Edge Based Level Set with Gaussian Filtering Regularized and its Application in Liver Segmentation

Abstract:

A novel edge-based active contour model (ACM) is proposed in this paper. Our edge-based active contour model has many advantages over the conventional active contour models. Firstly, the proposed model can get much smoother contour and needs much less iterations to evolution by being implemented with a special processing named Selectively Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) method. Secondly, we introduce Bilateral Gaussian Filter which can preserve edges to smooth images. So we make weak edges more clear than traditional Gaussian Filter. Thirdly, the level set function can be easily initialized with binary function, which is more efficient to construct than the widely used signed distance function (SDF) because of the special processing. Experiments on synthetic image and segmenting liver from abdominal CT images demonstrate the advantages of the proposed method over geodesic active contours (GAC) in term of both efficiency and accuracy.

• Periodical: Advanced Materials Research (Volumes 121-122)
• Pages: 222-227
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.121-122.222
• Online since: June 2010
• Authors: Rui Jie Feng, Hui Yan Jiang
• Keywords: Bilateral Gaussian Filter, GAC Model, Image Segmentation, Level Set, Liver

References

[1] K.J. Mortele, P.R. Ros: Cystic focal liver lesions in the adult: differential CT and MR imaging features, RadioGraphics , 21(2001), pp.895-910.

DOI: 10.1148/radiographics.21.4.g01jl16895

[2] S.J. Lim, Y.Y. Jeong, C.W. Lee Y.S. Ho: Automatic segmentation of the liver in CT images using the watershed segmentation based on morphological filtering, Proceedings of SPIE Medical Imaging: Image Processing, 5370 (2004), pp.1658-1666.

DOI: 10.1117/12.533586

[3] K.T. Bae M.L. Giger C.T. Chen, C.E. Kahn: Automatic segmentation of liver structure in CT Images, Med. Phys , 20(1) (1993), pp.71-78.

DOI: 10.1118/1.597064

[4] L. Jeongjin, K. Namkug, L. Ho, S.B. Joon, W. Hyungjin, S. Yongmoon et al: Efficient liver segmentation using a level-set method with optimal detection of the initial liver boundary from level-set speed images, Computer Methods and Program in Biomedicine, 88(2007).

DOI: 10.1016/j.cmpb.2007.07.005

[5] S. Pan, B.M. Dawant: Automatic 3D segmentation of the liver from abdominal CT images: a level-set approach, Proceeding of SPIE Medical Imaging : Image Processing, 4322(2001) , pp.128-138.

DOI: 10.1117/12.431019

[6] L. Gao, A. Kosaka, A. Kak: A deformable model for automatic CT liver extraction, Acad. Radio, 12 (9) (2005), pp.1178-1189.

DOI: 10.1016/j.acra.2005.05.005

[7] M. Kass, A. Witkin, D. Terzopoulos: Snakes: active contour models, International Journal of Computer Vision, (1988) , pp.321-331.

DOI: 10.1007/bf00133570

[8] V. Caselles, R. Kimmel, G. Sapiro: Geodesic active contours, Processing of IEEE International Conference on Computer Vision, Boston, MA (1995), pp.694-699.

DOI: 10.1109/iccv.1995.466871

[9] T. Chan, L. Vese: Active contours without edges, IEEE Transaction on Image Processing, 10(2) (2001) , pp.266-277.

DOI: 10.1109/83.902291

[10] Z. Kaihua, Z. Lei, S. Huihui, Z. Wengang: Active contours with selective local or global segmentation: A new formulation and level set method, Image and Vision Computing, 28 (2010) pp.668-676.

DOI: 10.1016/j.imavis.2009.10.009

[11] C. Tomasi, R. Manduch: Bilateral filtering for gray and color images, Proceedings of the Sixth International Conference on Computer Vision, Washington DC, USA, IEEE Computer Society, (1998), pp.839-846.

DOI: 10.1109/iccv.1998.710815

[12] Y. Shi, W.C. Karl: Real-time tracking using level sets, IEEE Conference on computer Vision and Pattern Recognition, 2 (2005), pp.34-41.

DOI: 10.1109/cvpr.2005.294