Vertebrae Localization in Pathological Spine CT via Dense Classification from Sparse Annotations

  • Ben Glocker
  • Darko Zikic
  • Ender Konukoglu
  • David R. Haynor
  • Antonio Criminisi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8150)


Accurate localization and identification of vertebrae in spinal imaging is crucial for the clinical tasks of diagnosis, surgical planning, and post-operative assessment. The main difficulties for automatic methods arise from the frequent presence of abnormal spine curvature, small field of view, and image artifacts caused by surgical implants. Many previous methods rely on parametric models of appearance and shape whose performance can substantially degrade for pathological cases.

We propose a robust localization and identification algorithm which builds upon supervised classification forests and avoids an explicit parametric model of appearance. We overcome the tedious requirement for dense annotations by a semi-automatic labeling strategy. Sparse centroid annotations are transformed into dense probabilistic labels which capture the inherent identification uncertainty. Using the dense labels, we learn a discriminative centroid classifier based on local and contextual intensity features which is robust to typical characteristics of spinal pathologies and image artifacts. Extensive evaluation is performed on a challenging dataset of 224 spine CT scans of patients with varying pathologies including high-grade scoliosis, kyphosis, and presence of surgical implants. Additionally, we test our method on a heterogeneous dataset of another 200, mostly abdominal, CTs. Quantitative evaluation is carried out with respect to localization errors and identification rates, and compared to a recently proposed method. Our approach is efficient and outperforms state-of-the-art on pathological cases.


Image Point Appearance Model Image Artifact Dense Label Surgical Implant 
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.


  1. 1.
    Ben Ayed, I., Punithakumar, K., Minhas, R., Joshi, R., Garvin, G.J.: Vertebral Body Segmentation in MRI via Convex Relaxation and Distribution Matching. In: MICCAI 2012, Part I. LNCS, vol. 7510, pp. 520–527. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  2. 2.
    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, Part III. LNCS, vol. 7512, pp. 509–516. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Steger, S., Wesarg, S.: Automated Skeleton Based Multi-modal Deformable Registration of Head&Neck Datasets. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part II. LNCS, vol. 7511, pp. 66–73. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  4. 4.
    Lecron, F., Boisvert, J., Mahmoudi, S., Labelle, H., Benjelloun, M.: Fast 3D Spine Reconstruction of Postoperative Patients Using a Multilevel Statistical Model. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part II. LNCS, vol. 7511, pp. 446–453. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Hsiang, J.: Wrong-level surgery: A unique problem in spine surgery. Surg. Neurol. Int. 2(47) (2011)Google Scholar
  6. 6.
    Ma, J., Lu, L., Zhan, Y., Zhou, X., Salganicoff, M., Krishnan, A.: Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part I. LNCS, vol. 6361, pp. 19–27. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Oktay, A.B., Akgul, Y.S.: Localization of the Lumbar discs using machine learning and exact probabilistic inference. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 158–165. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  8. 8.
    Schmidt, S., Kappes, J., Bergtholdt, M., Pekar, V., Dries, S., Bystrov, D., Schnörr, C.: Spine detection and labeling using a parts-based graphical model. In: Karssemeijer, N., Lelieveldt, B. (eds.) IPMI 2007. LNCS, vol. 4584, pp. 122–133. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Huang, S.H., Chu, Y.H., Lai, S.H., Novak, C.L.: Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI. TMI 28(10), 1595–1605 (2009)Google Scholar
  10. 10.
    Kelm, B.M., Zhou, S.K., Suehling, M., Zheng, Y., Wels, M., Comaniciu, D.: Detection of 3D spinal geometry using iterated marginal space learning. In: Menze, B., Langs, G., Tu, Z., Criminisi, A. (eds.) MICCAI 2010. LNCS, vol. 6533, pp. 96–105. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Glocker, B., Feulner, J., Criminisi, A., Haynor, D.R., Konukoglu, E.: Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 590–598. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  12. 12.
    Klinder, T., Ostermann, J., Ehm, M., Franz, A., Kneser, R., Lorenz, C.: Automated model-based vertebra detection, identification, and segmentation in CT images. MedIA 13(3), 471–482 (2009)Google Scholar
  13. 13.
    Zhan, Y., Maneesh, D., Harder, M., Zhou, X.S.: Robust MR Spine Detection Using Hierarchical Learning and Local Articulated Model. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. 7510, pp. 141–148. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  14. 14.
    Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  15. 15.
    Caruana, R., Karampatziakis, N., Yessenalina, A.: An empirical evaluation of supervised learning in high dimensions. In: ICML, pp. 96–103 (2008)Google Scholar
  16. 16.
    Budvytis, I., Badrinarayanan, V., Cipolla, R.: Semi-supervised video segmentation using tree structured graphical models. In: CVPR, pp. 2257–2264 (2011)Google Scholar
  17. 17.
    Criminisi, A., Shotton, J., Bucciarelli, S.: Decision forests with long-range spatial context for organ localization in CT volumes. In: MICCAI Workshop on Probabilistic Models for Medical Image Analysis (2009)Google Scholar
  18. 18.
    Cheng, Y.: Mean shift, mode seeking, and clustering. PAMI 17(8), 790–799 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Ben Glocker
    • 1
  • Darko Zikic
    • 1
  • Ender Konukoglu
    • 2
  • David R. Haynor
    • 3
  • Antonio Criminisi
    • 1
  1. 1.Microsoft ResearchCambridgeUK
  2. 2.Martinos Center for Biomedical Imaging, MGH, Harvard Medical SchoolUSA
  3. 3.University of WashingtonSeattleUSA

Personalised recommendations