A New Multi-phase Level Set Framework for 3D Medical Image Segmentation Based on TPBG

In this paper, we propose a new multi-phase level set framework for 3D medical image segmentation to deal with the limitation of 2-phase segmentation algorithms using one level set. By developing the technique of painting the background with average gray level of the object (TPBG) and reusing the active contours model without edges which is 2-phase one, we are able to obtain more than two segments (n-1 times for n phases, n>1). Following the philosophy of dichotomy, we illustrate the efficiency of the proposed framework by segmenting a 3D medical image into more than two segments step by step

[1]  L. Vese,et al.  A level set algorithm for minimizing the Mumford-Shah functional in image processing , 2001, Proceedings IEEE Workshop on Variational and Level Set Methods in Computer Vision.

[2]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[3]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  S. Osher,et al.  A level set approach for computing solutions to incompressible two-phase flow , 1994 .

[5]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[6]  R. Deriche,et al.  A variational framework for active and adaptative segmentation of vector valued images , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[7]  V. Caselles,et al.  A geometric model for active contours in image processing , 1993 .

[8]  J. Sethian,et al.  A geometric approach to segmentation and analysis of 3D medical images , 1996, Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis.

[9]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..