Conference Paper2024

ECGInsight: A Web Application-Based Approach to Myocardial Infarction Detection From ECG Image Reports Utilizing ResNet

J. H. Setu, S. T. Pasha, N. Halder, S. Sikder, A. Islam, M. Z. Alam

23rd IEEE International Conference on Machine Learning and Applications (ICMLA)

IEEE, pp. 514-519

  • Good Health and Well-being — Relevance: 96%
DOI: 10.1109/icmla61862.2024.00075URL

Abstract

Cardiovascular illness is frequently the cause of my-ocardial infarction (MI), also referred to as a heart attack, which happens when the blood supply to a portion of the heart muscle is interrupted or diminished. This event can range from being asymptomatic to causing significant declines in cardiovascular function and premature mortality. An electrocardiogram (ECG) is vital for diagnosing and assessing MI, as it measures the heart's electrical activity and can detect various cardiac conditions. In this study, we developed a Residual Network (ResNet)-based model for MI detection using ECG signals. The model was trained on the PTB-XL dataset, which includes 21,837 annotated ECG signals, and tested on converted ECG signals from the Mendeley Data ECG Images dataset. Our model achieved high precision, recall, and F1-scores, demonstrating robust performance with an accuracy of 98.95 % on the validation set and 98.63 % on the test set. In addition, we developed ECGInsight, a web application that lets users take or upload a picture of an ECG report. The photo is converted to ECG signals, which are then processed by ResNet to produce predictions with confidence levels. This study underscores the potential of Deep Learning (DL) models in automated MI detection and highlights the practical utility of the ECGInsight web application in making MI detection accessible to users, ultimately contributing to advancements in cardiovascular healthcare.

Keywords

  • myocardial infarction detection
  • PTB-XL dataset
  • electrocardiogram
  • ResNet
  • Web application
  • cardiovascular disease
  • automated diagnosis
  • Deep learning

