Article Text

other Versions

Download PDFPDF
Convolutional neural network to identify symptomatic Alzheimer’s disease using multimodal retinal imaging
  1. C. Ellis Wisely1,
  2. Dong Wang2,
  3. Ricardo Henao3,
  4. Dilraj S. Grewal1,
  5. Atalie C. Thompson1,
  6. Cason B. Robbins1,
  7. Stephen P. Yoon1,
  8. Srinath Soundararajan1,
  9. Bryce W. Polascik1,
  10. James R. Burke4,
  11. Andy Liu4,
  12. Lawrence Carin2,
  13. Sharon Fekrat1
  1. 1Department of Ophthalmology, Duke University Health System, Durham, NC, USA
  2. 2Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina, USA
  3. 3Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina, USA
  4. 4Department of Neurology, Duke University Health System, Durham, NC, USA
  1. Correspondence to Dr Sharon Fekrat, Department of Ophthalmology, Duke University, Durham, NC 27708-0187, USA; sharon.fekrat{at}


Background/Aims To develop a convolutional neural network (CNN) to detect symptomatic Alzheimer’s disease (AD) using a combination of multimodal retinal images and patient data.

Methods Colour maps of ganglion cell-inner plexiform layer (GC-IPL) thickness, superficial capillary plexus (SCP) optical coherence tomography angiography (OCTA) images, and ultra-widefield (UWF) colour and fundus autofluorescence (FAF) scanning laser ophthalmoscopy images were captured in individuals with AD or healthy cognition. A CNN to predict AD diagnosis was developed using multimodal retinal images, OCT and OCTA quantitative data, and patient data.

Results 284 eyes of 159 subjects (222 eyes from 123 cognitively healthy subjects and 62 eyes from 36 subjects with AD) were used to develop the model. Area under the receiving operating characteristic curve (AUC) values for predicted probability of AD for the independent test set varied by input used: UWF colour AUC 0.450 (95% CI 0.282, 0.592), OCTA SCP 0.582 (95% CI 0.440, 0.724), UWF FAF 0.618 (95% CI 0.462, 0.773), GC-IPL maps 0.809 (95% CI 0.700, 0.919). A model incorporating all images, quantitative data and patient data (AUC 0.836 (CI 0.729, 0.943)) performed similarly to models only incorporating all images (AUC 0.829 (95% CI 0.719, 0.939)). GC-IPL maps, quantitative data and patient data AUC 0.841 (95% CI 0.739, 0.943).

Conclusion Our CNN used multimodal retinal images to successfully predict diagnosis of symptomatic AD in an independent test set. GC-IPL maps were the most useful single inputs for prediction. Models including only images performed similarly to models also including quantitative data and patient data.

  • retina
  • diagnostic tests/investigation
  • imaging

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.


  • Presented at A portion of this data was presented at the 2019 Association for Research in Vision and Ophthalmology (ARVO) annual meeting in Vancouver, Canada.

  • Contributors CEW was the first author and drafted the manuscript. DW, RH and LC coauthored the manuscript, provided critical review, and designed the CNN. ACT, SS, CBR, SY, JB, BWP and AL were involved in patient recruitment, data management, imaging and review of the manuscript. ACT performed statistical analysis. DSG and SF designed the study, coauthored the manuscript and critically reviewed the manuscript.

  • Funding This research was supported in part by Alzheimer's Drug Discovery Foundation.

  • Competing interests None declared.

  • Patient consent for publication Not required.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data availability statement Data from this study is available upon reasonable request from our corresponding author, Dr. Sharon Fekrat,

  • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.

Linked Articles

  • At a glance
    Frank Larkin