Segmentation of Pathological Spines in CT Images Using a Two-Way CNN and a Collision-Based Model

  • Robert KorezEmail author
  • Boštjan Likar
  • Franjo Pernuš
  • Tomaž Vrtovec
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10734)


Accurate boundary delineation and segmentation of pathological spines is indispensable in spine-related applications that rely on the knowledge of vertebral shape. However, exact vertebral boundaries are often difficult to determine due to articulation of vertebrae with each other that may cause vertebral overlaps in segmentations of adjacent vertebrae. To solve this problem, we propose a novel method that consists of two steps. In the first step, the probability maps that determine vertebral boundaries are obtained from a two-way convolutional neural network, trained on normal thoracolumbar spines. In the second step, a collision-based model that consists of (at least two) consecutive vertebra mesh models is initialized close to the observed vertebrae and vertices of each mesh are displaced towards the detected boundaries. As this can lead to mesh collisions in the form of vertices of one mesh penetrating the adjacent one (and/or vice versa), these vertices are efficiently detected and then driven out of the adjacent mesh while locally preserving the shape of the corresponding mesh. By applying the proposed method to 15 three-dimensional computed tomography images of the lumbar spine containing 75 normal and fractured vertebrae, quantitative comparison against reference vertebra segmentations yielded an overall mean Dice similarity coefficient of 93.2%, mean symmetric surface distance of 0.5 mm, and Hausdorff distance of 8.4 mm.


Image segmentation Computed tomography Pathological spine Two-way convolutional neural network Collision-based model 



This work was supported by the Slovenian Research Agency (ARRS) under grants P2-0232, J2-5473, J7-6781 and J2-7118.


  1. 1.
    Kim, Y., Kim, D.: A fully automatic vertebra segmentation method using 3D deformable fences. Comput. Med. Imag. Graph. 33(5), 343–352 (2009)CrossRefGoogle Scholar
  2. 2.
    Klinder, T., Ostermann, J., Ehm, M., Franz, A., Kneser, R., Lorenz, C.: Automated model-based vertebra detection, identification, and segmentation in CT images. Med. Image Anal. 13(3), 471–482 (2009)CrossRefGoogle Scholar
  3. 3.
    Weese, J., Kaus, M., Lorenz, C., Lobregt, S., Truyen, R., Pekar, V.: Shape constrained deformable models for 3D medical image segmentation. In: Insana, M.F., Leahy, R.M. (eds.) IPMI 2001. LNCS, vol. 2082, pp. 380–387. Springer, Heidelberg (2001). Scholar
  4. 4.
    Rasoulian, A., Rohling, R., Abolmaesumi, P.: Lumbar spine segmentation using a statistical multi-vertebrae anatomical shape+pose model. IEEE Trans. Med. Imaging 32(10), 1890–1900 (2013)CrossRefGoogle Scholar
  5. 5.
    Castro-Mateos, I., Pozo, J., Pereañez, M., Lekadir, K., Lazary, A., Frangi, A.: Statistical interspace models (SIMs): application to robust 3D spine segmentation. IEEE Trans. Med. Imaging 34(8), 1663–1675 (2015)CrossRefGoogle Scholar
  6. 6.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  7. 7.
    Chen, H., Shen, C., Qin, J., Ni, D., Shi, L., Cheng, J.C.Y., Heng, P.-A.: Automatic localization and identification of vertebrae in Spine CT via a joint learning model with deep neural networks. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 515–522. Springer, Cham (2015). Scholar
  8. 8.
    Chen, H., Dou, Q., Wang, X., Qin, J., Cheng, J.C.Y., Heng, P.-A.: 3D fully convolutional networks for intervertebral disc localization and segmentation. In: Zheng, G., Liao, H., Jannin, P., Cattin, P., Lee, S.-L. (eds.) MIAR 2016. LNCS, vol. 9805, pp. 375–382. Springer, Cham (2016). Scholar
  9. 9.
    Jamaludin, A., Kadir, T., Zisserman, A.: SpineNet: automatically pinpointing classification evidence in Spinal MRIs. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 166–175. Springer, Cham (2016). Scholar
  10. 10.
    Davy, A., Havaei, M., Warde-Farley, D., Biard, A., Tran, L., Jodoin, P.M., Courville, A., Larochelle, H., Pal, C., Bengio, Y.: Brain tumor segmentation with deep neural networks. In: Proceedings of the 3rd MICCAI Multimodal Brain Tumor Segmentation Challenge - BRATS 2014, pp. 1–5 (2014)Google Scholar
  11. 11.
    Schlegl, T., Waldstein, S.M., Vogl, W.-D., Schmidt-Erfurth, U., Langs, G.: Predicting semantic descriptions from medical images with convolutional neural networks. In: Ourselin, S., Alexander, D.C., Westin, C.-F., Cardoso, M.J. (eds.) IPMI 2015. LNCS, vol. 9123, pp. 437–448. Springer, Cham (2015). Scholar
  12. 12.
    Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.M., Larochelle, H.: Brain tumor segmentation with deep neural networks. Med. Image Anal. 35, 18–31 (2017)CrossRefGoogle Scholar
  13. 13.
    Kamnitsas, K., Ledig, C., Newcombe, V.F., Simpson, J.P., Kane, A.D., Menon, D.K., Rueckert, D., Glocker, B.: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78 (2017)CrossRefGoogle Scholar
  14. 14.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition - CVPR 2015, pp. 3431–3440 (2015)Google Scholar
  15. 15.
    Sorkine, O., Alexa, M.: As-rigid-as-possible surface modeling. In: Proceedings of the 5th Symposium on Geometry Processing - SGP 2007, pp. 1–8 (2007)Google Scholar
  16. 16.
    Möller, T., Trumbore, B.: Fast, minimum storage ray-triangle intersection. J. Graph. Tools 2(1), 21–28 (1997)CrossRefGoogle Scholar
  17. 17.
    Ibragimov, B., Likar, B., Pernuš, F., Vrtovec, T.: Shape representation for efficient landmark-based segmentation in 3-D. IEEE Trans. Med. Imaging 33(4), 861–874 (2014)CrossRefGoogle Scholar
  18. 18.
    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
  19. 19.
    Korez, R., Ibragimov, B., Likar, B., Pernuš, F., Vrtovec, T.: A framework for automated spine and vertebrae interpolation-based detection and model-based segmentation. IEEE Trans. Med. Imaging 34(8), 1649–1662 (2015)CrossRefGoogle Scholar
  20. 20.
    Botsch, M., Kobbelt, L.: A remeshing approach to multiresolution modeling. In: Proceedings of the 2nd Eurographics Symposium on Geometry Processing - SGP 2004, pp. 189–196 (2004)Google Scholar
  21. 21.
    Bossa, M., Olmos, S.: Multi-object statistical pose+shape models. In: Proceedings of the 4th IEEE International Symposium on Biomedical Imaging - ISBI 2007, pp. 1204–1207. IEEE (2007)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Robert Korez
    • 1
    Email author
  • Boštjan Likar
    • 1
  • Franjo Pernuš
    • 1
  • Tomaž Vrtovec
    • 1
  1. 1.Faculty of Electrical EngineeringUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations