Coronary Artery Disease (CAD) is a major disorder in heart rhythm invoices the reduction or blockage of blood flow due to the narrow artery which results in coronary artery disease Our project is to investigate and detect the occurrence of coronary artery disease (cardiac block) using a probabilistic neural network. We would apply the probabilistic neural network to CT Images and, Feature extraction by using the Gray Level Co-Occurrence Matrix (GLCM). Image recognition and image compression are done by using the Gaussian bilateral filter method and also large dimensionality of the data is reduced. Automatic cardiac block classification is done by using a Probabilistic Neural Network (PNN). The segmentation process is done by using the K-means clustering algorithm and also detects the cardiac block spread region. PNN is the fastest technique and also provide good classification accuracy.