Boundary detection in echocardiographic images by directional gradient vector flow

Snakes, or active contour models, have been widely used in image segmentation. In this paper, a new type of dynamic external force for snakes named directional gradient vector flow (DGVF) is proposed for the detection of left ventricular boundary from echocardiographic images. The new method is able to discern between positive and negative step edges by incorporating directional gradient information. It makes use of the gradients in both x and y directions and deals with the external force field for the two directions separately. The DGVF field is utilized dynamically in snake deformation, according to the orientation of snake in each iteration. Experimental results demonstrate that the DGVF snake performs better boundary detection than gradient vector flow (GVF) snake in noisy echocardiographic images.