Skip to main content
Springer Nature Link
Log in

Personalized Graphical Models for Anatomical Landmark Localization in Whole-Body Medical Images

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

The goal of this work is to accurately and reliably localize anatomical landmarks in 3D Computed Tomography (CT) scans of the upper bodies of cancer patients even in the presence of pathologies and imaging artifacts that may markedly change the appearances of anatomical structures. We propose a method based on dense matching of parts-based graphical models. For landmark localization, we replace population averaged models by personalized models that are adapted to each test image at runtime. We do so by jointly leveraging weighted combinations of labeled training exemplars. We report results for localizing standard anatomical landmarks in clinical 3D CT volumes, using a database of 83 lung cancer patients. We compare our method against both (baseline) population averaged graphical models and against atlas-based deformable registration and show the method is in each case able to localize landmarks with significantly improved reliability and accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. Population mean and personalized spatial priors have the same meaning as the maximum spatial prior distribution defined in Sect. 2.5. We use the shorter names for clarity.

  2. This is achieved in the algorithm by a linear interpolation of the intensity values in both the reference and the test volume between \(-\)750 HU and 1750 HU.

References

  • Beichel, R., Bischof, H., Leberl, F., & Sonka, M. (2005). Robust active appearance models and their application to medical image analysis. IEEE TMI, 24(9), 1151–1169.

    Google Scholar 

  • Besbes, A., & Paragios, N. (2011). In Landmark-based segmentation of lungs while handling partial correspondences using sparse graph-based priors. 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro (pp. 989–995). IEEE.

  • Besbes, A., Komodakis, N., Langs, G., & Paragios, N. (2009). Shape priors and discrete mrfs for knowledge-based segmentation. 2009 IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2009 (pp. 1295–1302). IEEE.

  • Buehler, P., Everingham, M., Huttenlocher, D., & Zisserman, A. (2008). Long term arm and hand tracking for continuous sign language TV broadcasts. In Proceedings of the British Machine Vision Conference.

  • Chum, O., Philbin, J., Sivic, J., Isard, M., & Zisserman, A. (2007). Total recall: Automatic query expansion with a generative feature model for object retrieval. In Proceedings of the International Conference on Computer Vision.

  • Cootes, T., Hill, A., Taylor, C., & Haslam, J. (1994). Use of active shape models for locating structures in medical images. Image and Vision Computing, 12(6), 355–365.

    Article  Google Scholar 

  • Cootes, T. F., Edwards, G. J., & Taylor, C. J. (2001). Active appearance models. IEEE TPAMI, 23(6), 681–685.

    Article  Google Scholar 

  • Corso, J., Alomari, R., & Chaudhary, V. (2008). Lumbar disc localization and labeling with a probabilistic model on both pixel and object features. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention.

  • Crandall, D., & Huttenlocher, D. (2006). Weakly supervised learning of part-based spatial models for visual object recognition. In Proceedings of the European Conference on Computer Vision (pp. 16–29).

  • Crandall, D., Felzenszwalb, P., & Huttenlocher, D. (2005). Spatial priors for part-based recognition using statistical models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

  • Criminisi, A., Shotton, J., & Bucciarelli, S. (2009). Decision forests with long-range spatial context for organ localization in CT volumes. In MICCAI Workshop on Probabilistic Models for Medical Image Analysis.

  • Criminisi, A., Shotton, J., Robertson, D., & Konukoglu, E. (2011). Regression forests for efficient anatomy detection and localization in CT studies. In Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging (pp 106–117). Berlin Heidelberg: Springer.

  • Donner, R., Langs, G., & Bischof, H. (2007). Sparse MRF appearance models for fast anatomical structure localisation. In Proceedings of the British Machine Vision Conference.

  • Eichner, M., Ferrari, V., & Zurich, S. (2009). Better appearance models for pictorial structures. In Proceedings of the British Machine Vision Conference.

  • Felzenszwalb, P., McAllester, D., & Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

  • Felzenszwalb, P. F., & Huttenlocher, D. P. (2005). Pictorial structures for object recognition. International Journal of Computer Vision, 61(1), 55–79.

    Article  Google Scholar 

  • Fergus, R., Perona, P., & Zisserman, A. (2007). Weakly supervised scale-invariant learning of models for visual recognition. International Journal of Computer Vision, 71(3), 273–303.

    Article  Google Scholar 

  • Fischler, M., & Elschlager, R. (1973). The representation and matching of pictorial structures. IEEE Transaction on Computers, 100(22), 67–92.

    Article  Google Scholar 

  • Lan, X., & Huttenlocher, D. (2005). Beyond trees: Common-factor models for 2d human pose recovery. In Proceedings of the International Conference on Computer Vision.

