for 3d medical volume fuzzy segmentation Pattern Recogn. Lett. 130 312-318
[9]  
Turner EL(2019)Automated detection of myocardial infarction using a gramian angular field and principal component analysis network IEEE Access 7 171570-171583
[10]  
Dobson J(2019)Automated interpretable detection of myocardial infarction fusing energy entropy and morphological features Comput. Methods Programs Biomed. 175 9-23