June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Analyzing the Retinal and Choroidal Vasculature and Structure in Cognitively Healthy Individuals at Higher Genetic Risk for Alzheimer’s Disease using a Convolutional Neural Network
Author Affiliations & Notes
  • Cason Robbins
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Dilraj Singh Grewal
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Dong Wang
    Electrical and Computer Engineering, Duke University School of Medicine, Durham, North Carolina, United States
  • Clayton Wisely
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Ricardo Henao
    Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, North Carolina, United States
  • Jia Min Lee
    Tan Tock Seng Hospital, Singapore, Singapore
  • Rupesh V Agrawal
    Tan Tock Seng Hospital, Singapore, Singapore
  • Srinath Soundararajan
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Atalie C. Thompson
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Brenda Plassman
    Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, North Carolina, United States
  • Eleonora M Lad
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Heather Whitson
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
    Medicine, Duke University School of Medicine, Durham, North Carolina, United States
  • Lawrence Carin
    Electrical and Computer Engineering, Duke University School of Medicine, Durham, North Carolina, United States
  • Sharon Fekrat
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Footnotes
    Commercial Relationships   Cason Robbins, None; Dilraj Grewal, None; Dong Wang, None; Clayton Wisely, None; Ricardo Henao, None; Jia Lee, None; Rupesh Agrawal, None; Srinath Soundararajan, None; Atalie Thompson, None; Brenda Plassman, None; Eleonora Lad, None; Heather Whitson, None; Lawrence Carin, None; Sharon Fekrat, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 2489. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Cason Robbins, Dilraj Singh Grewal, Dong Wang, Clayton Wisely, Ricardo Henao, Jia Min Lee, Rupesh V Agrawal, Srinath Soundararajan, Atalie C. Thompson, Brenda Plassman, Eleonora M Lad, Heather Whitson, Lawrence Carin, Sharon Fekrat; Analyzing the Retinal and Choroidal Vasculature and Structure in Cognitively Healthy Individuals at Higher Genetic Risk for Alzheimer’s Disease using a Convolutional Neural Network. Invest. Ophthalmol. Vis. Sci. 2021;62(8):2489.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To evaluate differences in retinal and choroidal vasculature and structure in cognitively healthy individuals with at least one APOE e4 allele (who are at a greater risk for Alzheimer’s disease than those without an APOE e4 allele) compared to those without an APOE e4 allele using retinal and choroidal quantitative parameters as well as a convolutional neural network (CNN).

Methods : In this cross-sectional study, 188 eyes of 98 cognitively healthy individuals with at least one APOE e4 allele and 225 eyes of 117 individuals without an APOE e4 allele were imaged. Of these, 150 eyes of 84 APOE e4 participants and 169 eyes of 98 participants without APOE e4 were used to develop a CNN. Zeiss Cirrus HD-5000 with AngioPlex (Carl Zeiss Meditec, Dublin, CA) was utilized to acquire OCT and OCTA images; enhanced depth imaging foveal OCT scans were acquired and underwent image binarization to determine choroidal area and vascularity index. Generalized estimating equations (GEE) adjusted for age and sex were used to compare parameters between groups.

Results : The two groups were matched with regards to age, sex, and Mini-Mental State Examination score (all p > 0.05). After adjustment for covariates in a multivariable GEE model, the two groups did not significantly differ in superficial capillary plexus vessel density or perfusion density, foveal avascular zone area, ganglion cell layer thickness, retinal nerve fiber layer thickness, central subfield thickness, subfoveal choroidal thickness, total choroidal area, choroid luminal area, or choroidal vascularity index (all p > 0.05). A CNN was unable to discriminate between the two groups (area under the receiver operating characteristic value = 0.526).

Conclusions : Retinal thickness, retinal microvasculature, and choroidal vasculature in cognitively healthy individuals with APOE e4-based predisposition to Alzheimer’s disease do not significantly differ from cognitively healthy individuals without an APOE e4 allele. Longitudinal study may help better identify the onset of retinal microvascular abnormalities in relation to the onset of cognitive impairment.

This is a 2021 ARVO Annual Meeting abstract.

 

Results of generalized estimating equation analysis for retinal and choroidal structural parameters in individuals with at least one APOE e4 allele and individuals with no APOE e4 alleles.

Results of generalized estimating equation analysis for retinal and choroidal structural parameters in individuals with at least one APOE e4 allele and individuals with no APOE e4 alleles.

×
×

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.

×