Automatic liver contour segmentation using GVF snake

Liver segmentation is critical for the development of algorithms to detect and define focal lesions. It is also helpful in presurgical planning for hepatic resection and to gauge the results of therapies. The purpose of this study was to develop a computerized method for extraction of liver contours on contrast-enhanced hepatic CT. The method is based on a snake algorithm with Gradient Vector Flow (GVF) field as its external force, which uses an edge map and an initial contour as its starting point. A Canny edge algorithm is thus applied to obtain the initial edge map. To suppress edges inside liver parenchyma, a liver template determined by analyzing the histogram of the liver image is employed. Based on the modified edge map, the GVF field is then computed in an iterative manner. Due to the finite iteration step, an area uncovered by the GVF field in the liver can be extracted and serves as an initial contour for the snake algorithm. Preliminary results have shown the potential of separating the liver from its adjacent structures (e.g., kidney and stomach) of similar densities.