June 2015
Volume 56, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2015
Automatic segmentation and classification of intraretinal cystoid fluid and subretinal fluid in 3D-OCT using convolutional neural networks
Author Affiliations & Notes
  • Thomas Schlegl
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria
  • Ana-Maria Glodan
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Vienna Reading Center, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Dominika Podkowinski
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Vienna Reading Center, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Sebastian M Waldstein
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Vienna Reading Center, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Bianca S. Gerendas
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Vienna Reading Center, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Ursula Schmidt-Erfurth
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Vienna Reading Center, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria
  • Georg Langs
    Christian Doppler Laboratory for Ophthalmic Image Analysis, Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria
  • Footnotes
    Commercial Relationships Thomas Schlegl, None; Ana-Maria Glodan, None; Dominika Podkowinski, None; Sebastian Waldstein, None; Bianca Gerendas, None; Ursula Schmidt-Erfurth, Alcon (C), Bayer (C), Boehringer Ingelheim (C), Novartis (C); Georg Langs, None
  • Footnotes
    Support None
Investigative Ophthalmology & Visual Science June 2015, Vol.56, 5920. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Thomas Schlegl, Ana-Maria Glodan, Dominika Podkowinski, Sebastian M Waldstein, Bianca S. Gerendas, Ursula Schmidt-Erfurth, Georg Langs, ; Automatic segmentation and classification of intraretinal cystoid fluid and subretinal fluid in 3D-OCT using convolutional neural networks. Invest. Ophthalmol. Vis. Sci. 2015;56(7 ):5920.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Purpose
 

The key driver for vision loss in macular diseases such as neovascular age-related macular degeneration is the accumulation of macular edema. Out of the two components of macular edema, intraretinal cystoid fluid (IRC) leads to severe vision loss. Conversely, recent evidence suggests that subretinal fluid (SRF) may be associated with better visual acuity outcomes. The precise classification and quantification of IRC and SRF are therefore of paramount importance for disease management. We propose a fully automated segmentation and classification method for IRC and SRF in spectral-domain optical coherence tomography (SD-OCT) images.

 
Methods
 

We use convolutional neural networks (CNN) to capture characteristic visual appearance patterns and classify normal retinal tissue, IRC and SRF. The CNN is trained in a supervised manner using approximately 300,000 2D image patches extracted from 157 OCT image volumes available at the Vienna Reading Center. All image patches are sampled at random positions. 73% of the patches show healthy tissue, 8% show IRC and 18% show SRF. Besides the visual appearance of the image patches we provide the CNN with the Euclidean distances of the patch centers to the fovea and the 3D coordinates of the patch centers. We evaluate the automatic segmentation performing four-fold cross-validation. Based on the image patches of the training set the CNN learns representative and discriminative features appropriate for pixel-wise image classification. The pixel-wise classification results in a segmentation of the whole OCT volume into normal retinal tissue, IRC and SRF.

 
Results
 

The amount of spatial overlap between predicted class labels and the corresponding ground truth annotations is computed as performance measure. The classifier achieves an overall accuracy over all three classes of 96%. The pixel-based class-wise accuracies of normal retinal tissue, IRC and SRF are 98%, 90% and 92%, respectively.

 
Conclusions
 

Our CNN classifier automatically and highly accurately segments and discriminates between normal retinal tissue, IRC and SRF in retinal SD-OCT. This may enable precise structure-function correlations, and the prediction of visual function based on SD-OCT on the large scale.  

 
Figure 1: Intensity image (a), ground truth (b) and segmentation result (c) of a case showing SRF (top) and IRC (bottom).
 
Figure 1: Intensity image (a), ground truth (b) and segmentation result (c) of a case showing SRF (top) and IRC (bottom).

 
×
×

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.

×