Deep Belief Network Based Vertebra Segmentation for CT Images

  • Syed Furqan Qadri
  • Mubashir Ahmad
  • Danni Ai
  • Jian YangEmail author
  • Yongtian Wang
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 875)


Automatic vertebra segmentation is a challenging task from CT images due to anatomically complexity, shape variation and vertebrae articulation with each other. Deep Learning is a machine learning paradigm that focuses on deep hierarchical learning modeling of input data. In this paper, we propose a novel approach of automatic vertebrae segmentation from computed tomography (CT) images by using deep belief networks (BDNs) modeling. Using the DBN model, the contexture features of vertebra from CT images are extracted automatically by an unsupervised pattern called pre-training and followed by supervised training called back-propagation algorithm; then segmentation the vertebra from other abdominal structure. To evaluate the performance, we computed the overall accuracy (94.2%), sensitivity (83.2%), specificity (94.8%) and mean Dice coefficients (0.85 ± 0.03) for segmentation evaluation. Experimental results show that our proposed model provides a more accuracy in vertebra segmentation compared to the previous state of art methods.


Segmentation Deep belief network (BDN) Pre-training Back-propagation algorithm 



This work was supported by the National Science Foundation Program of China (61527827).


  1. 1.
    Kadoury, S., Labelle, H., Paragios, N.: Spine segmentation in medical images using manifold embeddings and higher-order MRFs. Med. Imaging IEEE Trans. 32(7), 1227–1238 (2013)CrossRefGoogle Scholar
  2. 2.
    Rasoulian, A., Rohling, R., Abolmaesumi, P.: Lumbar spine segmentation using a statistical multi-vertebrae anatomical shape+pose model. Med. Imaging IEEE Trans. 32(10), 1890–1900 (2013)CrossRefGoogle Scholar
  3. 3.
    Aslan, M.S., Farag, A.A., Arnold, B., Xiang, P.: Segmentation of vertebrae using level sets with expectation maximization algorithm. IEEE 2010–2013 (2011)Google Scholar
  4. 4.
    Ghosh, S., Alomari, R., Chaudhary, V., Dhillon G.: Automatic lumbar vertebrae segmentation from clinical CT for wedge compression fracture diagnosis. In: SPIE, pp. 1–9 (2011)Google Scholar
  5. 5.
    Narkhede, H.P.: Review of image segmentation techniques. Int. J. Sci. Mod. Eng. 2319–6386 (2013)Google Scholar
  6. 6.
    Aslan, M.S., Ali, A., Farag, A., Rara, A., Arnold, B., Xiang, P.: 3D vertebrae body segmentation using shape based graph cuts. In: IEEE ICPR, pp. 3951–3954 (2010)Google Scholar
  7. 7.
    Suzani, A., Rasoulian, A., Seitel, A., Fels, S., Rohling, R.N.: Deep learning for automatic localization, identification, and segmentation of vertebral bodies in volumetric MR images, vol. 9415, pp. 1–7 (2015)Google Scholar
  8. 8.
    Herring, J., Dawant, B.: Automatic lumbar vertebral identification using surface-based registration. Comput. Biomed. Res. 34(2), 74–84 (2001)Google Scholar
  9. 9.
    Klinder, T., Wolz, R., Lorenz, C., Franz, A., Ostermann, J.: Spine segmentation using articulated shape models. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008. LNCS, vol. 5241, pp. 227–234. Springer, Heidelberg (2008). Scholar
  10. 10.
    Lim, P.H., Bagci, U., Bai, L.: Introducing willmore flow into level set segmentation of spinal vertebrae. IEEE Trans. Biomed. Eng. 60, 115–122 (2013)CrossRefGoogle Scholar
  11. 11.
    Naegel, B.: Using mathematical morphology for the anatomical labeling of vertebrae from 3D CT-scan images. Comput. Med. Imaging Graph. 31(3), 141–156 (2007)CrossRefGoogle Scholar
  12. 12.
    Ghebreab, S., Smeulders, A.: Combining strings and neck- laces for interactive three-dimensional segmentation of spinal images using an integral deformable spine model. IEEE Trans. Biomed. Eng. 51(10), 1821–1829 (2004)CrossRefGoogle Scholar
  13. 13.
    Hacihaliloglu, I., Rasoulian, A., Rohling, R.N., Abolmaesumi, P.: Local phase tensor features for 3-D ultrasound to statistical shape+pose spine model registration. IEEE Trans. Med. Imaging 33, 2167–2179 (2014)CrossRefGoogle Scholar
  14. 14.
    Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Khatami, A., Khosravi, A., Nguyen, T., Lim, C.P., Nahavandi, S.: Medical image analysis using wavelet transform and deep belief networks. Expert Syst. Appl. 86, 190–198 (2017)CrossRefGoogle Scholar
  16. 16.
    Abdel-Zaher, A.M., Eldeib, A.M.: Breast cancer classification using deep belief networks. Expert Syst. Appl. 46, 139–144 (2016)CrossRefGoogle Scholar
  17. 17.
    Sun, W., Zheng, B., Qian, W.: Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis. Comput. Biol. Med. 89, 530–539 (2017)CrossRefGoogle Scholar
  18. 18.
    Hatipoglu, N., Bilgin, G.: Cell segmentation in histopathological images with deep learning algorithms by utilizing spatial relationships. Med. Biol. Eng. Comput. 55, 1829–1848 (2017)CrossRefGoogle Scholar
  19. 19.
    Pinaya, W.H.L., et al.: Using deep belief network modelling to characterize differences in brain morphometry in schizophrenia. Sci. Rep. 6, 38897 (2016)CrossRefGoogle Scholar
  20. 20.
    Zhang, S., et al.: A deep learning framework for modeling structural features of RNA-binding protein targets. Nucleic Acids Res. 44, e32 (2015)CrossRefGoogle Scholar
  21. 21.
    Li, H., Li, X., Ramanathan, M., Zhang, A.: Identifying informative risk factors and predicting bone disease progression via deep belief networks. Methods 69, 257–265 (2014)CrossRefGoogle Scholar
  22. 22.
    Yao, J., Burns, J.E., Munoz, H., Summers, R.M.: Detection of vertebral body fractures based on cortical shell unwrapping. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012. LNCS, vol. 7512, pp. 509–516. Springer, Heidelberg (2012). Scholar
  23. 23.
    Ahmad, M., Yang, J., Ai, D., Qadri, S.F., Wang, Y.: Deep-stacked auto encoder for liver segmentation. In: Wang, Y., et al. (eds.) IGTA 2017. CCIS, vol. 757, pp. 243–251. Springer, Singapore (2018). Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Syed Furqan Qadri
    • 1
  • Mubashir Ahmad
    • 2
  • Danni Ai
    • 2
  • Jian Yang
    • 2
    Email author
  • Yongtian Wang
    • 1
    • 2
  1. 1.School of Computer Science and TechnologyBeijing Institute of TechnologyBeijingChina
  2. 2.Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and ElectronicsBeijing Institute of TechnologyBeijingChina

Personalised recommendations