June 2020
Volume 61, Issue 7
ARVO Annual Meeting Abstract  |   June 2020
Developing community based diabetic referral service using deep learning on hand held, non-mydriatic fundus images.
Author Affiliations & Notes
  • Joan M. M. Nunez Do Rio
    University College London, London, United Kingdom
  • Adam M Dubis
    University College London, London, United Kingdom
  • Ahmed M Hagag
    University College London, London, United Kingdom
  • Rajiv Raman
    VR, Sankara Nethralaya Chennai, India
  • Sobha Sivaprasad
    Moorfields Eye Hospital, United Kingdom
  • Christos Bergeles
    King's College London, United Kingdom
  • Footnotes
    Commercial Relationships   Joan M. Nunez Do Rio, None; Adam Dubis, None; Ahmed Hagag, None; Rajiv Raman, None; Sobha Sivaprasad, Allergan (F), Bayer (S), Boehringer Ingelheim (F), Novartis (F), Optos (F), Roche (F); Christos Bergeles, None
  • Footnotes
    Support  Support of the Global Challenges Research Fund and United Kingdom Research and Innovation (Grant Ref: MR/P027881/1). National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital National Health Service Foundation Trust and UCL Institute of Ophthalmology.
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 2035. doi:
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Joan M. M. Nunez Do Rio, Adam M Dubis, Ahmed M Hagag, Rajiv Raman, Sobha Sivaprasad, Christos Bergeles; Developing community based diabetic referral service using deep learning on hand held, non-mydriatic fundus images.. Invest. Ophthalmol. Vis. Sci. 2020;61(7):2035.

      Download citation file:

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

  • Supplements

Purpose : Deep learning (DL) has been showing great promise in ophthalmology, especially in diagnosis of referable diabetic retinopathy (DR). To date, these advances have always been done using clinically collected datasets. However, the real power of DL is in moving the experience of highly qualified ophthalmologists to community settings, especially in rural and developing areas. The images collected in non-clinical settings by field workers without clinical training present worse quality and high degree of image variance due to acquisition set-ups and illumination. DL systems can contribute to create cost-effective diagnostic models in non-clinical settings. In this study we developed a DL based system for the classification of referable DR using hand held non-mydriatic retinal photographs.

Methods : Non-mydriatic retinal photographs were collected as part of the ORNATE India Project, an ongoing community-based study to test novel diabetic screening services. Retinal photographs were acquired by field workers as part of door-door and point of care non-clinical screening using Zeiss Visuscout® 100 mobile fundus camera and graded by trained ophthalmologists. A total of 6,655 images (11.3% referral samples) were used to train and validate the DL system. Due to the highly unbalanced distribution of the data, the testing set was formed by 40% of the referral samples and the same number of non-referral samples. An Inception-ResNet V2 model was fined tuned on augmented and oversampled training data to balance class distribution.

Results : In the validation set, precision, recall and AUC (Area Under the Curve) for referable DR achieved 75.74%, 82.79% and 86.15%. Due to the highly imbalanced dataset, results benefit from imbalanced data augmentation and oversampling to train the model under an apparently balanced distribution. Highly regularized training set-ups, using techniques such as L2 regularization and dropout, improved performance by reducing the model tendency to overfit training data.

Conclusions : The DL system demonstrated promising results in detecting referral DR suspects using non-mydriatic retinal images. We showed that artificial intelligence can be used to create grading algorithms using data collected at non-clinical settings by field workers. These support future work on the development of automated screening programs for diagnosis of DR in special populations or rural areas.

This is a 2020 ARVO Annual Meeting abstract.


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.