CNN Based Detection of Cardiovascular Diseases from ECG Images

TL;DR

This paper presents a CNN model based on InceptionV3 architecture that detects myocardial infarction and other cardiac conditions from ECG images with over 93% accuracy, aiding early diagnosis.

Contribution

It introduces a transfer learning approach using InceptionV3 for ECG-based cardiac disease detection, achieving high accuracy with a specific dataset.

Findings

Achieved 93.27% accuracy in detecting MI and other conditions.

Demonstrated the effectiveness of deep learning for ECG analysis.

Supports clinical decision-making in cardiology.

Abstract

This study develops a Convolutional Neural Network (CNN) model for detecting myocardial infarction (MI) from Electrocardiogram (ECG) images. The model, built using the InceptionV3 architecture and optimized through transfer learning, was trained using ECG data obtained from the Ch. Pervaiz Elahi Institute of Cardiology in Pakistan. The dataset includes ECG images representing four different cardiac conditions: myocardial infarction, abnormal heartbeat, history of myocardial infarction, and normal heart activity. The developed model successfully detects MI and other cardiovascular conditions with an accuracy of 93.27%. This study demonstrates that deep learning-based models can provide significant support to clinicians in the early detection and prevention of heart attacks.