Investigative Ophthalmology & Visual Science Cover Image for Volume 59, Issue 9
July 2018
Volume 59, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2018
Unsupervised deep learning to identify markers in optical coherence tomography
Author Affiliations & Notes
  • Sebastian M Waldstein
    Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Philipp Seeboeck
    Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Rene Donner
    Department of Biomedical Imaging, Medical University of Vienna, Vienna, Austria
  • Amir Sadeghipour
    Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Georg Langs
    Department of Biomedical Imaging, Medical University of Vienna, Vienna, Austria
  • Bianca S Gerendas
    Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Aaron Osborne
    Genentech, Inc., South San Francisco, California, United States
  • Ursula Schmidt-Erfurth
    Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Footnotes
    Commercial Relationships   Sebastian Waldstein, Bayer (F), Bayer (C), Genentech (F), Novartis (C); Philipp Seeboeck, None; Rene Donner, None; Amir Sadeghipour, None; Georg Langs, None; Bianca S Gerendas, Roche (C); Aaron Osborne, Genentech (E); Ursula Schmidt-Erfurth, Bayer (C), Boehringer (C), Carl Zeiss Meditec (C), Novartis (C)
  • Footnotes
    Support  Christian Doppler Research Society, Genentech
Investigative Ophthalmology & Visual Science July 2018, Vol.59, 1736. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Sebastian M Waldstein, Philipp Seeboeck, Rene Donner, Amir Sadeghipour, Georg Langs, Bianca S Gerendas, Aaron Osborne, Ursula Schmidt-Erfurth; Unsupervised deep learning to identify markers in optical coherence tomography. Invest. Ophthalmol. Vis. Sci. 2018;59(9):1736.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Robust and sensitive imaging biomarkers remain an unmet need in the management of macular disease. Classical OCT biomarkers e.g. fluid are defined based on human intuition and experience. However, these conventional markers may not represent a comprehensive vocabulary to capture all important information in OCT images. Furthermore, they are inherently limited by pre-made hypotheses.

Methods : To complement the vocabulary of OCT biomarkers, we propose large-scale unsupervised deep learning to identify features inherent in OCT data in a completely unbiased fashion. We use auto-encoder methodology to automatically identify and categorize relevant features without human prior knowledge. This approach is first applied on the (local) A-scan level to capture fine-grained features in the image. Consecutively, we apply the auto-encoder method on (global) volume and patient timeline levels to encode simplified descriptions of entire OCT volumes and the behavior of patients over time. Our method is trained on clinical trial data of 1,097 patients with neovascular age-related macular degeneration under standardized anti-VEGF therapy. We evaluate the resulting biomarkers by correlating them with measures of visual function (BCVA and LLVA).

Results : The deep learning system identified 20 distinct (local) A-scan features that correlated with BCVA (R2=0.17) and LLVA (R2=0.29, individual correlation coefficient up to r=-0.39). Some markers corresponded to known findings such as retinal fluid or subretinal hyperreflective material, while other markers did not reveal an obvious link to known morphologic features. Two non-fluid related markers even had a positive correlation with BCVA and LLVA. On the global level, unsupervised learning resulted in a compact 20-dimensional description of the OCT volume. Correlation with visual function was superior to the A-scan level (R2=0.26 (BCVA) and 0.37 (LLVA)). On the timeline level, the method revealed clear differences between patients receiving different treatment regimens (monthly vs. PRN).

Conclusions : Unsupervised deep learning enabled an unbiased representation of clinically important markers in OCT imaging that correlated well with visual acuity. Furthermore, it successfully achieved a compact summary of volumetric OCT data on a volume level and also over time. The presented methodology offers advances in analyzing big data in retinal disease.

This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×