Automatic medical image segmentation based on EPGV-Snake

This communication presents a novel approach to contour segmentation of Computed Tomography (CT) images. Image segmentation is achieved by means of the snake algorithm and the dynamic programming (DP) optimization technique. Based upon the edge preserving gradient vector flow (EPGVF) field, a new strategy for contour points initialization and splitting is presented. Contour initialization is carried out from EPGVF magnitude thresholding. In the multi-object image segmentation, the delineation of all the image objects is done through the splitting of the contour at the divergent points in the image. The proposed technique can attain a good solution without the need of an operator intervention. Some experiences on synthetic and CT medical images show that the proposed algorithm gives good results.

[1]  Dong Joong Kang,et al.  A fast and stable snake algorithm for medical images , 1999, Pattern Recognition Letters.

[2]  Jerry L. Prince,et al.  Gradient vector flow: a new external force for snakes , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Zeyun Yu,et al.  Normalized Gradient Vector Diffusion and Image Segmentation , 2002, ECCV.

[5]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[6]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Chunming Li,et al.  Segmentation of external force field for automatic initialization and splitting of snakes , 2005, Pattern Recognit..

[8]  Ravinda G. N. Meegama,et al.  NURBS snakes , 2003, Image Vis. Comput..

[9]  Tian Jie,et al.  An automatic active contour model for multiple objects , 2002, Object recognition supported by user interaction for service robots.

[10]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[11]  Jerry L. Prince,et al.  Generalized gradient vector flow external forces for active contours , 1998, Signal Process..

[12]  Hadj Batatia,et al.  A general quasi-automatic initialization for snakes: application to ultrasound images , 2005, IEEE International Conference on Image Processing 2005.