Learning to Segment 3D Linear Structures Using Only 2D Annotations

  • Mateusz KozińskiEmail author
  • Agata Mosinska
  • Mathieu Salzmann
  • Pascal Fua
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)


We propose a loss function for training a Deep Neural Network (DNN) to segment volumetric data, that accommodates ground truth annotations of 2D projections of the training volumes, instead of annotations of the 3D volumes themselves. In consequence, we significantly decrease the amount of annotations needed for a given training set. We apply the proposed loss to train DNNs for segmentation of vascular and neural networks in microscopy images and demonstrate only a marginal accuracy loss associated to the significant reduction of the annotation effort. The lower labor cost of deploying DNNs, brought in by our method, can contribute to a wide adoption of these techniques for analysis of 3D images of linear structures.


  1. 1.
    Kutulakos, K., Seitz, S.: A theory of shape by space carving. IJCV 38(3), 197–216 (2000)CrossRefGoogle Scholar
  2. 2.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A., Delp, S. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998). Scholar
  3. 3.
    Law, M.W.K., Chung, A.C.S.: Three dimensional curvilinear structure detection using optimally oriented flux. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 368–382. Springer, Heidelberg (2008). Scholar
  4. 4.
    Turetken, E., Becker, C., Glowacki, P., Benmansour, F., Fua, P.: Detecting irregular curvilinear structures in gray scale and color imagery using multi-directional oriented Flux. In: ICCV, December 2013Google Scholar
  5. 5.
    Becker, C., Rigamonti, R., Lepetit, V., Fua, P.: Supervised feature learning for curvilinear structure segmentation. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8149, pp. 526–533. Springer, Heidelberg (2013). Scholar
  6. 6.
    Breitenreicher, D., Sofka, M., Britzen, S., Zhou, S.K.: Hierarchical discriminative framework for detecting tubular structures in 3D images. In: Gee, J.C., Joshi, S., Pohl, K.M., Wells, W.M., Zöllei, L. (eds.) IPMI 2013. LNCS, vol. 7917, pp. 328–339. Springer, Heidelberg (2013). Scholar
  7. 7.
    Sironi, A., Turetken, E., Lepetit, V., Fua, P.: Multiscale centerline detection. PAMI 38(7), 1327–1341 (2016)CrossRefGoogle Scholar
  8. 8.
    Peng, H., Zhou, Z., Meijering, E., et al.: Automatic tracing of ultra-volumes of neuronal images. Nat. Methods 14, 332–333 (2017)CrossRefGoogle Scholar
  9. 9.
    Peng, H., Tang, J., Xiao, H.: Virtual finger boosts three-dimensional imaging and microsurgery as well as terabyte volume image visualization and analysis. Nat. Commun. 5, 4342 (2014)CrossRefGoogle Scholar
  10. 10.
    Vitanovski, D., Schaller, C., Hahn, D., Daum, V., Hornegger, J.: 3D annotation and manipulation of medical anatomical structures. In: Proceedings of SPIE on Medical Imaging, vol. 7261 (2009)Google Scholar
  11. 11.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). Scholar
  12. 12.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  13. 13.
    Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv Preprint (2014)Google Scholar
  14. 14.
    Bullitt, E., Zeng, D., Gerig, G.: Vessel tortuosity and brain tumor malignancy: a blinded study. Acad. Radiol. 12(10), 1232–1240 (2005)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Mateusz Koziński
    • 1
    Email author
  • Agata Mosinska
    • 1
  • Mathieu Salzmann
    • 1
  • Pascal Fua
    • 1
  1. 1.Computer Vision LaboratoryÉcole Polytechnique Fédérale de LausanneLausanneSwitzerland

Personalised recommendations