Cardio Vision

Abstract

Coronary artery disease (CAD) remains a leading cause of mortality worldwide, demanding efficient and accurate diagnostic tools. CardioVision aims to revolutionize CAD diagnosis through a DL-based web application that analyzes Coronary CT Angiography (CCTA) images. Leveraging a deep learning model, CardioVision employs advanced image enhancement techniques and convolutional neural networks (CNNs) to detect CAD. The model was trained using publicly available datasets, and further validated for high accuracy and reliability. The proposed CAD detection model aids radiologists and cardiologists in early identification of cardiac disease. Recent models for CAD detection require high computational resources and large image datasets. Thus, this study aims to develop a CNN-based CAD detection model. The Aquila optimization technique is utilized to optimize the hyperparameters of the UNet++ model for CAD prediction. This proposed method and hyperparameter tuning approach not only reduce computational costs but also enhance the performance of the UNet++ model. Our study findings conclude that the proposed model can be used to identify CAD with limited resources.