Study of Image Segmentation for MR Diffusion Weighed Image Based on Active Contour

MR Diffusion Weighed Image(DWI) is one of many functional magnetic resonance imaging(fMRI) techniques, and could provide complicated spatial and structural information about the tissue. Aiming at segmentation MR diffusion weighed image for real-time application with numerical stability constraints and high efficiency, a method based on the minimization algorithm is developed. Our approach is based on the image segmentation tasks into a global minimization method. The minimization algorithm minimization the energy, avoid the drawback in the level set approach and easy to implement, allows us a fast minimization of the active contour. Experimental results show that the effectiveness for image segmentation with our method is preferable.

[1]  Chunming Li,et al.  Level set evolution without re-initialization: a new variational formulation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Wei Li,et al.  Fast magnetic resonance diffusion‐weighted imaging of acute human stroke , 1992, Neurology.

[3]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[4]  Tony F. Chan,et al.  A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model , 2002, International Journal of Computer Vision.

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

[6]  P. Olver,et al.  Conformal curvature flows: From phase transitions to active vision , 1996, ICCV 1995.

[7]  Mila Nikolova,et al.  Algorithms for Finding Global Minimizers of Image Segmentation and Denoising Models , 2006, SIAM J. Appl. Math..

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