July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Deep-Learning-Based Estimation of Regional Volumetric Information from 2D Fundus Photography in Cases of Optic Disc Swelling
Author Affiliations & Notes
  • Samuel Johnson
    Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, United States
  • Mohammad Shafkat Islam
    Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, United States
  • Jui-Kai Wang
    Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, United States
    Center for the Prevention and Treatment of Visual Loss, Iowa City VA Health System, Iowa City, Iowa, United States
  • Thurtell Matthew
    Ophthalmology and Visual Sciences, University of Iowa Hospital and Clinics, Iowa City, Iowa, United States
    Neurology, University of Iowa Hospital and Clinics, Iowa City, Iowa, United States
  • Randy H Kardon
    Center for the Prevention and Treatment of Visual Loss, Iowa City VA Health System, Iowa City, Iowa, United States
    Ophthalmology and Visual Sciences, University of Iowa Hospital and Clinics, Iowa City, Iowa, United States
  • Mona Garvin
    Center for the Prevention and Treatment of Visual Loss, Iowa City VA Health System, Iowa City, Iowa, United States
    Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, United States
  • Footnotes
    Commercial Relationships   Samuel Johnson, None; Mohammad Shafkat Islam, None; Jui-Kai Wang, None; Thurtell Matthew, None; Randy Kardon, Acorda (C), Department of Veterans Affairs Research Foundation (S), Fight for Sight (S), Novartis (C); Mona Garvin, The University of Iowa (P)
  • Footnotes
    Support  R01 EY023279, I01 RX001786
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 3597. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Samuel Johnson, Mohammad Shafkat Islam, Jui-Kai Wang, Thurtell Matthew, Randy H Kardon, Mona Garvin; Deep-Learning-Based Estimation of Regional Volumetric Information from 2D Fundus Photography in Cases of Optic Disc Swelling. Invest. Ophthalmol. Vis. Sci. 2019;60(9):3597.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : With the introduction of optical coherence tomography (OCT) as well as retinal-layer-segmentation algorithms, quantitative assessment for optic disc swelling has improved. However, OCT is not always available as its use is usually limited to specialized clinics. Previously, we published an approach using a random forest to estimate the retinal thickness between the inner limiting membrane (ILM) and retinal pigment epithelium (RPE) in fundus photographs (Johnson et al., OMIA, 2018). We now propose a new model using deep-learning techniques to predict thickness between the surfaces which avoids selection of key image features for model training.

Methods : A U-Net convolutional neural network (Ronneberger et al., MICCAI 2015) was trained using 78 (70 training, 8 validation) cropped fundus photographs (input, Fig. 1, top) and matching OCT-derived thickness maps (reference standard, Fig. 1, bottom) from recruited subjects with optic disc swelling at the University of Iowa Neuro-Ophthalmology Clinic. Images were preprocessed by using contrast limited adaptive histogram equalization as well as normalization. Hyperparameters were as follows: 500 epochs, 10e-3 learning rate, and a batch size of 8. The trained model was then used to predict OCT-based thickness maps on ten strictly withheld test images.

Results : Model predictions on the test images were compared with OCT-derived volumetric measures: total retinal volume as well as regional volumes were calculated. For total retinal volume, a root-mean-square-error (RMSE) of 2.07 mm3 was achieved. When comparing regional volumes, the nasal, temporal, inferior, superior, and peripapillary regions had RMSEs of 0.75 mm3, 0.82 mm3, 0.85 mm3, 0.91 mm3, and 1.62 mm3 respectively.

Conclusions : The proposed deep-neural-network is capable of estimating retinal thickness at the pixel level in fundus photographs without using expert-designed image features. Since OCT is not available everywhere yet, this could be an alternative approach to gain insight for optic-disc-swelling assessment.

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

 

Fig 1: Top: Input 200x200 ONH region fundus photographs. Middle: The predicted thickness map for the above fundus image. Bottom: OCT reference standard thickness map. All volumes shown are in mm3. PRV (partial retinal volume) refers to the cumulative volume of all 4 quadrants. TRV is defined in the map image.

Fig 1: Top: Input 200x200 ONH region fundus photographs. Middle: The predicted thickness map for the above fundus image. Bottom: OCT reference standard thickness map. All volumes shown are in mm3. PRV (partial retinal volume) refers to the cumulative volume of all 4 quadrants. TRV is defined in the map image.

 

Fig 2: Workflow depiction with network architecture

Fig 2: Workflow depiction with network architecture

×
×

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.

×