Characterizing normal and abnormal cardiac echo motion patterns

The Information about cardiac mechanical performance is of critical importance in understanding the etiology of heart diseases. However, little work has been done to date, to understand the relationship of cardiovascular diseases to the global cardiac motion patterns. In this paper we address the problem of distinguishing between normal and abnormal motion patterns in cardiac echo videos. Specifically, we describe the overall motion of the heart using average velocity curves. We then detect characteristic patterns in these curves that help distinguish normal from abnormal motion. The motion patterns observed in normal and abnormal groups using the extracted features are found to be easily separable.