Left Ventricle MRI Images Segmentation by Unifying Level Set Method and Snake Model with Shape Constraints
ZHOU ZeMing1,2, YOU JianJie2, FAN ChunHui1, Pheng Ann Heng3, XIA DeShen2
1.Meteorology College, PLA University of Science and Technology, Nanjing 211101 2.Department of Computer,Nanjing University of Science and Technology , Nanjing 210094 3.Department of Computer Science and Engineering, Chinese University of HongKong, HongKong
Abstract A segmentation algorithm for the left ventricle MRI images is proposed by unifying the level set method and the snake model with shape constraints. Due to the weak edges and the low contrast regions, the deformation curve leaks from the outer boundary of the left ventricle when the snake model is used to segment the MRI image of the left ventricle. After the training samples have been aligned and the variation modes have been analyzed, the allowable shape space of the left ventricle is constructed. According to the properties of the cardiac MRI images, the shape constraint energy field around the average shape is created by the level set method. After the shape constraint energy term is added, the snake model can effectively prevent the deformation curve from leaking out of the low contrast regions. The evolving curve is subject to the shape constraints by mapping it to the allowable shape space. The segmentation experiments demonstrate the effectiveness of the proposed model.
ZHOU ZeMing,YOU JianJie,FAN ChunHui等. Left Ventricle MRI Images Segmentation by Unifying Level Set Method and Snake Model with Shape Constraints[J]. , 2006, 19(6): 782-786.
[1] Kass M, Witkin A, Terzopoulos D. Snake: Active Contour Models. International Journal of Computer Vision, 1988, 1 (4):321-331 [2] Lin Yao, Tian Jie. A Review on Segmentation Methods of Medical Images. Pattern Recognition and Artificial Intelligence, 2002, 15(2):192-204 (in Chinese) (林 瑶,田 捷.医学图象分割方法综述.模式识别与人工智能, 2002, 15(2): 192-204) [3] Amini A A, Weymouth T E, Jain T C. Using Dynamic Programming for Solving Variational Problems in Vision. IEEE Trans on Pattern Analysis and Machine Intelligence, 1990, 12 (9): 855-867 [4] Cohen L D. On Active Contour Models and Balloons. Computer Vision, Graphics and Image Processing: Image Understanding, 1991, 53(2): 211-218 [5] Xu C, Prince J L. Snakes, Shapes and Gradient Vector Flow. IEEE Trans on Image Processing, 1998, 7(3): 359-369 [6] Zhou Zeming, Wang Yuanquan, Pheng A H, et al. 3D Left Ventricle Surface Reconstruction Based on Level Sets. Journal of Computer Research and Development, 2005, 42(7): 1173-1178 (in Chinese) (周则明,王元全,王平安,等. 基于水平集的3D左心室表面重建.计算机研究与发展, 2005, 42(7): 1173- 1178) [7] Steven C M, Lelieveldt B P F, van der Geest R J,et al. Multistage Hybrid Active Appearance Model Matching: Segmentation of Left and Right Ventricles in Cardiac MR Images. IEEE Trans on Medical Imaging, 2001, 20(5): 415-423 [8] Paragios N, Detiche R. Coupled Geodesic Active Regions for Image Segmentation: A Level Set Approach // Proc of the 6th European Conference on Computer Vision. Dublin, Ireland, 2000: 224-240 [9] Cremers D, Schnrr C. Statistical Shape Knowledge in Variational Motion Segmentation. Image and Vision Computing, 2003, 21(1): 77-86 [10] Leventon M E, Grimson W E L, Faugeras O. Statistical Shape Influence in Geodesic Active Contours // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, USA, 2000, Ⅰ: 316-323 [11] Cootes T F, Taylor C J, Cooper D H, et al. Active Shape Models: Their Training and Application. Computer Vision and Image Understanding, 1995, 61(1): 38-59 [12] Adalsteinsson D, Sethian J A, Affitiation A A. The Fast Construction of Extension Velocities in Level Set Methods. Journal of Computational Physics, 1999, 148(1): 2-22
2006, Vol. 19 
