Landmark-guided diffeomorphic demons algorithm and its application to automatic segmentation of the whole spine and pelvis in CT images

  • Shouhei HanaokaEmail author
  • Yoshitaka Masutani
  • Mitsutaka Nemoto
  • Yukihiro Nomura
  • Soichiro Miki
  • Takeharu Yoshikawa
  • Naoto Hayashi
  • Kuni Ohtomo
  • Akinobu Shimizu
Original Article



A fully automatic multiatlas-based method for segmentation of the spine and pelvis in a torso CT volume is proposed. A novel landmark-guided diffeomorphic demons algorithm is used to register a given CT image to multiple atlas volumes. This algorithm can utilize both grayscale image information and given landmark coordinate information optimally.


The segmentation has four steps. Firstly, 170 bony landmarks are detected in the given volume. Using these landmark positions, an atlas selection procedure is performed to reduce the computational cost of the following registration. Then the chosen atlas volumes are registered to the given CT image. Finally, voxelwise label voting is performed to determine the final segmentation result.


The proposed method was evaluated using 50 torso CT datasets as well as the public SpineWeb dataset. As a result, a mean distance error of \(0.59\pm 0.14\hbox { mm}\) and a mean Dice coefficient of \(0.90\pm 0.02\) were achieved for the whole spine and the pelvic bones, which are competitive with other state-of-the-art methods.


From the experimental results, the usefulness of the proposed segmentation method was validated.


Multiatlas segmentation Diffeomorphic demons algorithm Anatomical landmark Spine Pelvis 



This work was supported in part by JSPS Grant-in-Aid for Scientific Research KAKENHI Grant Numbers 15H01108 and 15K19775.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical standard

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1975 Declaration of Helsinki, as revised in 2008(5). For this type of study, formal consent is not required.


