Abstract
We present a novel method for the automatic segmentation of the vertebral bodies from 2D sagittal magnetic resonance (MR) images of the spine. First, a new affinity matrix is constructed by incorporating neighboring information, which local intensity is considered to depict the image and overcome the noise effectively. Second, the Gaussian kernel function is to weight chi-square distance based on the neighboring information, which the vital spatial structure of the image is introduced to improve the accuracy of the segmentation task. Third, an adaptive local scaling parameter is utilized to facilitate the image segmentation and avoid the optimal configuration of controlling parameter manually. The encouraging results on the spinal MR images demonstrate the advantage of the proposed method over other methods in terms of both efficiency and robustness.
Similar content being viewed by others
References
Gath I, Geva AB: Unsupervised optimal fuzzy clustering. IEEE Transportation Pattern Analytical Machine Intelligence 11:773–781, 1989
Schillo C, Herrmann G, Ackermann F, et al: Statistical classification and segmentation of biomolecular surfaces. Proceedings International Conference Image Processing 3(3):560–563, 1995
Kass M, Witkin A, Terzopoulos D: Snakes: Active contour models. International J Computer Vision 5:321–331, 1988
Caselles V, Kimmel R, Sapiro G: Geodesic active contours. International J Computer Vision 22(1):61–79, 1997
Ronfard R: Region-based strategies for active contour models. International J Computer Vision 46:223–247, 2002
Paragios N, Deriche R: Geodesic active contours and level sets for detection and tracking of moving objects. IEEE Transaction Pattern Analysis Machine Intelligence 22:1–15, 2000
Chan T, Vese L: Active contour without edges. IEEE Transaction Image Processing 10(2):266–277, 2001
Cootes TF, Taylor CJ, Cooper DH, Graham J: Active shape models—their training and application. Computer Vision Image Understanding (61) 38–59, 1995
Mitchell SC, Bosch JG, Lelieveldt BP, et al: 3-d active appearance models: segmentation of cardiac MR and ultrasound images. IEEE Transport Medicine Imaging 21(9):1167–1178, 2002
Dunn JC: A fuzzy relative of the ISODATA process and its use in detecting compact well separated cluster. J Cybernet 3(3):32–57, 1974
Bezdek JC: Pattern recognition with fuzzy objective function algorithms. Kluwer Academic, Norwell, 1981
J, Gray RM: Image Segmentation and Compression Using Hidden Markov Models (Monograph). Norwell: Kluwer Academic, 2000
Greig DM, Porteous BT, Seheult AH: Exact maximum a posteriori estimation for binary images. J Royal Statistical Society Series B 51:271–279, 1989
Wu Z, Leahy R: An optimal graph theoretic approach to data clustering: theory and its application to image segmentation. IEEE Transactions Pattern Analysis Machine Intelligence 15(11):1101–1113, 1993
Shi J, Malik J: Normalized cuts and image segmentation. IEEE Transactions Pattern Analysis Machine Intelligence 22(8):888–905, 2000
Angayarkanni P: MRI mammogram image segmentation using ncut method and genetic algorithm with partial filters. IJCSI International J Computer Science Issues 8(1):455–459, 2011
Gamio J, Belongie S, Majumdar S: Normalized cuts in 3D for spinal MRI segmentation. IEEE Transactions Medical Imaging 23(1):36–44, 2004
Malik J, Belongie S, Leung T, et al: Contour and texture analysis for image segmentation. International J Computer Vision 43(1):7–27, 2001
Ng A, Jordan M, Weiss Y: On spectral clustering: analysis and an algorithm. Advances Neural Information Processing Systems (NIPS) 849–856, 2001
Cour T, Benezit F, Shi J: Spectral segmentation with multiscale graph decomposition. IEEE Conference Computer Vision Pattern Recognition 2(2):1124–1131, 2005
Zelnik ML, Perona P: Self-tuning spectral clustering. Advances Neural Information Processing Systems (NIPS) 1601–1608, 2004
Hagen L, Kahng A: New spectral methods for ratio cut partitioning and clustering. IEEE Transactions Computer-Aided Design 11(9):1074–1085, 1992
Perona P, Malik J: Scale-space and edge detection using anisotropic diffusion. IEEE Transportation Pattern Analytical Machine Intelligence 12:629–639, 1990
Perona P, Shiota T, Malik J: Anisotropic diffusion. Geometry-Driven Diffusion Computer Vision 1:73–92, 1994
Mayer A, Greenspan H: An adaptive mean-shift framework for MRI brain segmentation. IEEE Transactions Image Processing 28(8):1238–1250, 2009
Sezgin M, Sankur B: Survey over image thresholding techniques and quantitative performance evaluation. J Electronic Imaging 13(1):146–165, 2004
Alt H, Guibas LJ: Discrete geometric shapes: matching, interpolation, and approximation. In: Sack JR, Urrutia J Eds. Handbook of Computational Geometry. Amsterdam: Elsevier Science, 2000, pp 121–153
Acknowledgments
The authors gratefully acknowledge the useful comments and suggestions of the editors and reviewers, which have improved this manuscript. This work is partially supported by the National Science Foundation of China (project no. 31000450, no. 81000613) and the Major State Basic Research Development Program of China (973 Program, no. 2010CB732500).
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Zheng, Q., Lu, Z., Feng, Q. et al. Adaptive Segmentation of Vertebral Bodies from Sagittal MR Images Based on Local Spatial Information and Gaussian Weighted Chi-Square Distance. J Digit Imaging 26, 578–593 (2013). https://doi.org/10.1007/s10278-012-9552-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-012-9552-9