  • Langerak, T. R., van der Heide, U. A., Kotte, A. N., Viergever, M. A., van Vulpen, M., & Pluim, J. P. (2010). Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation (simple). IEEE Transactions on Medical Imaging, 29(12), 2000–2008.

    Article  Google Scholar 

  • Langs, G., Donner, R., Peloschek, P., & Bischof, H. (2007). Robust autonomous model learning from 2d and 3d data sets. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention (pp 968–976).

  • Ou, Y., Besbes, A., Bilello, M., Mansour, M., Davatzikos, C., & Paragios, N. (2010). Detecting mutually-salient landmark pairs with mrf regularization. 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro (pp. 400–403). IEEE.

  • Potesil, V., Kadir, T., Platsch, G., & Brady, M. (2010). Improved anatomical landmark localization in medical images using dense matching of graphical models. In Proceedings of the British Machine Vision Conference.

  • Ramanan, D. (2007). Learning to parse images of articulated bodies. In Proceedings of the Neural Information Processing Systems.

  • Roche, A., Malandain, G., Pennec, X., & Ayache, N. (1998). The correlation ratio as a new similarity measure for multimodal image registration. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention (pp. 1115–1124).

  • Sabuncu, M. R., Yeo, B. T., Van Leemput, K., Fischl, B., & Golland, P. (2010). A generative model for image segmentation based on label fusion. IEEE Transactions on Medical Imaging, 29(10), 1714–1729.

    Article  Google Scholar 

  • Sapp, B., Jordan, C., & Taskar, B. (2010). Adaptive pose priors for pictorial structures. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 422–429).

  • Schmidt, S., Kappes, J., Bergtholdt, M., et al. (2007). Spine detection and labeling using a parts-based graphical model. In Proceedings of the Information Processing in Medical Imaging.

  • Sigal, L., & Black, M. (2006). Measure locally, reason globally: Occlusion-sensitive articulated pose estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

  • Toews, M., & Arbel, T. (2007). A statistical parts-based model of anatomical variability. IEEE TMI, 26(4), 497–508.

  • Wang, C., Teboul, O., Michel, F., Essafi, S., & Paragios, N. (2010). 3d knowledge-based segmentation using pose-invariant higher-order graphs. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention (pp. 189–196). Springer.

  • Warfield, S. K., Zou, K. H., & Wells, W. M. (2004). Simultaneous truth and performance level estimation (staple): An algorithm for the validation of image segmentation. IEEE Transactions on Medical Imaging, 23(7), 903–921.

    Article  Google Scholar 

  • Wörz, S., & Rohr, K. (2006). Localization of anatomical point landmarks in 3D medical images by fitting 3D parametric intensity models. Medical Image Analysis, 10(1), 41–58.

  • Wright, T. (2008). Trued deformable registration. Siemens Medical Solutions white paper.

  • Xiang, B., Wang, C., Deux, J.F., Rahmouni, A., & Paragios, N. (2012). 3d cardiac segmentation with pose-invariant higher-order mrfs. 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI) (pp. 1425–1428), IEEE.

  • Zhang, P., & Cootes, T. (2011). Automatic part selection for groupwise registration. In Proceedings of the Information Processing in Medical Imaging (pp. 636–647). Springer.

  • Zhang, P., & Cootes, T. (2012). Automatic construction of parts+ geometry models for initialising groupwise registration. IEEE Transactions on Medical Imaging, 99, 1–1.

    MATH  Google Scholar 

  • Zhang, P., Adeshina, S., & Cootes, T. (2010). Automatic learning sparse correspondences for initialising groupwise registration. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention.

Download references

Acknowledgments

We are grateful to Dr. Jean-Marc Peyrat (Siemens) for refining the manuscript, Prof. Daniel Slosman (Clinique Générale-Beaulieu, Geneva, Switzerland) and Dr. Jérôme Declerck (Siemens) for image database, and to Mr. Tomas Potesil for help with data annotation.

Author information

Authors and Affiliations

  1. Department of Engineering Science, University of Oxford, Oxford, UK

    Vaclav Potesil

  2. Mirada Medical Ltd, Oxford, UK

    Timor Kadir

  3. Siemens Molecular Imaging Ltd, Oxford, UK

    Günther Platsch

  4. Department of Oncology, University of Oxford, Oxford, UK

    Michael Brady

Authors
  1. Vaclav Potesil
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Timor Kadir
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Günther Platsch
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Michael Brady
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Vaclav Potesil.

Additional information

Communicated by K. Ikeuchi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Potesil, V., Kadir, T., Platsch, G. et al. Personalized Graphical Models for Anatomical Landmark Localization in Whole-Body Medical Images. Int J Comput Vis 111, 29–49 (2015). https://doi.org/10.1007/s11263-014-0731-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-014-0731-7

Keywords

Search

Navigation