Advertisement

2D-PCA Based Tensor Level Set Framework for Vertebral Body Segmentation

  • Ahmed ShalabyEmail author
  • Aly Farag
  • Melih Aslan
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 17)

Abstract

In this paper, a novel statistical shape modeling method is developed for the vertebral body (VB) segmentation framework. Two-dimensional principal component analysis (2D-PCA) technique is exploited to extract the shape prior. The obtained shape model is then embedded into the image domain to develop a new shape-based segmentation approach. Our framework consists of four main steps: (1) shape model construction using 2D-PCA, (2) the detection of the VB region using the Matched filter, (3) initial segmentation using a new region-based tensor level set model, and (4) registration of the shape priors and initially segmented region to obtain the final segmentation. The proposed method is validated on a Phantom as well as clinical CT images with various Gaussian noise levels. The experimental results show that the noise immunity and the segmentation accuracy of our framework are much higher than scalar level sets approaches. Additionally, the construction of the shape model using 2D-PCA is computationally more efficient than PCA.

Keywords

Vertebral Body Training Image Shape Model Segmentation Accuracy Clinical Dataset 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Abdelmunim, H., Farag, A.A.: Curve/surface representation and evolution using vector level sets with application to the shape-based pattern analysis and machine intelligence. IEEE Trans. 29(6) (2007)Google Scholar
  2. 2.
    Aslan, M.S., Abdelmunim, H., Farag, A.A., Arnold, B., Mustafa, E., Xiang, P.: A new shape based segmentation framework using statistical and variational methods. In: Proceedings of IEEE International Conference on Image Processing (ICIP) (2011)Google Scholar
  3. 3.
    Aslan, M.S., Ali, A., Chen, D., Arnold, B., Farag, A.A., Xiang, P.: 3D vertebrae segmentation using graph cuts with shape prior constraints. In: Proceedings of IEEE International Conference on Image Processing (ICIP) (2010)Google Scholar
  4. 4.
    Aslan, M.S., Ali, A., Farag, A.A., Abdelmunim, H., Arnold, B., Xiang, P.: A new segmentation and registration approach for vertebral body analysis. Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI) (2011)Google Scholar
  5. 5.
    Aslan, M.S., Ali, A., Farag, A.A., Arnold, B., Chen, D., Xiang P.: 3D vertebrae segmentation in CT images with random noises. In: Proceedings of the International Conference on Pattern Recognition (ICPR’10) (2010)Google Scholar
  6. 6.
    Aslan, M.S., Ali, A., Rara, H., Arnold, B., Farag, A.A., Fahmi, R., Xiang, P.: A novel 3D segmentation of vertebral bones from volumetric CT images using graph cuts. ISVC’09 (2009)Google Scholar
  7. 7.
    Aslan, M.S., Mostafa, E., Abdelmunim, H., Shalaby, A., Farag, A.A., Arnold, B.: A novel probabilistic simultaneous segmentation and registration using level set. Proceedings of the International Conference on Image Processing (ICIP) (2011)Google Scholar
  8. 8.
    Chen, T.F., Vese, L.A.: Active contours without edge. IEEE Trans. Image Process. 10(2), 266–277 (2001)CrossRefGoogle Scholar
  9. 9.
    Kalender, W.A., Felsenberg, D., Genant, H., Fischer, M., Dequeker, J., Reeve, J.: The European spine phantom–a tool for standardization and quality control in spinal bone measurements by DXA and QCT. J. Radiol. 20, 83–92 (1995)Google Scholar
  10. 10.
    Kaminsky, J., Klinge, P., Bokemeyer, M., Luedemann, W., Samii, M.: Specially adapted interactive tools for an improved 3D-segmentation of the spine. Comput. Med. Imaging Graph. 28(3), 118–127 (2004)CrossRefGoogle Scholar
  11. 11.
    Kang, Y., Engelke, K., Kalender, W.A.: New accurate and precise 3D segmentation method for skeletal structures in volumetric CT data. IEEE Trans. Med. Imaging (TMI) 22(5), 586–598 (2003)CrossRefGoogle Scholar
  12. 12.
    Mastmeyer, A., Engelke, K., Fuchs, C., Kalender, W.A.: A hierarchical 3D segmentation method and the definition of vertebral body coordinate systems for QCT of the lumbar spine. Med. Image Anal. 10(4), 560–577 (2006)CrossRefGoogle Scholar
  13. 13.
    Shalaby, A., Mahmoud, A., Mostafa, E., Abdoulmalek, A., Farag, A.A.: Segmentation framework of vertebral body using 2D-PCA. In: Proceedings of 15th Saudi Technical Exchange Meeting, (STEM’12), Dhahran, Saudi Arabia, pp. 81–85. 17–19 Dec 2012Google Scholar
  14. 14.
    Wang, B., Gao, X., Tao, D., Li, X.: A unified tensor level set for image segmentation. IEEE Trans. Syst. Man Cybern. 40(3), 857–867 (2010)CrossRefGoogle Scholar
  15. 15.
    Yang, J., Zhang, D., Frangi, A.F., Yang, J.: Two-dimensional PCA: a new approach to appearance based face representation and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 26(1), 131–137 (2004)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Computer Vision and Image Processing LaboratoryUniversity of LouisvilleLouisvilleUSA

Personalised recommendations