Heart disease detection and diagnosis using medical imaging has become a critical field in healthcare, particularly with the integration of deep learning techniques. This study focuses on two key applications for diagnosing coronary heart diseases through imaging. The first concept involves classifying heart diseases from Echocardiogram images using deep learning models such as Convolutional Neural Networks (CNN), MobileNet, and DenseNet. These models are trained to detect conditions such as Angina Pectoris, Coronary Artery Disease, and Left Ventricular Hypertrophy. The second concept centers on segmentation and localization in CT Angiography images for coronary heart disease diagnosis, using YOLO V8 to identify bifurcation and focal points in the angiogram images. Both approaches aim to enhance diagnostic accuracy by automating the detection and interpretation of cardiovascular diseases, thereby supporting healthcare professionals in making timely and accurate decisions. The integration of deep learning for medical image analysis offers a promising solution for early diagnosis and better patient outcomes.

Keywords: Heart Disease, Echocardiogram, CNN, MobileNet, DenseNet, Coronary Artery Disease, Left Ventricular Hypertrophy, YOLO V8, CT Angiography, Bifurcation, Focal Points, Deep Learning.