  1. 1.
    Yao J, O’Connor SD, Summers R (2006) Computer aided lytic bone metastasis detection using regular CT images. Reinhardt JM, Pluim JPW (eds) Proc. SPIE 6144, Medical Imaging 2006: Image Processing, vol. 6144. San Diego, CA, pp 614459. doi: 10.1117/12.652288
  2. 2.
    Létourneau D, Kaus M, Wong R, Vloet A, Fitzpatrick DA, Gospodarowicz M, Jaffray DA (2008) Semiautomatic vertebrae visualization, detection, and identification for online palliative radiotherapy of bone metastases of the spine). Med Phys 35(1):367–376CrossRefPubMedGoogle Scholar
  3. 3.
    Ferrari V, Parchi P, Condino S, Carbone M, Baluganti A, Ferrari M, Mosca F, Lisanti M (2013) An optimal design for patient-specific templates for pedicle spine screws placement. Int J Med Robot Comput Assist Surg 9(3):298–304CrossRefGoogle Scholar
  4. 4.
    Pereañez M, Lekadir K, Hoogendoorn C, Castro-Mateos I, Frangi A (2015) Detailed vertebral segmentation using part-based decomposition and conditional shape models. In: Yao J, Glocker B, Klinder T, Li S (eds) Recent advances in computational methods and clinical applications for spine imaging. Springer, Switzerland, pp 95–103Google Scholar
  5. 5.
    Kadoury S, Labelle H, Paragios N (2013) Spine segmentation in medical images using manifold embeddings and higher-order MRFs. IEEE Trans Med Imaging 32(7):1227–1238CrossRefPubMedGoogle Scholar
  6. 6.
    Klinder T, Ostermann J, Ehm M, Franz A, Kneser R, Lorenz C (2009) Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal 13(3):471–482CrossRefPubMedGoogle Scholar
  7. 7.
    Rasoulian A, Rohling R, Abolmaesumi P (2013) Lumbar spine segmentation using a statistical multi-vertebrae anatomical shape+pose model. IEEE Trans Med Imaging 32(10):1890–1900CrossRefPubMedGoogle Scholar
  8. 8.
    Castro-Mateos I, Pozo JM, Pereanez M, Lekadir K, Lazary A, Frangi AF (2015) Statistical interspace models (SIMs): application to robust 3D spine segmentation. IEEE Trans Med Imaging 34(8):1663–1675CrossRefPubMedGoogle Scholar
  9. 9.
    Korez R, Ibragimov B, Likar B, Pernus F, Vrtovec T (2015) A framework for automated spine and vertebrae interpolation-based detection and model-based segmentation. IEEE Trans Med Imaging 34(8):1649–1662CrossRefPubMedGoogle Scholar
  10. 10.
    Iglesias JE, Sabuncu MR (2015) Multi-atlas segmentation of biomedical images: a survey. Med Image Anal 24(1):205–219CrossRefPubMedPubMedCentralGoogle Scholar
  11. 11.
    Aljabar P, Heckemann RA, Hammers A, Hajnal JV, Rueckert D (2009) Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy. Neuroimage 46(3):726–738CrossRefPubMedGoogle Scholar
  12. 12.
    van Rikxoort E, Arzhaeva Y, van Ginneken B (2007) Automatic segmentation of the liver in computed tomography scans with voxel classification and atlas matching. In: Proceedings of the MICCAI workshop, 3D segmentation in the clinic: a grand challenge, 2007, pp 101–108Google Scholar
  13. 13.
    Rohlfing T, Brandt R, Menzel R, Maurer CR Jr (2004) Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains. NeuroImage 21(4):1428–1442. doi: 10.1016/j.neuroimage.2003.11.010 CrossRefPubMedGoogle Scholar
  14. 14.
    Heckemann RA, Hajnal JV, Aljabar P, Rueckert D, Hammers A (2006) Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. NeuroImage 33(1):115–126. doi: 10.1016/j.neuroimage.2006.05.061 CrossRefPubMedGoogle Scholar
  15. 15.
    Sanroma G, Wu G, Gao Y, Shen D (2014) Learning to rank atlases for multiple-atlas segmentation. IEEE Trans Med Imaging 33:1939–1953CrossRefPubMedPubMedCentralGoogle Scholar
  16. 16.
    McIntosh C, Purdie TG (2016) Contextual atlas regression forests: multiple-atlas-based automated dose prediction in radiation therapy. IEEE Trans Med Imaging 35:1000–1012CrossRefPubMedGoogle Scholar
  17. 17.
    Konukoglu E, Glocker B, Zikic D, Criminisi A (2012) Neighbourhood approximation forests. In: Ayache N, Delingette H, Golland P, Mori K (eds) Medical image computing and computer-assisted intervention—MICCAI 2012: 15th international conference, Nice, France, October 1–5, 2012, proceedings, part III. Springer, Berlin Heidelberg, pp 75–82Google Scholar
  18. 18.
    Thirion J-P (1998) Image matching as a diffusion process: an analogy with Maxwell’s demons. Med Image Anal 2(3):243–260CrossRefPubMedGoogle Scholar
  19. 19.
    Vercauteren T, Pennec X, Perchant A, Ayache N (2008) Symmetric log-domain diffeomorphic registration: a demons-based approach. In: Metaxas D, Axel L, Fichtinger G, Székely G (eds) Medical image computing and computer-assisted intervention–MICCAI 2008. Springer, Heidelberg, pp 754–761Google Scholar
  20. 20.
    Forsberg D (2014) Atlas-based segmentation of the thoracic and lumbar vertebrae. In: Yao J, Glocker B, Klinder T, Li S (eds) Recent advances in computational methods and clinical applications for spine imaging. Springer International Publishing, Cham, pp 215–220Google Scholar
  21. 21.
    Wang Z, Zhen X, Tay K, Osman S, Romano W, Li S (2015) Regression segmentation for spinal images. IEEE Trans Med Imaging 34(8):1640–1648CrossRefPubMedGoogle Scholar
