Advertisement

Training CNNs for Image Registration from Few Samples with Model-based Data Augmentation

  • Hristina Uzunova
  • Matthias Wilms
  • Heinz Handels
  • Jan Ehrhardt
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10433)

Abstract

Convolutional neural networks (CNNs) have been successfully used for fast and accurate estimation of dense correspondences between images in computer vision applications. However, much of their success is based on the availability of large training datasets with dense ground truth correspondences, which are only rarely available in medical applications. In this paper, we, therefore, address the problem of CNNs learning from few training data for medical image registration. Our contributions are threefold: (1) We present a novel approach for learning highly expressive appearance models from few training samples, (2) we show that this approach can be used to synthesize huge amounts of realistic ground truth training data for CNN-based medical image registration, and (3) we adapt the FlowNet architecture for CNN-based optical flow estimation to the medical image registration problem. This pipeline is applied to two medical data sets with less than 40 training images. We show that CNNs learned from the proposed generative model outperform those trained on random deformations or displacement fields estimated via classical image registration.

References

  1. 1.
    Andreopoulos, A., Tsotsos, J.K.: Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI. Med. Image Anal. 12(3), 335–357 (2008)CrossRefGoogle Scholar
  2. 2.
    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). doi: 10.1007/978-3-319-46723-8_49 CrossRefGoogle Scholar
  3. 3.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998). doi: 10.1007/BFb0054760 CrossRefGoogle Scholar
  4. 4.
    Dosovitskiy, A., Fischer, P., Ilg, E., et al.: Flownet: Learning optical flow with convolutional networks. CVPR 2015, 2758–2766 (2015)Google Scholar
  5. 5.
    Ehrhardt, J., Schmidt-Richberg, A., Werner, R., Handels, H.: Variational registration. In: Handels, H., Deserno, T.M., Meinzer, H.-P., Tolxdorff, T. (eds.) Bildverarbeitung für die Medizin 2015. I, pp. 209–214. Springer, Heidelberg (2015). doi: 10.1007/978-3-662-46224-9_37 Google Scholar
  6. 6.
    Hauberg, S., Freifeld, O., Larsen, A.B.L., et al.: Dreaming more data: Class-dependent distributions over diffeomorphisms for learned data augmentation. AISTATS 2016, 342–350 (2016)Google Scholar
  7. 7.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. NIPS 2012, 1097–1105 (2012)Google Scholar
  8. 8.
    Lee, S., Wolberg, G., Shin, S.Y.: Scattered data interpolation with multilevel b-splines. IEEE Trans. Vis. Comput. Graph 3(3), 228–244 (1997)CrossRefGoogle Scholar
  9. 9.
    Matthews, I., Baker, S.: Active appearance models revisited. IJCV 60(2), 135–164 (2004)CrossRefGoogle Scholar
  10. 10.
    Miller, E.G., Matsakis, N.E., Viola, P.A.: Learning from one example through shared densities on transforms. CVPR 2000, 464–471 (2000)Google Scholar
  11. 11.
    Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Epicflow: Edge-preserving interpolation of correspondences for optical flow. CVPR 2015, 1164–1172 (2015)Google 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). doi: 10.1007/978-3-319-24574-4_28 CrossRefGoogle Scholar
  13. 13.
    Shattuck, D.W., Mirza, M., Adisetiyo, V., et al.: Construction of a 3D probabilistic atlas of human cortical structures. Neuroimage 39(3), 1064–1080 (2008)CrossRefGoogle Scholar
  14. 14.
    Simonovsky, M., Gutiérrez-Becker, B., Mateus, D., Navab, N., Komodakis, N.: A deep metric for multimodal registration. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 10–18. Springer, Cham (2016). doi: 10.1007/978-3-319-46726-9_2 CrossRefGoogle Scholar
  15. 15.
    Sotiras, A., Davatzikos, C., Paragios, N.: Deformable medical image registration: A survey. IEEE Trans. Med. Imag. 32(7), 1153–1190 (2013)CrossRefGoogle Scholar
  16. 16.
    Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: Deepflow: Large displacement optical flow with deep matching. CVPR 2013, 1385–1392 (2013)Google Scholar
  17. 17.
    Wilms, M., Handels, H., Ehrhardt, J.: Multi-resolution multi-object statistical shape models based on the locality assumption. Med. Image Anal. 38, 17–29 (2017)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Hristina Uzunova
    • 1
  • Matthias Wilms
    • 1
  • Heinz Handels
    • 1
  • Jan Ehrhardt
    • 1
  1. 1.Institute of Medical InformaticsUniversity of LübeckLübeckGermany

Personalised recommendations