5 Automated Segmentation of Real-Time 3D Echocardiography Using an Incompressibility Constraint Yun Zhu, Xenophon Papademetris, Albert Sinusas and James Duncan Yale University USA 1. Introduction Coronary Heart Disease (CHD) is characterized by reduced blood flow and oxygen supply to the heart muscle, resulting from the occlusion of one or more major coronary arteries. CHD remains the most prevalent cause of mortality in developed countries and represents one of the major burdens on the healthcare systems today. Approximately every 25 seconds, an American will suffer from a coronary event, and about every minute, someone will die from one. According to the 2009 American Heart Association (AHS) report (Lloyd-Jones et al., 2009}, an estimated of 16.8 million American adults have CHD (extrapolated to US population in 2009 from National Health and Nutrition Examination Survey (NHANES) 2005-2006) and about 20% of total deaths in the United States are caused by CHD. The advancements in noninvasive imaging techniques, such as real-time three-dimensional (RT3D) echocardiography, have enabled physicians to detect CHD in its earliest and most treatable stage. With cardiac imaging, physicians are able to evaluate essential global and local functional parameters, such as ejection fraction (EF), wall thickening, strain/strain rate, and etc. The rapid progress in cardiac imaging, however, has led to new challenges in handling of huge amount of image data involved in comprehensive functional patient studies. Manually analyzing these data sets becomes a formidable task for cardiologists, radiologists, and technicians in order to interpret the data and derive clinically useful information for diagnosis or decision support for surgical and pharmacological interventions. Also, manual analysis is subjective and therefore compromises the accuracy and reproducibility of quantitative measurements. The abovementioned reasons have triggered a great demand for computerized techniques to automate the analysis of cardiac images. Various image-processing tasks need to be performed in order to recover diagnostically useful information, among which myocardial segmentation is one of the most important tasks. Myocardial segmentation aims to delineate the endocardial (ENDO) and epicardial (EPI) boundaries from cardiac images. Accurate segmentation of myocardial boundaries is essential for deriving cardiac global functional parameters such as ventricular mass/volume, ejection fraction, and wall thickening. It is also a prerequisite step for accurate myocardial deformation analysis.