Light weight multi-branch network-based extraction and classification of myocardial infarction from 12 lead electrocardiogram images

ABSTRACT

Myocardial Infarction (MI) is a heart disease due to lack of blood and oxygen flow to some part of the heart muscle. MI is a leading cause of death globally. To decrease the likelihood of MI complications, it is essential to diagnose and treat MI promptly. A Light Weight Multi-branch Network (LW-MN) based feature extraction and classification of MI from Electrocardiogram image is proposed. Extracting the information from Electrocardiogram images without segmenting the leads separately may result in loss of information. Segmenting the 12 leads by detecting the text above each lead will extract the information accurately without any information loss. Light Weight model used to extract features and fusing all twelve leads features using the depth fusion method. The outcome from the fusion method is fed into DenseNet-161 classification algorithm. LW-MN model acquired a classification accuracy, specificity, sensitivity, and F1-score of 96.09%, 97.33%, 97.78%, and 95.18%.

KEYWORDS:

• Myocardial infarction
• ECG images
• feature fusion
• MobileNet
• Light weight model
• feature extraction
• classification
• DenseNet

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Jothiaruna Nagaraj

Jothiaruna Nagaraj is a Ph.D. student at the Vellore Institute of Technology, Vellore since 2020 and researches in School of Information Technology and Engineering (SITE) department. She got her B.E. title in Computer Science and Engineering from Kingston Engineering College, Vellore in 2017 and received her M. Tech. title in Computer Science and Engineering from SASTRA University, Thanjavur in 2019. Her research interests include Image Processing, and Deep Learning.

Anny Leema

Dr. Anny Leema is an Associate Professor in the Analytics Department, School Computer Science and Engineering at Vellore Institute of Technology. She received her PhD in Computer Science from Karpagam Academy of Higher Education in 2013 with good number of publications indexed by Scopus. She is having 21 years of teaching experience. Her research includes data mining, web mining, RFID, Wireless sensor networks, e-learning and Machine Learning. She has edited the book Machine Learning Approaches for Improvising Modern Learning Systems and written six chapters in the research areas E Learning, Machine learning and RFID. Published more than 40 research papers in the International Journals and forty two papers in National and International Conferences. Published two Indian Patents and one Australian patent got granted. She is a reviewer of several International Journals and Program Committee member of various International Conferences.