June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
DDLSNet: a novel deep learning-based system for grading glaucomatous funduscopic images for damage
Author Affiliations & Notes
  • Haroon Rasheed
    University of California Los Angeles David Geffen School of Medicine, Los Angeles, California, United States
  • Esteban Morales
    Glaucoma, Jules Stein Eye Institute, Los Angeles, California, United States
  • Tyler Austin Davis
    Computer Science, University of California Los Angeles, Los Angeles, California, United States
  • Zhe Fei
    University of California Los Angeles Jonathan and Karin Fielding School of Public Health, Los Angeles, California, United States
    Biostatistics, University of California Los Angeles, Los Angeles, California, United States
  • Lourdes Grassi
    Glaucoma, Jules Stein Eye Institute, Los Angeles, California, United States
  • Agustina De Gainza
    Glaucoma, Jules Stein Eye Institute, Los Angeles, California, United States
  • Joseph Caprioli
    Glaucoma, Jules Stein Eye Institute, Los Angeles, California, United States
  • Footnotes
    Commercial Relationships   Haroon Rasheed None; Esteban Morales None; Tyler Davis None; Zhe Fei None; Lourdes Grassi None; Agustina De Gainza None; Joseph Caprioli None
  • Footnotes
    Support  Supported by an unrestricted grant from Research to Prevent Blindness, the National Institutes of Health Grant 5K23EY022659 (KN-M), the Payden Glaucoma Fund, and the Simms/Mann Family Foundation.
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 2038 – A0479. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Haroon Rasheed, Esteban Morales, Tyler Austin Davis, Zhe Fei, Lourdes Grassi, Agustina De Gainza, Joseph Caprioli; DDLSNet: a novel deep learning-based system for grading glaucomatous funduscopic images for damage. Invest. Ophthalmol. Vis. Sci. 2022;63(7):2038 – A0479.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Efforts at automatic identification of the optic disc and its neural rim have been reported, but have not been used to grade glaucoma severity with an accepted metric. In this retrospective observational study, we propose a DDLSNet pipeline consisting of a rim segmentation (RimNet) branch and a disc size classification (DiscNet) branch to automate glaucoma grading with the disc damage likelihood scale (DDLS).

Methods : To develop RimNet, funduscopic images from the UCLA Stein Glaucoma Division were randomly split into training, validation, and test datasets (80/10/10). Optic rims of the training set were drawn by glaucoma specialists. RimNet uses contrast enhancement, an InceptionV3/LinkNet rim segmentation model, and computer vision to identify the thinnest rim location and calculate the rim-to-disc ratio (RDR). To develop DiscNet, paired funduscopic images and OCT data from UCLA Stein Glaucoma Division were randomly split into training, validation, test datasets (80/10/10). DiscNet uses a VGG19 network to label disc size as small, medium, or large. The DDLS grade is calculated from RDR and disc size. Three glaucoma specialists graded the RimNet test set with DDLS (scale 1-10). The main outcome measure was a weighted kappa agreement with agreement defined as +/- 1 DDLS grade between graders and DDLSnet.

Results : RimNet was developed on 857 images (mean age=60.3 (±14.2) years, male:female ratio=0.42), and achieved an RDR mean absolute error of 0.06 (±0.04) on test set between RimNet and physician. DiscNet was developed on 8366 images (mean age=67.6 (±14.5) years, male:female ratio=0.57), and achieved 77% classification accuracy on test set. DDLSNet was evaluated on 87 images from the RimNet test set; Table 1 lists the agreements between DDLSNet and graders and between individual graders.

Conclusions : DDLSNet achieved acceptable performance as shown by fair weighted kappa agreement with grader 2 and 3. This illustrates the feasibility of developing an automated process such as DDLSNet for glaucomatous grading of optic disc images. Further improvements are required, and will be achieved by further training of graders, increasing sample size, and algorithm enhancement.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

 

Table 1: Weighted kappa agreement and percent agreement intergrader and between DDLSNet and graders.

Table 1: Weighted kappa agreement and percent agreement intergrader and between DDLSNet and graders.

 

Figure 1: Left column shows raw funduscopic images. Right column shows DDLSNet results showcasing RDR, disc size, and DDLS grade.

Figure 1: Left column shows raw funduscopic images. Right column shows DDLSNet results showcasing RDR, disc size, and DDLS grade.

×
×

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.

×