Advertisement

Modeling Disease Progression in Retinal OCTs with Longitudinal Self-supervised Learning

  • Antoine RivailEmail author
  • Ursula Schmidt-Erfurth
  • Wolf-Dieter Vogl
  • Sebastian M. Waldstein
  • Sophie Riedl
  • Christoph Grechenig
  • Zhichao Wu
  • Hrvoje Bogunovic
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11843)

Abstract

Longitudinal imaging is capable of capturing the static anatomical structures and the dynamic changes of the morphology resulting from aging or disease progression. Self-supervised learning allows to learn new representation from available large unlabelled data without any expert knowledge. We propose a deep learning self-supervised approach to model disease progression from longitudinal retinal optical coherence tomography (OCT). Our self-supervised model takes benefit from a generic time-related task, by learning to estimate the time interval between pairs of scans acquired from the same patient. This task is (i) easy to implement, (ii) allows to use irregularly sampled data, (iii) is tolerant to poor registration, and (iv) does not rely on additional annotations. This novel method learns a representation that focuses on progression specific information only, which can be transferred to other types of longitudinal problems. We transfer the learnt representation to a clinically highly relevant task of predicting the onset of an advanced stage of age-related macular degeneration within a given time interval based on a single OCT scan. The boost in prediction accuracy, in comparison to a network learned from scratch or transferred from traditional tasks, demonstrates that our pretrained self-supervised representation learns a clinically meaningful information.

References

  1. 1.
    Fujimoto, J., Swanson, E.: The development, commercialization, and impact of optical coherence tomography. Invest. Ophthalmol. Vis. Sci. 57(9), OCT1–OCT13 (2016)CrossRefGoogle Scholar
  2. 2.
    Vogl, W.D., Waldstein, S.M., Gerendas, B.S., Schlegl, T., Langs, G., Schmidt-Erfurth, U.: Analyzing and predicting visual acuity outcomes of anti-VEGF therapy by a longitudinal mixed effects model of imaging and clinical data. Invest. Ophthalmol. Vis. Sci. 58(10), 4173 (2017)CrossRefGoogle Scholar
  3. 3.
    Vogl, W.D., Waldstein, S.M., Gerendas, B.S., Schmidt-Erfurth, U., Langs, G.: Predicting macular edema recurrence from spatio-temporal signatures in optical coherence tomography images. IEEE Trans. Med. Imaging 36(9), 1773–1783 (2017)CrossRefGoogle Scholar
  4. 4.
    Schmidt-Erfurth, U., et al.: Prediction of individual disease conversion in early AMD using artificial intelligence. Invest. Ophthalmol. Vis. Sci. 59(8), 3199–3208 (2018)CrossRefGoogle Scholar
  5. 5.
    Sabuncu, M.R., Bernal-Rusiel, J.L., Reuter, M., Greve, D.N., Fischl, B., Alzheimer’s Disease Neuroimaging Initiative: Event time analysis of longitudinal neuroimage data. NeuroImage 97, 9–18 (2014)Google Scholar
  6. 6.
    Lorenzi, M., Ziegler, G., Alexander, D.C., Ourselin, S.: Efficient Gaussian process-based modelling and prediction of image time series. In: Ourselin, S., Alexander, D.C., Westin, C.-F., Cardoso, M.J. (eds.) IPMI 2015. LNCS, vol. 9123, pp. 626–637. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-19992-4_49CrossRefGoogle Scholar
  7. 7.
    Lee, H., Huang, J., Singh, M., Yang, M.: Unsupervised representation learning by sorting sequences. CoRR abs/1708.01246 (2017)Google Scholar
  8. 8.
    Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., Shah, R.: Signature verification using a “siamese” time delay neural network. In: Advances in NIPS, pp. 737–744 (1994)Google Scholar
  9. 9.
    Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)
  10. 10.
    Chen, X., Niemeijer, M., Zhang, L., Lee, K., Abramoff, M.D., Sonka, M.: Three-dimensional segmentation of fluid-associated abnormalities in retinal OCT: probability constrained graph-search-graph-cut. IEEE Trans. Med. Imaging 31(8), 1521–1531 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Antoine Rivail
    • 1
    Email author
  • Ursula Schmidt-Erfurth
    • 1
  • Wolf-Dieter Vogl
    • 1
  • Sebastian M. Waldstein
    • 1
  • Sophie Riedl
    • 1
  • Christoph Grechenig
    • 1
  • Zhichao Wu
    • 2
  • Hrvoje Bogunovic
    • 1
  1. 1.Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and OptometryMedical University of ViennaViennaAustria
  2. 2.University of MelbourneMelbourneAustralia

Personalised recommendations