June 2017
Volume 58, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2017
Fully automated detection of hyperreflective foci in optical coherence tomography
Author Affiliations & Notes
  • Freerk G Venhuizen
    Diagnostic Image Analysis Group, Radboudumc, Nijmegen, Netherlands
    Department of ophthalmology, Radboudumc, Nijmegen, Netherlands
  • Samuel Schaffhauser
    Diagnostic Image Analysis Group, Radboudumc, Nijmegen, Netherlands
    Department of statistics, ETH Zürich, Zürich, Switzerland
  • Vivian Schreur
    Department of ophthalmology, Radboudumc, Nijmegen, Netherlands
  • Lebriz Altay
    Department of ophthalmology, Uniklinik Köln, Cologne, Germany
  • Bart Liefers
    Diagnostic Image Analysis Group, Radboudumc, Nijmegen, Netherlands
    Department of ophthalmology, Radboudumc, Nijmegen, Netherlands
  • Bram van Ginneken
    Diagnostic Image Analysis Group, Radboudumc, Nijmegen, Netherlands
  • Carel C B Hoyng
    Department of ophthalmology, Radboudumc, Nijmegen, Netherlands
  • Thomas Theelen
    Department of ophthalmology, Radboudumc, Nijmegen, Netherlands
    Diagnostic Image Analysis Group, Radboudumc, Nijmegen, Netherlands
  • Eiko de Jong
    Department of ophthalmology, Radboudumc, Nijmegen, Netherlands
  • Clara I Sanchez
    Diagnostic Image Analysis Group, Radboudumc, Nijmegen, Netherlands
    Department of ophthalmology, Radboudumc, Nijmegen, Netherlands
  • Footnotes
    Commercial Relationships   Freerk Venhuizen, None; Samuel Schaffhauser, None; Vivian Schreur, None; Lebriz Altay, None; Bart Liefers, None; Bram van Ginneken, None; Carel Hoyng, None; Thomas Theelen, None; Eiko de Jong, None; Clara Sanchez, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2017, Vol.58, 671. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Freerk G Venhuizen, Samuel Schaffhauser, Vivian Schreur, Lebriz Altay, Bart Liefers, Bram van Ginneken, Carel C B Hoyng, Thomas Theelen, Eiko de Jong, Clara I Sanchez; Fully automated detection of hyperreflective foci in optical coherence tomography. Invest. Ophthalmol. Vis. Sci. 2017;58(8):671.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Diabetic macular edema (DME) is a retinal disorder characterized by a buildup of cystoidal fluid in the retina. The typical treatment consists of monthly intravitreal anti vascular endothelial growth factor (anti-VEGF) injections. However, the efficacy of this treatment varies strongly. Recent studies have indicated that the presence and number of hyperreflective foci can possibly be considered a prognostic biomarker for treatment response in DME. As the detection of foci is difficult and time-consuming manual foci quantification seems infeasible. We therefore developed a fully automated system capable of detecting and quantifying foci in optical coherence tomography (OCT) images.

Methods : 119 fovea centered B-scans obtained from 49 patients with DME were selected from a clinical database. The data was divided in a training set of 96 B-scans from 40 patients, and a test set containing 23 B-scans from 9 patients. A convolutional neural network (CNN) was developed to predict if an image pixel belongs to a hyperreflective focus by considering a small neighborhood around the pixel of interest. The CNN consists of 7 convolutional layers and 2 max pooling layers. After providing the system with enough training samples, the network automatically detects pixels with a high probability of being part of a hyperreflective focus. Connected detections are considered as a single detection. The obtained results were compared to manual annotations made by two experienced human graders in consensus for the central 3 mm surrounding the fovea. Hyperreflective foci were only annotated in the layers ranging from the inner plexiform layer (IPL) to the outer nuclear layer (ONL) as manual detection is challenging in the other layers. When a detection is overlapping with an annotated focus it is considered a true positive, otherwise it is counted as a false positive.

Results : In the independent test set a sensitivity of 0.83 was obtained. At this level of sensitivity, an average of 8.3 false positives per B-scan were detected. False positives were mainly caused by detections outside the selected range (IPL to ONL) and misdetections by the graders.

Conclusions : An image analysis algorithm for the automatic detection and quantification of hyperreflective foci in OCT B-scans was developed. The experiments show promising results to obtain quantitative foci based biomarkers that can be used for the prediction of treatment response in DME.

This is an abstract that was submitted for the 2017 ARVO Annual Meeting, held in Baltimore, MD, May 7-11, 2017.

 

×
×

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.

×