A New Medical Image Segmentation Technique Based on Variational Level Set Method

The main obj ective of medical image segmentation is to extract and characterize anatomical structures with respect to some input features or expert knowledge. This paper describes a way of medical image segmentation based on level set method to extract the region of interest of various medical images such as magnetic resonance imaging (MRI), computer tomography (CT), and positron emission tomography (PET) image. The overall technique of the paper is divided into three steps. The first step is to do threshold of the input image to make the entire pixel under threshold value to 0 and others to take the value as original image. This helps to keep original properties of original image and keep all value fixed as original image except the pixel that are not necessary for our analysis. Next, a morphological technique is used to remove some small ignorable parts. Finally we apply variational level set method for final segmentation. The experimental results show the efficacy of the proposed method.

[1]  Olivier D. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[2]  Xun Wang,et al.  Deformable Contour Method: A Constrained Optimization Approach , 2004, International Journal of Computer Vision.

[3]  O. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2002, 5th IEEE EMBS International Summer School on Biomedical Imaging, 2002..

[4]  Max A. Viergever,et al.  Geodesic deformable models for medical image analysis , 1998, IEEE Transactions on Medical Imaging.

[5]  Yunmei Chen,et al.  On the incorporation of shape priors into geometric active contours , 2001, Proceedings IEEE Workshop on Variational and Level Set Methods in Computer Vision.

[6]  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).

[7]  Rachid Deriche,et al.  Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation , 2002, International Journal of Computer Vision.

[8]  Anthony J. Yezzi,et al.  A geometric snake model for segmentation of medical imagery , 1997, IEEE Transactions on Medical Imaging.

[9]  Nikos Paragios,et al.  Shape Priors for Level Set Representations , 2002, ECCV.

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

[11]  Laurent D. Cohen,et al.  Global Minimum for Active Contour Models: A Minimal Path Approach , 1997, International Journal of Computer Vision.

[12]  Kaleem Siddiqi,et al.  Area and length minimizing flows for shape segmentation , 1998, IEEE Trans. Image Process..