A Statistical Local Binary Fitting Model for Blood Vessel Segmentation

Abstract:

Network structure such as blood vessels in medical images are important features for computer-aided diagnosis and follow-up of many diseases. In this study, a new model-based segmentation method is proposed to detect blood vessels in medical images. The Local Binary Fitting (LBF) model with statistical distribution function is used for this purpose. The brain tissues and cerebral vessels in the image are modeled by Gaussian distribution and uniform distribution respectively. The region distribution combined with the LBF model is used in curve evolution. And the level set method is developed to implement the curve evolution to assure high efficiency of the cerebrovascular segmentation. Comparisons with the LBF method show that our model can achieve better results.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 3430-3434
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.3430
• Online since: September 2013
• Authors: Shi Feng Zhao, Ming Quan Zhou, Kang Wang
• Keywords: Blood Vessel, Intensity Inhomogeneity, Segmentation

References

[1] Delphine Nain, Anthony J. Yezzi, Greg Turk. Vessel Segmentation Using A Shape Driven Flow. Medical Image Computing and Computer-Assisted Intervention - MICCAI , pp.51-59, (2004).

DOI: 10.1007/978-3-540-30135-6_7

[2] Ayman El-Baz, Georgy Gimel'farb, Ahmed Elnakib, Robert Falk, and Mohamed Abou El-Ghar. Fast, Accurate Unsupervised Segmentation of 3D Magnetic Resonance Angiography. Atherosclerosis Disease Management, 2011, pp.411-432.

DOI: 10.1007/978-1-4419-7222-4_14

[3] Lesage, D., Angelini, E. D., Bloch, I., and Funka-Lea, G. A review of 3D vessel lumen segmentation techniques: models, features and extraction schemes. Medical Image Analysis, 13(6), p.819–845, (2009).

DOI: 10.1016/j.media.2009.07.011

[4] Holtzman-Gazit, M., Kimmel, R., Peled, N., and Goldsher, D. Segmentation of thin structures in volumetric medical images. IEEE Transactions on Image Processing, 15, p.354–363, (2006).

DOI: 10.1109/tip.2005.860624

[5] Gooya, A., Liao, H., Matsumiya, K., Masamune, K., Masutani, Y., and Dohi, T. A variational method for geometric regularization of vascular segmentation in medical images. IEEE Transactions on Image Processing, 17(8), p.1295–1312, (2008).

DOI: 10.1109/tip.2008.925378

[6] Gooya, A., Dohi, T., Sakuma, I., and Liao, H. R-PLUS: a Riemannian anisotropic edge detection scheme for vascular segmentation. In MICCAI'08: Proceedings of the 11th international conference on medical image computing and computer-assisted intervention—Part I (p.262.

DOI: 10.1007/978-3-540-85988-8_32

[7] Cohen, L. D., and Deschamps, T. Segmentation of 3D tubular objects with adaptive front propagation and minimal tree extraction for 3D medical imaging. Computer Methods in Biomechanics and Biomedical Engineering, 10(4), p.289–305, (2007).

DOI: 10.1080/10255840701328239

[8] M. Descoteaux, L. Collins and K. Siddiqi. A Multi-Scale Geometric Flow for Segmenting Vasculature in MRI : Theory and Validation. Medical Image Analysis, 12(4), pp.497-513. August (2008).

DOI: 10.1016/j.media.2008.02.003

[9] Law, M. W. K., and Chung, A. C. S. Weighted local variancebased edge detection and its application to vascular segmentation in magnetic resonance angiography. IEEE Transactions on Medical Imaging, 26(9), p.1224–1241, (2007).

DOI: 10.1109/tmi.2007.903231