Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Deep learning predicts bilateral versus unilateral diabetic retinopathy
Author Affiliations & Notes
  • Jen-Yeu Wang
    Stanford University School of Medicine, Stanford, California, United States
    California University of Science and Medicine, Colton, California, United States
  • Yizhuo Shen
    Harvard Medical School, Boston, Massachusetts, United States
  • Akshay Reddy
    California University of Science and Medicine, Colton, California, United States
  • Nathaniel Tak
    Midwestern University Arizona College of Osteopathic Medicine, Glendale, Arizona, United States
  • Neel Shrikant Nawathey
    Touro University California College of Osteopathic Medicine, Vallejo, California, United States
  • Parsa Riazi Esfahani
    California University of Science and Medicine, Colton, California, United States
  • San San Lwin
    California University of Science and Medicine, Colton, California, United States
  • Alexander Garcia
    California University of Science and Medicine, Colton, California, United States
  • Longines Lee
    California University of Science and Medicine, Colton, California, United States
  • James Martel
    California Northstate University College of Medicine, Elk Grove, California, United States
  • Footnotes
    Commercial Relationships   Jen-Yeu Wang None; Yizhuo Shen None; Akshay Reddy None; Nathaniel Tak None; Neel Nawathey None; Parsa Riazi Esfahani None; San San Lwin None; Alexander Garcia None; Longines Lee None; James Martel None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 3775. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Jen-Yeu Wang, Yizhuo Shen, Akshay Reddy, Nathaniel Tak, Neel Shrikant Nawathey, Parsa Riazi Esfahani, San San Lwin, Alexander Garcia, Longines Lee, James Martel; Deep learning predicts bilateral versus unilateral diabetic retinopathy. Invest. Ophthalmol. Vis. Sci. 2024;65(7):3775.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Diabetic retinopathy, a leading cause of adult blindness, is a complex and incurable ocular disease driven by vascular damage in the retinas of patients with diabetes. Although the disease usually affects both eyes of a patient, the pathophysiology of the bilateral versus unilateral presentation remains unclear. The present investigation seeks to understand if fundus images of one diseased eye contain features that can be meaningfully learned by deep neural networks to indicate bilateral or unilateral diabetic retinopathy at the patient level.

Methods : The public EyePACS diabetic retinopathy dataset was queried and found to contain retinal images from 3,811 bilateral and 1,500 unilateral diabetic retinopathy patients. The eye with the greater severity was selected, ties broken randomly, yielding a dataset of 5,311 total images split representatively into 4,248 (80%) images for training and 1,063 (20%) images for testing. The first approach involved transfer learning of convolutional neural networks pretrained on ImageNet, including AlexNet, VGG-16, and ResNet-18. The second approach utilized a non-pretrained ResNet-18 with a modified two-channel output layer as the network architecture. Model performance was evaluated with accuracy, precision, recall, and F1 score.

Results : Pretrained AlexNet, pretrained VGG-16, pretrained ResNet-18, and non-pretrained ResNet-18 were implemented on PyTorch and fitted with the one-cycle learning rate policy on the training set. The pretrained networks were fine-tuned for 10 epochs, while the non-pretrained network underwent training for 20 epochs. Evaluating the four models on the test set resulted in prediction accuracies of 73.38%, 70.46%, 72.34%, and 71.40%, respectively. While the pretrained AlexNet resulted in the highest F1 score at 0.8404, the pretrained ResNet-18 resulted in the highest precision at 0.7516. The evaluation metrics for all four models are provided in Table 1.

Conclusions : To our knowledge, this is the first study to demonstrate prediction of unilateral or bilateral diabetic retinopathy based on a single fundus photograph. We conclude that artificial intelligence is capable of performing this classification task with reasonable accuracy, suggesting the existence of latent features within retinal images that may yield insights into how diabetic retinopathy manifests globally in the patient.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Table 1. Performance of four deep learning models evaluated on the test set

Table 1. Performance of four deep learning models evaluated on the test set

×
×

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.

×