Investigative Ophthalmology & Visual Science Cover Image for Volume 60, Issue 9
July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Standardization and acceleration of OCT Angiography image quality assessment using a deep learning algorithm
Author Affiliations & Notes
  • Jost Lennart Lauermann
    Department of Ophthalmology, University of Muenster Medical Center, Muenster, Germany
  • Maximilian Treder
    Department of Ophthalmology, University of Muenster Medical Center, Muenster, Germany
  • Maged Alnawaiseh
    Department of Ophthalmology, University of Muenster Medical Center, Muenster, Germany
  • Chrristoph Clemens
    Department of Ophthalmology, University of Muenster Medical Center, Muenster, Germany
  • Nicole Eter
    Department of Ophthalmology, University of Muenster Medical Center, Muenster, Germany
  • Florian Alten
    Department of Ophthalmology, University of Muenster Medical Center, Muenster, Germany
  • Footnotes
    Commercial Relationships   Jost Lauermann, Bayer (R), Eyetec (R), Novartis (R); Maximilian Treder, Allergan (R), Novartis (R); Maged Alnawaiseh, Bayer (R), Novartis (R); Chrristoph Clemens, Bayer (R), Heidelberg Engineering (R), Novartis (R); Nicole Eter, Alimera (R), Alimera Sciences (C), Allergan (F), Allergan (R), Allergan (C), Bayer (F), Bayer (R), Bayer (C), Heidelberg Engineering (R), Novartis (F), Novartis (R), Novartis (C), Roche (C); Florian Alten, Bayer (R)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1499. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Jost Lennart Lauermann, Maximilian Treder, Maged Alnawaiseh, Chrristoph Clemens, Nicole Eter, Florian Alten; Standardization and acceleration of OCT Angiography image quality assessment using a deep learning algorithm. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1499.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To expedite and to standardize the process of image quality assessment in optical coherence tomography angiography (OCTA) using a specialized deep learning algorithm (DLA).

Methods : 200 randomly chosen en-face macular OCTA images of the central 3x3 mm superficial vascular plexus were evaluated retrospectively by an OCTA experienced reader. Images were defined either as sufficient (group 1, n=100) or insufficient image quality (group 2, n=100) based on Motion Artifact Score (MAS) and Segmentation Accuracy Score (SAS). A pre-trained multi-layer deep convolutional neural network (DCNN) was trained and validated with 160 of these en-face OCTA scans (group 1: 80; group 2: 80). Training accuracy and validation accuracy were computed. The DLA was tested in detecting 40 untrained OCTA images (group 1: 20; group 2: 20). An insufficient image quality probability score (IPS) and a sufficient image quality probability score (SPS) were calculated.

Results : Training and validation accuracy were 97 % and 100 %. 90 % (18/20) of the OCTA images with insufficient image quality and 90 % (18/20) with sufficient image quality were correctly classified by the DLA. Mean IPS was 0.88±0.21, mean SPS was 0.84±0.19. Discrimination between both groups was highly significant (p<0.001). Sensitivity of the DLA was 90 %, specificity 90 % and accuracy 90 %.

Conclusions : Deep learning (DL) appears to be a potential approach to automatically distinguish between sufficient and insufficient OCTA image quality and to establish image quality standards in this recent imaging modality.

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

×
×

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.

×