Cardiac Image Analysis for Accurate Heart Disease Diagnosis Using Deep Learning Techniques: A Comprehensive Review

Coronary illness is a leading cause of mortality worldwide. Prompt discovery and precise forecasts of coronary disease can help in forestalling and dealing with the sickness. Lately, profound learning strategies, e.g., convolution neural networks (CNNs) have shown promising outcomes in different clinical imaging errands, including coronary illness expectation. This review proposes a CNN-based approach for coronary illness expectation utilizing cardiovascular pictures. The proposed model comprises numerous convolution layers, pooling, and completely associated layers. The model is prepared on an enormous dataset of cardiovascular pictures and related marks for coronary illness presence or non-attendance. The prepared model is assessed on a different test dataset to evaluate its exactness, responsiveness, explicitness, and other execution measurements. Our outcomes show that the proposed CNN-based approach accomplishes high exactness and outflanks customary machine learning strategies for coronary illness expectation. The proposed model can be utilized as a device to help doctors in the early determination and treatment of coronary illness.