SRAD, Optical Flow and Primitive Prior Based Active Contours for Echocardiography

Accurate delineation of object borders is highly desirable in echocardiography, especially the left ventricle. Among other model-based techniques, active contours (or snakes) provide a unique and powerful approach to image analysis. In this work, we propose the use of a novel external energy for a gradient vector flow (GVF) snake. This energy consists of optical flow estimates of heart sequences along with the use of a speckle reducing anisotropic diffusion (SRAD) operator. This energy provides more information to the active contour model garnering adequate results for noisy moving sequences. Furthermore, an automatic primitive shape prior algorithm was employed to further improve the results and regularity of the snake, when dealing with especially speckle laden echocardiographic images. Results were compared with expert-defined segmentations yielding better sensitivity, precision rate and overlap ratio than the standard GVF model.