June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Automated Detection of Posterior Vitreous Detachment on Optical Coherence Tomography Images Using Computer Vision and Deep Learning Algorithms
Author Affiliations & Notes
  • Lingling Huang
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • Moira Feng
    University of California San Diego, La Jolla, California, United States
  • Alexa Li
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • Zixi Wang
    University of California San Diego, La Jolla, California, United States
  • Justin Arnett
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • Sally Baxter
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • Dirk-Uwe G Bartsch
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • David Kuo
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • Bharanidharan Radha Saseendrakumar
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • Joy Guo
    University of California San Diego, La Jolla, California, United States
  • Eric Nudleman
    University of California at San Diego Department of Ophthalmology at the Shiley Eye Institute, La Jolla, California, United States
  • Footnotes
    Commercial Relationships   Lingling Huang None; Moira Feng None; Alexa Li None; Zixi Wang None; Justin Arnett None; Sally Baxter None; Dirk-Uwe G Bartsch None; David Kuo None; Bharanidharan Radha Saseendrakumar None; Joy Guo None; Eric Nudleman Alcon, Code C (Consultant/Contractor)
  • Footnotes
    Support  DP5OD029610 National Institutes of Health Office of the Director. Unrestricted departmental grant from Research to Prevent Blindness. Vision core grant NEI P30EY022589
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 3002 – F0272. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Lingling Huang, Moira Feng, Alexa Li, Zixi Wang, Justin Arnett, Sally Baxter, Dirk-Uwe G Bartsch, David Kuo, Bharanidharan Radha Saseendrakumar, Joy Guo, Eric Nudleman; Automated Detection of Posterior Vitreous Detachment on Optical Coherence Tomography Images Using Computer Vision and Deep Learning Algorithms. Invest. Ophthalmol. Vis. Sci. 2022;63(7):3002 – F0272.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Recognizing a posterior vitreous detachment (PVD) is important for pre-surgical planning and risk-stratification for retinal tears and detachment. Deep learning (DL) methods of optical coherence tomography (OCT) images have been trialed on several retinal diseases to assist diagnosis; however, reliable models capable of detecting PVD have not been established. Our studies aim to develop reliable computer algorithms for automated detection of PVD on OCT images.

Methods : Consecutive OCT volumetric scans of 800 eyes obtained with Heidelberg Spectralis from November 2020 to October 2021 were retrospectively reviewed. Eyes with poor image quality or history of pars plana vitrectomy were excluded. Four trained graders individually labeled the PVD status of each eye by reviewing the entire volume B-scans, in addition to the horizontal and vertical raster scans. A second review was performed by an expert grader if consensus review was needed.

Two computer algorithms were developed. A customized computer vision algorithm based on image filtering and edge detection was designed to localize the posterior hyaloid and identify the presence or absence of a complete PVD in OCT volume scan. A second DL image classification model based on ResNet-50 architecture was trained to detect PVD status on OCT.

Results : Both the customized algorithm and DL model detection results were largely in agreement with the PVD status labeled by trained graders, with the customized algorithm surpassing the DL model in F1-scores for per-volume PVD detection. The accuracy of the customized algorithm and DL model was 85.57%, and 76.90%, respectively. The sensitivity of the customized algorithm and DL model was 78.21% and 86.09%, while the specificity was 93.62% and 70.45%, respectively (Table 1).

Conclusions : Using both traditional computer vision and deep learning approaches, we successfully developed reliable models to recognize PVD status on OCT images, demonstrating the potential for automated image classification to detect vitreoretinal pathologies and assist with pre-surgical planning. Further optimization of the two algorithms are currently in process with plans for validation using a prospective, independent data set.

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

 

×
×

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.

×