Detection of Cardiovascular Diseases in ECG Images using Machine Learning and Deep Learning Methods

Cardiovascular diseases (CVDs) continue to be a leading cause of mortality worldwide, necessitating early and accurate detection for effective intervention. Electrocardiogram (ECG) images provide valuable diagnostic information, but the complexity and variability of ECG patterns present challenges for automated detection. This study proposes a novel approach for the detection of CVDs using deep learning methods, specifically MobileNet and EfficientNetV2, applied to ECG image analysis.

MobileNet and EfficientNetV2 are chosen for their efficiency and scalability, making them suitable for resource-constrained environments and large-scale datasets. The methodology involves preprocessing of ECG images, including noise reduction and feature extraction. These processed images are then fed into the deep learning models for classification of CVDs. The models are trained on a diverse and comprehensive dataset comprising ECG images with annotated cardiovascular disease labels.

The results of this study demonstrate the effectiveness of MobileNet and EfficientNetV2 in detecting CVDs from ECG images. The deep learning models achieve high accuracy, sensitivity, and specificity, showcasing their potential for clinical applications. The proposed approach offers a non-invasive and automated solution for early CVD detection, enabling timely medical intervention and reducing the burden of cardiovascular diseases on healthcare systems.

Keywords: Cardiovascular diseases, ECG images, Deep learning, MobileNet, EfficientNetV2, Deep Learning, Image Processing.