  22. 22.
    Yao J, Burns JE, Forsberg D, Seitel A, Rasoulian A, Abolmaesumi P, Hammernik K, Urschler M, Ibragimov B, Korez R, Vrtovec T, Castro-Mateos I, Pozo JM, Frangi AF, Summers RM, Li S (2016) A multi-center milestone study of clinical vertebral CT segmentation. Comput Med Imaging Graph 49:16–28CrossRefPubMedGoogle Scholar
  23. 23.
    Kurtek S, Srivastava A, Klassen E, Laga H (2013) Landmark-guided elastic shape analysis of spherically-parameterized surfaces. Comput Graph Forum 32:429–438CrossRefGoogle Scholar
  24. 24.
    Kearney V, Chen S, Gu X, Chiu T, Liu H, Jiang L, Wang J, Yordy J, Nedzi L, Mao W (2015) Automated landmark-guided deformable image registration. Phys Med Biol 60:101CrossRefPubMedGoogle Scholar
  25. 25.
    Xie Q, Kurtek S, Klassen E, Christensen GE, Srivastava A (2014) Metric-based pairwise and multiple image registration. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision—ECCV 2014: 13th European conference, Zurich, Switzerland, September 6–12, 2014, proceedings, part II. Springer International Publishing, Cham, pp 236–250Google Scholar
  26. 26.
    Lam KC, Gu X, Lui LM (2015) Landmark constrained genus-one surface Teichmüller map applied to surface registration in medical imaging. Med Image Anal 25:45–55CrossRefPubMedGoogle Scholar
  27. 27.
    Nemoto M, Masutani Y, Hanaoka S, Nomura Y, Yoshikawa T, Hayashi N, Yoshioka N, Ohtomo K (2011) A unified framework for concurrent detection of anatomical landmarks for medical image understanding. In: SPIE medical imaging 2011. 7962, 14 Mar 2011. pp 79623E-79623E-79613. doi: 10.1117/12.878327
  28. 28.
    Hanaoka S, Shimizu A, Nemoto M, Nomura Y, Miki S, Yoshikawa T, Hayashi N, Ohtomo K, Masutani Y (2017) Automatic detection of over 100 anatomical landmarks in medical CT images: a framework with independent detectors and combinatorial optimization. Med Image Anal 35:192–214. doi: 10.1016/
  29. 29.
    Vercauteren T, Pennec X, Perchant A, Ayache N (2007) Non-parametric diffeomorphic image registration with the demons algorithm. In: Ayache N, Ourselin S, Maeder A (eds) Medical image computing and computer-assisted intervention–MICCAI 2007. Springer, Heidelberg, pp 319–326Google Scholar
  30. 30.
    Seitel A, Rasoulian A, Rohling R, Abolmaesumi P (2015) Lumbar and thoracic spine segmentation using a statistical multi-object shape + pose model. In: Yao J, Glocker B, Klinder T, Li S (eds) Recent advances in computational methods and clinical applications for spine imaging. Springer International Publishing, Cham, pp 221–225CrossRefGoogle Scholar
  31. 31.
    Hammernik K, Ebner T, Stern D, Urschler M, Pock T (2015) Vertebrae segmentation in 3D CT images based on a variational framework. In: Yao J, Glocker B, Klinder T, Li S (eds) Recent advances in computational methods and clinical applications for spine imaging. Springer International Publishing, Cham, pp 227–233CrossRefGoogle Scholar
  32. 32.
    Korez R, Ibragimov B, Likar B, Pernuš F, Vrtovec T (2015) Interpolation-based shape-constrained deformable model approach for segmentation of vertebrae from ct spine images. In: Yao J, Glocker B, Klinder T, Li S (eds) Recent advances in computational methods and clinical applications for spine imaging. Springer International Publishing, Cham, pp 235–240CrossRefGoogle Scholar
  33. 33.
    Castro-Mateos I, Pozo JM, Lazary A, Frangi A (2015) 3D vertebra segmentation by feature selection active shape model. In: Yao J, Glocker B, Klinder T, Li S (eds) Recent advances in computational methods and clinical applications for spine imaging. Springer International Publishing, Cham, pp 241–245CrossRefGoogle Scholar
  34. 34.
    Knutsson H, Andersson M (2005) Morphons: segmentation using elastic canvas and paint on priors. In: IEEE international conference on image processing 2005, 11–14 Sept. 2005. pp II-1226–II-1229. doi: 10.1109/ICIP.2005.1530283
  35. 35.
    Paik NC, Lim CS, Jang HS (2013) Numeric and morphological verification of lumbosacral segments in 8280 consecutive patients. Spine 38(10):E573–578. doi: 10.1097/BRS.0b013e31828b7195 CrossRefPubMedGoogle Scholar
  36. 36.
    Hanaoka S, Masutani Y, Nemoto M, Nomura Y, Yoshikawa T, Hayashi N, Yoshioka N, Ohtomo K (2011) Probabilistic modeling of landmark distances and structure for anomaly-proof landmark detection. In: Proceedings of the third international workshop on mathematical foundations of computational anatomy, 2011, pp 159–169Google Scholar

Copyright information

© CARS 2016

Authors and Affiliations

  1. 1.Department of RadiologyThe University of Tokyo HospitalTokyoJapan
  2. 2.Tokyo University of Agriculture and TechnologyKoganei-shiJapan
  3. 3.Department of Biomedical Information SciencesHiroshima City UniversityHiroshimaJapan
  4. 4.Department of Computational Diagnostic Radiology and Preventive MedicineThe University of Tokyo HospitalTokyoJapan

Personalised recommendations