June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Deep Learning Glaucoma Classification in enface OCTA scans of the human macular region
Author Affiliations & Notes
  • Julia Schottenhamml
    Pattern Recognition Lab, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Bayern, Germany
  • Stefan B Ploner
    Pattern Recognition Lab, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Bayern, Germany
  • Lennart Husvogt
    Pattern Recognition Lab, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Bayern, Germany
    Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States
  • Sophia Mardin
    Department of Information Systems and Services, Otto-Friedrich-Universitat Bamberg, Bamberg, Bayern, Germany
  • Bettina Hohberger
    Department of Ophthalmology, University Erlangen-Nürnberg, Erlangen, Germany
  • Christian Y Mardin
    Department of Ophthalmology, University Erlangen-Nürnberg, Erlangen, Germany
  • Andreas K Maier
    Pattern Recognition Lab, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Bayern, Germany
  • Footnotes
    Commercial Relationships   Julia Schottenhamml, None; Stefan Ploner, IP in VISTA-OCTA (P); Lennart Husvogt, None; Sophia Mardin, None; Bettina Hohberger, None; Christian Mardin, None; Andreas Maier, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 1004. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Julia Schottenhamml, Stefan B Ploner, Lennart Husvogt, Sophia Mardin, Bettina Hohberger, Christian Y Mardin, Andreas K Maier; Deep Learning Glaucoma Classification in enface OCTA scans of the human macular region. Invest. Ophthalmol. Vis. Sci. 2021;62(8):1004.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Glaucoma is one of the leading causes of irreversible vision loss. Several studies have shown a link between vascular damage and glaucoma on optical coherence tomography angiography (OCTA) images. These studies were mostly conducted in the region of the optic nerve head (ONH) or on larger 6x6 mm macula scans. Moreover, all these studies use handcrafted features for the glaucoma classification. We therefore propose a fully automatic classification algorithm on 3x3 mm macula scans based on convolutional neural networks (CNN) that are able to learn features from the images themselves.

Methods : Whole retina projection OCTA images (Spectralis OCT II, Heidelberg Engineering, Heidelberg) of 75 eyes of 75 healthy persons (h) and 184 eyes of 125 glaucoma patients (g) were retrospectively identified from the Erlangen glaucoma registry. They were divided into training set (h: 45 eyes/45 patients, g: 110 eyes/76 patients), validation set (h: 15 eyes/15 patients, g: 37 eyes/24 patients) and test set (h: 15 eyes/15 patients, g: 37 eyes/25 patients). Eyes of one person only belong to a single set. Different CNNs were trained and the one performing best (according to the AUROC) on the validation set was chosen for evaluation. For comparison, handcrafted features that were compatible with the available data (only a single enface OCTA image available) were selected. We chose the commonly used vessel density (VD) and a combination of global and local features proposed by Ong et al. (Ong). We then trained a support vector machine (SVM) on each of these traditional feature sets and again chose the best performing one on the validation set.

Results : The ROC curves, AUROC values and confusion matrices can be found in Figure 1 and the accuracies in Figure 2 for the different methods on the test set.

Conclusions : We were able to outperform other handcrafted features on 3x3 mm macula scans and achieved results on par with other algorithms proposed for different ocular regions. These other studies often have shown that their features work better on projections of a single vascular plexus than on a whole retina projection. Therefore, the next step would be to apply the deep learning pipeline presented in this paper to the different retinal plexuses separately.

This is a 2021 ARVO Annual Meeting abstract.

 

ROC curves, AUROC values and confusion matrices for the different methods.

ROC curves, AUROC values and confusion matrices for the different methods.

 

Accuracies for the different methods for the whole dataset and each class separately.

Accuracies for the different methods for the whole dataset and each class separately.

×
×

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.

×