July 2018
Volume 59, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2018
The development and validation of a deep learning algorithm for referable diabetic retinopathy
Author Affiliations & Notes
  • Stuart Keel
    Centre for Eye Research Australia, Melbourne, Victoria, Australia
  • Zhixi Li
    Zhongshan Ophthalmic Center, Guangzhou, China
  • Yifan He
    Healgoo Interactive Medical Technology Co.Ltd, Guangzhou, China
  • Wei Meng
    Healgoo Interactive Medical Technology Co.Ltd, Guangzhou, China
  • Robert Chang
    Byers Eye Institute at Stanford University, Palo Alto, California, United States
  • Mingguang He
    Zhongshan Ophthalmic Center, Guangzhou, China
    Centre for Eye Research Australia, Melbourne, Victoria, Australia
  • Footnotes
    Commercial Relationships   Stuart Keel, None; Zhixi Li, None; Yifan He, None; Wei Meng, None; Robert Chang, None; Mingguang He, None
  • Footnotes
    Support  National Natural Science Foundation of China (81420108008) and Science and Technology Planning Project of Guangdong Province (2013B20400003).
Investigative Ophthalmology & Visual Science July 2018, Vol.59, 738. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Stuart Keel, Zhixi Li, Yifan He, Wei Meng, Robert Chang, Mingguang He; The development and validation of a deep learning algorithm for referable diabetic retinopathy
      . Invest. Ophthalmol. Vis. Sci. 2018;59(9):738.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To describe the development and validation of an artificial-intelligence based, deep learning algorithm (DLA) for the detection of referable diabetic retinopathy (DR).

Methods : A cloud-based, convolutional neuron network (CNN) deep learning system for the automated detection of referable DR (≥pre-proliferative DR and/or diabetic macular edema) was developed and tested based on a set of 71,043 non-stereoscopic, retinal images. Retinal photographs were graded for DR severity by a panel of licensed ophthalmologists, with a gold standard grading for each image assigned when ≥3 consistent grading outcomes were achieved. For external validation, we also tested our DLA using 13,406 retinal images (any DR = 904; referable DR = 401) from three population-based cohorts of Malay, Caucasian and Indigenous Australians. Area under curve (AUC), sensitivity and specificity were the key outcome measures.

Results : In the local validation dataset, the AUC, sensitivity and specificity of the DLA for referable DR was 0.989, 97.0% and 91.4%, respectively. Testing against the independent, multi-ethnic dataset achieved an AUC, sensitivity and specificity of 0.955, 92.5% and 98.5%, respectively. Eighty six percent of false positives cases were due to a misclassification of background DR. Undetected intra-retinal microvascular abnormalities accounted for 77% of all false negative cases.

Conclusions : This artificial-intelligence based DLA can be used to detection referable DR from retinal images with high accuracy. This technology offers countless potential to increase the efficiency, accessibility and affordability of DR screening programmes.

This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.

×
×

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.

×