Intelligent Heart Disease Prediction System Using Multi Atlas Segmentation

The evaluation of ventricular function is important for the diagnosis of cardiovascular diseases. It involves the measurement o f the left ventricular (LV) mass. In this paper, a multi atlas segmentation method is proposed for cardiac magnetic resonance (MR) image segmentation. The proposed method is novel in two aspects. First, it formulates a patch-based label fusion model in a Bayesian framework. Second, it improves Image registration accuracy by utilizing label information, which improves image segmentation accuracy. The proposed method was evaluated on a cardiac MR Images set of 28 subjects. The results show that the proposed method is able to provide accurate information for clinical diagnosis.