References

  1. 1.R. Bousseljot, D. Kreiseler, A. Schnabel. (2009). Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomedizinische Technik/Biomedical Engineering, 317–318[10.1515/bmte.1995.40.s1.317]
  2. 2.Željko Ð. Vujovic. (2021). Classification Model Evaluation Metrics. International Journal of Advanced Computer Science and Applications, 12(6)[10.14569/ijacsa.2021.0120670]
  3. 3.Ulas Baran Baloglu, Muhammed Talo, Ozal Yildirim, Ru San Tan, U Rajendra Acharya. (2019). Classification of myocardial infarction with multi-lead ECG signals and deep CNN. Pattern Recognition Letters, 122, 23–30[10.1016/j.patrec.2019.02.016]
  4. 4.G.B. Moody, R.G. Mark. (2002). The MIT-BIH Arrhythmia Database on CD-ROM and software for use with it. , 185–188[10.1109/cic.1990.144205]
  5. 5.Wanni Xu, You-Lei Fu, Dongmei Zhu. (2023). ResNet and its application to medical image processing: Research progress and challenges. Computer Methods and Programs in Biomedicine, 240, 107660[10.1016/j.cmpb.2023.107660]
  6. 6.Shengliang Peng, Shujun Sun, Yu-Dong Yao. (2021). A Survey of Modulation Classification Using Deep Learning: Signal Representation and Data Preprocessing. IEEE Transactions on Neural Networks and Learning Systems, 33(12), 7020–7038[10.1109/tnnls.2021.3085433]
  7. 7.Salah S. Al-Zaiti, Christian Martin-Gill, Jessica K. Zègre-Hemsey, Zeineb Bouzid, Ziad Faramand, Mohammad O. Alrawashdeh, Richard E. Gregg, Stephanie Helman, Nathan T. Riek, Karina Kraevsky-Phillips, Gilles Clermont, Murat Akcakaya, Susan M. Sereika, Peter Van Dam, Stephen W. Smith, Yochai Birnbaum, Samir Saba, Ervin Sejdic, Clifton W. Callaway. (2023). Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction. Nature Medicine, 29(7), 1804–1813[10.1038/s41591-023-02396-3]
  8. 8.Mohammed B. Abubaker, Bilal Babayiğit. (2022). Detection of Cardiovascular Diseases in ECG Images Using Machine Learning and Deep Learning Methods. IEEE Transactions on Artificial Intelligence, 4(2), 373–382[10.1109/tai.2022.3159505]
  9. 9.V. Jahmunah, E.Y.K. Ng, Ru-San Tan, Shu Lih Oh, U Rajendra Acharya. (2022). Explainable detection of myocardial infarction using deep learning models with Grad-CAM technique on ECG signals. Computers in Biology and Medicine, 146, 105550[10.1016/j.compbiomed.2022.105550]
  10. 10.Keith A. Reimer, Robert B. Jennings, Arthur H. Tatum. (1983). Pathobiology of acute myocardial ischemia: Metabolic, functional and ultrastructural studies. The American Journal of Cardiology, 52(2), 72–81[10.1016/0002-9149(83)90180-7]
  11. 11.Hari Mohan Rai, Kalyan Chatterjee. (2021). Hybrid CNN-LSTM deep learning model and ensemble technique for automatic detection of myocardial infarction using big ECG data. Applied Intelligence, 52(5), 5366–5384[10.1007/s10489-021-02696-6]
  12. 12.Binish Fatimah, Pushpendra Singh, Amit Singhal, Dipro Pramanick, Pranav S., Ram Bilas Pachori. (2021). Efficient detection of myocardial infarction from single lead ECG signal. Biomedical Signal Processing and Control, 68, 102678[10.1016/j.bspc.2021.102678]
  13. 13.Stefan Gustafsson, Daniel Gedon, Erik Lampa, Antônio H. Ribeiro, Martin J. Holzmann, Thomas B. Schön, Johan Sundström. (2022). Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients. Scientific Reports, 12(1), 19615[10.1038/s41598-022-24254-x]
  14. 14.Girmaw Abebe Tadesse, Hamza Javed, Komminist Weldemariam, Yong Liu, Jin Liu, Jiyan Chen, Tingting Zhu. (2021). DeepMI: Deep multi-lead ECG fusion for identifying myocardial infarction and its occurrence-time. Artificial Intelligence in Medicine, 121, 102192[10.1016/j.artmed.2021.102192]
  15. 15.Sathvik Bhaskarpandit, Anurag Gade, Shaswati Dash, Dinesh Kumar Dash, Rajesh Kumar Tripathy, Ram Bilas Pachori. (2023). Detection of Myocardial Infarction From 12-Lead ECG Trace Images Using Eigendomain Deep Representation Learning. IEEE Transactions on Instrumentation and Measurement, 72, 1–12[10.1109/tim.2023.3241986]
  16. 16.Joyita Ghosh, Subir Gupta. (2023). ADAM Optimizer and CATEGORICAL CROSSENTROPY Loss Function-Based CNN Method for Diagnosing Colorectal Cancer. , 470–474[10.1109/cises58720.2023.10183491]
  17. 17.June Edhouse, William J Brady, Francis Morris. (2002). Acute myocardial infarction—Part II. BMJ, 324(7343), 963–966[10.1136/bmj.324.7343.963]
  18. 18.Patrick Wagner, Nils Strodthoff, Ralf-Dieter Bousseljot, Dieter Kreiseler, Fatima I. Lunze, Wojciech Samek, Tobias Schaeffter. (2020). PTB-XL, a large publicly available electrocardiography dataset. Scientific Data, 7(1), 154[10.1038/s41597-020-0495-6]
  19. 19.Ali Haider Khan, Muzammil Hussain, Muhammad Kamran Malik. (2021). ECG Images dataset of Cardiac and COVID-19 Patients. Data in Brief, 34, 106762[10.1016/j.dib.2021.106762]
← All publications