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
A Deep Learning System for Predicting the Progression of Diabetic Retinopathy
Author Affiliations & Notes
  • Victoria Wang
    Department of Ophthalmology, University of Southern California Keck School of Medicine, Los Angeles, California, United States
  • Men-Tzung Lo
    Department of Biomedical Sciences and Engineering, National Central University, Taoyuan, Taiwan
  • Ta-ching Chen
    Department of Ophthalmology, National Taiwan University Hospital, Taipei, Taiwan
  • Chu-Hsuan Huang
    Department of Ophthalmology, Cathay General Hospital, Taipei, Taiwan
  • Adam Huang
    School of Medicine, National Tsing Hua University, Hsinchu, Hsinchu City, Taiwan
  • Pa-Chun Wang
    Department of Medical Research, Cathay General Hospital, Taipei, Taiwan
  • Footnotes
    Commercial Relationships   Victoria Wang None; Men-Tzung Lo None; Ta-ching Chen None; Chu-Hsuan Huang None; Adam Huang None; Pa-Chun Wang None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 3768. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Victoria Wang, Men-Tzung Lo, Ta-ching Chen, Chu-Hsuan Huang, Adam Huang, Pa-Chun Wang; A Deep Learning System for Predicting the Progression of Diabetic Retinopathy. Invest. Ophthalmol. Vis. Sci. 2024;65(7):3768.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To address the increasing prevalence of diabetes, artificial intelligence (AI) systems have been developed for diabetic retinopathy (DR) screening and diagnosis. However, current AI systems are limited in predicting the progression and prognosis of DR. Identifying patients more likely to progress and appropriately referring them to an ophthalmologist is key to vision preservation. Our goal was to develop and evaluate a prognostication system that uses longitudinal fundus photos to train deep learning models for predicting DR progression from non-referable to referable status.

Methods : We conducted a retrospective study comparing pairs of retinal fundus images of the same eye taken at two time points separated by a year or more apart. The fundus photos were obtained from EyePACS DR’s graded dataset. We classified normal, mild nonproliferative DR (NPDR), and moderate NPDR to be non-referable DR (NRDR); severe NPDR and proliferative PDR were classified as referrable DR (RDR). In developing a DR prognostication system, we only considered cases where the first encounter was NRDR. Cases where both encounters were NRDR were labelled as negative; cases progressing from NRDR to RDR were labelled as positive. Using a subset of 12768 images of 6384 eyes (two images per eye, taken 733 +/-353 days apart), we trained a neural network, ResNeXt (80%-10%-10% training-validation-testing split), to predict DR severity. An independent e-ophtha dataset of 148 images with microaneurysm (MA) annotations (75%-25% training-validation split) was used to train another neural network, Mask-RCNN, to estimate the number of existing MAs. The resultant DR severity and MA number scores of the first NRDR image of a given eye were used to predict if the DR had progressed to RDR in the second, later image (Fig 1.)

Results : The area under the receiver operating characteristic curve (AUC) for predicting RDR was 0.956 with the ResNeXt model. The recall, precision, and F1-score in detecting individual MAs were 0.786, 0.615, and 0.690 respectively with the Mask-RCNN model. A combination of the ResNeXt and Mask-RCNN models had an AUC of 0.989.

Conclusions : We developed and validated an AI system that prognosticates DR progression based on longitudinal fundus photos. This system has the potential to support clinicians in identifying DR cases more likely to progress and referring them to an ophthalmologist for management.

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

 

Fig 1. DR prognostication model

Fig 1. DR prognostication model

×
×

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.

×