Automated detection scheme for acute myocardial infarction using convolutional neural network and long short-term
Ryosuke Muraki1, Atsushi Teramoto2, Keiko Sugimoto3
1Graduate School of Health Sciences, Fujita Health University, Toyoake, Japan.
Plos One
|February 25, 2022
Summary
This study introduces an AI method using deep learning for early acute myocardial infarction detection via echocardiography. The system achieved high accuracy, aiding in diagnosing heart conditions and preventing severe outcomes.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Imaging
Background:
- Early detection of acute myocardial infarction (AMI) is crucial to prevent chronic heart failure or sudden death.
- Echocardiography is a common noninvasive method for diagnosing AMI and assessing abnormal heart wall motion.
- Distinguishing subtle abnormal wall motion from normal myocardium in echocardiography can be challenging, necessitating high detection accuracy.
Purpose of the Study:
- To develop an automated method for detecting acute myocardial infarction (AMI) using echocardiography.
- To leverage deep learning, specifically convolutional neural networks (CNNs) and long short-term memory (LSTM), for enhanced diagnostic accuracy.
Main Methods:
- Utilized VGG16 (a CNN model) for feature extraction from echocardiographic views (left ventricular long-axis and short-axis at papillary muscle level).
- Employed Long Short-Term Memory (LSTM) networks for classifying cardiac images into normal myocardium or acute myocardial infarction categories.
- Input data included one cardiac cycle from the short-axis view (papillary muscle level) and the left ventricular long-axis view.
Main Results:
- The automated detection method achieved an overall classification accuracy of 85.1% for the left ventricular long-axis view.
- The short-axis view (papillary muscle level) analysis yielded a classification accuracy of 83.2%.
- The proposed deep learning approach demonstrated significant potential in identifying myocardial infarction from echocardiographic data.
Conclusions:
- The developed CNN-LSTM model shows promise for the accurate and automated detection of acute myocardial infarction using echocardiography.
- This AI-driven approach can aid clinicians in the early diagnosis and management of myocardial infarction.
- Further validation and integration into clinical workflows could improve patient outcomes for heart conditions.
Related Concept Videos
01:30Acute Coronary Syndrome III: Diagnostic Studies
36
Diagnosing acute coronary syndrome or ACS begins with a thorough patient history. Notable symptoms include central, crushing chest pain radiating to the left arm, neck, jaw, or back, along with shortness of breath, sweating (diaphoresis), nausea, vomiting, dizziness, and palpitations.It is crucial to note any history of cardiac illnesses and assess risk factors, including age, gender, smoking, hypertension, diabetes, hyperlipidemia, and a sedentary lifestyle.During physical examination, vital...
36
01:30Acute Coronary Syndrome I: Introduction
103
Acute Coronary Syndrome (ACS) encompasses a spectrum of heart conditions caused by sudden obstruction of coronary arteries, typically resulting from the rupture of an atherosclerotic plaque and subsequent thrombus (blood clot) formation. This obstruction can lead to partial or complete blockage of blood flow, causing varying degrees of myocardial ischemia or infarction.ACS includes the following clinical entities:Unstable Angina (UA)Non-ST-Elevation Myocardial Infarction (NSTEMI)ST-Elevation...
103