July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Automatic Segmentation of Drusen and Exudates on Color Fundus Images using Generative Adversarial Networks
Author Affiliations & Notes
  • Jonne Engelberts
    Thirona, Nijmegen, Netherlands
  • Cristina González-Gonzalo
    Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, Netherlands
    Department of Ophthalmology, Radboud University Medical Center, Nijmegen, Netherlands
  • Clara I Sanchez
    Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, Netherlands
    Department of Ophthalmology, Radboud University Medical Center, Nijmegen, Netherlands
  • Mark J. van Grinsven
    Thirona, Nijmegen, Netherlands
  • Footnotes
    Commercial Relationships   Jonne Engelberts, Thirona (E); Cristina González-Gonzalo, None; Clara Sanchez, None; Mark van Grinsven, Thirona (E)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1493. doi:https://doi.org/
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Jonne Engelberts, Cristina González-Gonzalo, Clara I Sanchez, Mark J. van Grinsven; Automatic Segmentation of Drusen and Exudates on Color Fundus Images using Generative Adversarial Networks. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1493. doi: https://doi.org/.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : The presence of drusen and exudates, visible as bright lesions on color fundus images, is one of the early signs of visual threatening diseases such as Age-related Macular Degeneration and Diabetic Retinopathy. Accurate detection and quantification of these lesions during screening can help identify patients that would benefit from treatment. We developed a method based on generative adversarial networks (GANs) to segment bright lesions on color fundus images.

Methods : We used 4179 color fundus images that were acquired during clinical routine. The images were contrast enhanced to increase the contrast between bright lesions and the background. All bright lesions were manually annotated by marking the center point of the lesions. The GAN was trained to estimate the image without bright lesions. The final segmentation was obtained by taking the difference between the input image and the estimated output.

Results : This method was applied to an independent test set of 52 color fundus images with non-advanced stages of AMD from the European Genetic Database, which were fully segmented for bright lesions by two trained human observers. The method achieved Dice scores of 0.4862 and 0.4849 when compared to the observers, whereas the inter-observer Dice score was 0.5043. The total segmented bright lesion area per image was evaluated using the intraclass correlation (ICC). The method scored 0.8537 and 0.8352 when compared to the observers, whereas the inter-observer ICC was 0.8893.

Conclusions : The results show the performance is close to the agreement between trained observers. This automatic segmentation of bright lesions can help early diagnosis of visual threatening diseases and opens the way for large scale clinical trials.

This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.

 

Figure 1a: contrast enhanced color fundus image. Figure 1b: generated image. Figure 1c: difference between 1a and 1b. Figure 1d: observer 1 annotations. Figure 1e observer 2 annotations. Figure 1f: automatic segmentation by applying a threshold to figure 1c.

Figure 1a: contrast enhanced color fundus image. Figure 1b: generated image. Figure 1c: difference between 1a and 1b. Figure 1d: observer 1 annotations. Figure 1e observer 2 annotations. Figure 1f: automatic segmentation by applying a threshold to figure 1c.

×
×

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.

×