Snake-based liver lesion segmentation
C. Krishnamurthy, Jeffrey J. Rodrı́guez, Robert J. Gillies · 2004
A novel and robust method for accurate segmentation of liver lesions is discussed. The initial contour for the snake is formed using edge and region information. The modified snake, guided by fuzzy edge information, deforms from this initial position, providing an accurate representation of the lesion boundary with few iterations and minimal user interaction. Results obtained from this algorithm are comparable to those obtained from manual segmentation by a trained radiologist.