Probabilistic Point Cloud Reconstructions for Vertebral Shape Analysis

  • Anjany SekuboyinaEmail author
  • Markus Rempfler
  • Alexander Valentinitsch
  • Maximilian Loeffler
  • Jan S. Kirschke
  • Bjoern H. Menze
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)


We propose an auto-encoding network architecture for point clouds (PC) capable of extracting shape signatures without supervision. Building on this, we (i) design a loss function capable of modelling data variance on PCs which are unstructured, and (ii) regularise the latent space as in a variational auto-encoder, both of which increase the auto-encoders’ descriptive capacity while making them probabilistic. Evaluating the reconstruction quality of our architectures, we employ them for detecting vertebral fractures without any supervision. By learning to efficiently reconstruct only healthy vertebrae, fractures are detected as anomalous reconstructions. Evaluating on a dataset containing \(\sim \)1500 vertebrae, we achieve area-under-ROC curve of >75%, without using intensity-based features.



This work is supported by the European Research Council (ERC) under the European Union’s ‘Horizon 2020’ research & innovation programme (GA637164–iBack–ERC–2014–STG). The Quadro P5000 used for this work was donated by NVIDIA Corporation.

Supplementary material

490281_1_En_42_MOESM1_ESM.pdf (2.9 mb)
Supplementary material 1 (pdf 2932 KB)


  1. 1.
    Ingalhalikar, M., et al.: Sex differences in the structural connectome of the human brain. Proc. Natl. Acad. Sci. 111(2), 823–828 (2014)CrossRefGoogle Scholar
  2. 2.
    Shakeri, M., Lombaert, H., Tripathi, S., Kadoury, S.: Deep spectral-based shape features for Alzheimer’s disease classification. In: Reuter, M., Wachinger, C., Lombaert, H. (eds.) SeSAMI 2016. LNCS, vol. 10126, pp. 15–24. Springer, Cham (2016). Scholar
  3. 3.
    Isensee, F., et al.: Brain tumor segmentation and radiomics survival prediction: contribution to the brats 2017 challenge. arXiv e-prints (2018)Google Scholar
  4. 4.
    Bronstein, M.M., et al.: Geometric deep learning: going beyond euclidean data. IEEE Sig. Process. Mag. 34(4), 18–42 (2017)CrossRefGoogle Scholar
  5. 5.
    Qi, C.R., et al.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)Google Scholar
  6. 6.
    Gutiérrez-Becker, B., Wachinger, C.: Deep multi-structural shape analysis: application to neuroanatomy. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 523–531. Springer, Cham (2018). Scholar
  7. 7.
    Fan, H., et al.: A point set generation network for 3D object reconstruction from a single image. In: CVPR (2017)Google Scholar
  8. 8.
    Yang, Y., et al.: FoldingNet: point cloud auto-encoder via deep grid deformation. In: CVPR (2018)Google Scholar
  9. 9.
    Baum, T., et al.: Automatic detection of osteoporotic vertebral fractures in routine thoracic and abdominal MDCT. Eur. Radiol. 24(4), 872–880 (2014)CrossRefGoogle Scholar
  10. 10.
    Tomita, N., et al.: Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Comput. Biol. Med. 98, 8–15 (2018)CrossRefGoogle Scholar
  11. 11.
    Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: NIPS (2017)Google Scholar
  12. 12.
    An, J., Cho, S.: Variational autoencoder based anomaly detection using reconstruction probability. Technical report, SNU Data Mining Center (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Anjany Sekuboyina
    • 1
    • 2
    Email author
  • Markus Rempfler
    • 3
  • Alexander Valentinitsch
    • 2
  • Maximilian Loeffler
    • 2
  • Jan S. Kirschke
    • 2
  • Bjoern H. Menze
    • 1
  1. 1.Department of InformaticsTechnical University of MunichMunichGermany
  2. 2.Department of NeuroradiologyKlinikum rechts der IsarMunichGermany
  3. 3.Friedrich Miescher Institute for Biomedical ResearchBaselSwitzerland

Personalised recommendations