July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Deep learning algorithm for diagnosis of Alzheimer’s disease using multimodal retinal imaging
Author Affiliations & Notes
  • Clayton Ellis Wisely
    Ophthalmology, Duke University, North Carolina, United States
  • Dong Wang
    Electrical and Computer Engineering, Duke University, North Carolina, United States
  • Ricardo Henao
    Biostatistics and Bioinformatics, Duke University, Durham, North Carolina, United States
  • Dilraj S Grewal
    Ophthalmology, Duke University, North Carolina, United States
  • Stephen Paul Yoon
    Ophthalmology, Duke University, North Carolina, United States
  • Bryce Polascik
    Ophthalmology, Duke University, North Carolina, United States
  • Atalie C. Thompson
    Ophthalmology, Duke University, North Carolina, United States
  • James R Burke
    Neurology, Duke University, North Carolina, United States
  • Lawrence Carin
    Electrical and Computer Engineering, Duke University, North Carolina, United States
  • Sharon Fekrat
    Ophthalmology, Duke University, North Carolina, United States
  • Footnotes
    Commercial Relationships   Clayton Wisely, None; Dong Wang, None; Ricardo Henao, None; Dilraj Grewal, None; Stephen Yoon, None; Bryce Polascik, None; Atalie Thompson, None; James Burke, None; Lawrence Carin, None; Sharon Fekrat, None
  • Footnotes
    Support  This work was supported in part by funding from the National Institutes of Health P30EY005722 to Duke University, the 2018 Unrestricted Grant from Research to Prevent Blindness (Duke University), and the Karen L. Wrenn Alzheimer’s Disease Award. None of the funding agencies had any role in the design or conduct of this research.
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1461. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Clayton Ellis Wisely, Dong Wang, Ricardo Henao, Dilraj S Grewal, Stephen Paul Yoon, Bryce Polascik, Atalie C. Thompson, James R Burke, Lawrence Carin, Sharon Fekrat; Deep learning algorithm for diagnosis of Alzheimer’s disease using multimodal retinal imaging. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1461.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop a deep learning algorithm to diagnose Alzhiemer’s disease (AD) using multimodal retinal images including OCT angiography (OCTA) and ultra-widefield (UWF) scanning laser ophthalmoscopy (SLO) color and autofluorescence (FAF) images.

Methods : AD and control subjects aged ≥50 were enrolled in this cross-sectional study (Clinicaltrials.gov NCT03233646). AD was diagnosed by an experienced neurologist. Controls were cognitively intact healthy volunteers. Exclusion criteria included history of non-AD dementia, diabetes, uncontrolled hypertension, demyelinating disorders, glaucoma, macular degeneration, other vitreoretinal pathology, or corrected visual acuity <20/40. Subjects were imaged with Zeiss Cirrus HD-5000 AngioPlex OCTA. Non-mydriatic color and FAF images were captured using Optos California UWF fundus SLO. Images with poor quality, low resolution, poor centration, or motion artifacts were excluded. A deep learning binary classifier model was built to distinguish between AD and control subjects. Our classifier was built on top of the first five layers from a ResNet-18 network, pre-trained on a public image dataset, CIFAR-10. We adopted batch normalization after each convolution and before rectified linear unit (ReLU) activation.

Results : 222 eyes of 117 controls and 63 eyes of 36 AD subjects were used to develop the algorithm. After exclusions UWF color and FAF images were included for both eyes of 105 control and 27 AD subjects, with partial sets included for others. 3x3 mm OCTA images centered on the fovea were included for 125 control eyes and 28 AD eyes. The model was trained and tested with 9-fold cross-validation. In each fold the training set included 198 control and 57 AD eyes, and test set included 24 control and 6 AD eyes. With OCTA and UWF color and FAF images, the model predicted the probability of AD, P(AD), for each AD or control subject (Figure 1). The area under the receiver operating characteristic curve (AUC) and mean accuracy describe the model’s precision-recall and trade-off. AUC (Figure 2) was 0.74 (SD = 0.014) and accuracy was 0.79 (SD = 0.012).

Conclusions : Our deep learning algorithm demonstrates the ability to use multimodal retinal imaging for automated AD diagnosis with nearly 80% accuracy. Larger databases containing additional imaging modalities may improve diagnostic accuracy of this algorithm and enable clinical utility for early AD diagnosis.

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

 

 

×
×

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.

×