June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Machine Learning Quantification of Fluid Volume in Eyes with Retinal Vein Occlusion Undergoing Treatment with Aflibercept: The REVOLT study
Author Affiliations & Notes
  • Mohammad Khan
    McMaster University, Hamilton, Ontario, Canada
  • Simrat Sodhi
    University of Cambridge, Cambridge, Cambridgeshire, United Kingdom
  • John Golding
    Vitreous Retina Macula Specialists of Toronto, Ontario, Canada
  • Austin Pereira
    Ophthalmology & Vision Sciences, University of Toronto, Toronto, Ontario, Canada
  • Anuradha Dhawan
    Vitreous Retina Macula Specialists of Toronto, Ontario, Canada
  • Jonathan D Oakley
    Voxeleron, San Francisco, California, United States
  • Daniel Russakoff
    Voxeleron, San Francisco, California, United States
  • Netan Choudhry
    Vitreous Retina Macula Specialists of Toronto, Ontario, Canada
    Ophthalmology & Vision Sciences, University of Toronto, Toronto, Ontario, Canada
  • Footnotes
    Commercial Relationships   Mohammad Khan None; Simrat Sodhi None; John Golding None; Austin Pereira None; Anuradha Dhawan None; Jonathan Oakley Voxeleron, Code E (Employment); Daniel Russakoff Voxeleron, Code E (Employment); Netan Choudhry Topcon, Optos PLC, Bayer, Allergan, Hoffman La Roche, Johnson & Johnson, Novartis, Carl Zeiss Meditec, Ellex , Code C (Consultant/Contractor), Topcon, Optos, Carl Zeiss Meditec, Code R (Recipient)
  • Footnotes
    Support  Bayer
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 214 – F0061. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Mohammad Khan, Simrat Sodhi, John Golding, Austin Pereira, Anuradha Dhawan, Jonathan D Oakley, Daniel Russakoff, Netan Choudhry; Machine Learning Quantification of Fluid Volume in Eyes with Retinal Vein Occlusion Undergoing Treatment with Aflibercept: The REVOLT study. Invest. Ophthalmol. Vis. Sci. 2022;63(7):214 – F0061.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Retinal vein occlusions (RVOs) are the second leading cause of vascular blindness, where anti-VEGF agents are among the first-line treatment options. Recent developments in artificial intelligence (AI) models have shown promise in OCT fluid segmentation and predictive value in anti-VEGF treatment outcomes. However, there are currently no trials demonstrating AI with swept-source Optical Coherence Tomography (SS-OCT) images in concordance with OCT analysis for RVO patients.

Methods : 49 treatment-naive subject eyes were diagnosed with visual impairment due to RVOs, either central (CRVO) or branch (BRVO). SS-OCT data was used to assess retinal layer thicknesses, as well as quantify intraretinal fluid (IRF), subretinal fluid (SRF), and serous pigment epithelium detachments (PEDs) using a deep learning-based, macular fluid segmentation algorithm. Patients received 3 loading doses of 2 mg intravitreal aflibercept injections (IAI). Image analysis was performed at baseline, month 3 & month 6 follow-up. Baseline OCT morphological features and fluid measurements were correlated using the Pearson correlation coefficient (PCC) to changes in BCVA to determine which features most impacted 6-month change in BCVA. The difference between areas of non-perfusion in OCT-A images treated with and without a denoising algorithm would also be evaluated.

Results : A combined model of thickness in the Outer-Plexiform Layer (OPL), retinal nerve fiber layer (RNFL) and presence of IRF had the strongest overall correlation for CRVO (PCC=0.865, p <0.05); while for BRVO the addition of IRF to the OPL-Inner Nasal model had a strong correlation (PCC=0.803, p<0.05). Baseline Ischemic Index in the Deep Capillary Complex (DCP) for CRVO without denoising demonstrated notable correlation with 6-month change in BCVA (PCC=0.7501, p = 0.079), and denoising strengthened this correlation (PCC=0.9100, p = 0.0101).

Conclusions : A combined model of IRF and thickness, alongside ischemic indices provide the best correlation to BCVA changes. This is clinically consistent given that the DCP supplies the OPL, as macular fluid builds up, these vessels have reduced flexibility to accommodate; thus becoming more occluded, causing further damage to the OPL. Ultimately, an AI approach to analyzing fluid metrics may provide an advantage in personalizing therapy and predicting BCVA outcomes for RVO patients.

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.

×