A three-dimensional graph searching technique for cardiac border detection in sequential images and its application to magnetic resonance image data

Developed is a new method of automated border detection using graph searching principles. The method takes into account the added information available in temporal or spatial sequences of images that are commonly available in biomedical applications. This method is applied to detect endocardial and epicardial borders in short-axis magnetic resonance images of the heart. Preliminary results show that it may be more robust in areas of noise when compared to a method based only on data from a single image. They suggest that this method could potentially improve performance of automated edge detection methods when spatial or temporal sequences of frames are available