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
Prediction of Visual Acuity Response to Ranibizumab in Age-Related Macular Degeneration Using Artificial Intelligence-Based Analysis of Fluorescein Angiography
Author Affiliations & Notes
  • Ryan S. Huang
    University of Toronto Temerty Faculty of Medicine, Toronto, Ontario, Canada
  • Andrew Mihalache
    University of Toronto Temerty Faculty of Medicine, Toronto, Ontario, Canada
  • Marko Popovic
    University of Toronto Temerty Faculty of Medicine, Toronto, Ontario, Canada
  • Colyn Munn
    Dalhousie University Faculty of Medicine, Halifax, Nova Scotia, Canada
  • Yonatan Serlin
    Dalhousie University Faculty of Medicine, Halifax, Nova Scotia, Canada
  • Isabela Martins Melo
    University of Toronto Temerty Faculty of Medicine, Toronto, Ontario, Canada
  • Aurora Pecaku
    University of Toronto Temerty Faculty of Medicine, Toronto, Ontario, Canada
  • Lyna Kamintsky
    Dalhousie University Faculty of Medicine, Halifax, Nova Scotia, Canada
  • Alon Friedman
    Dalhousie University Faculty of Medicine, Halifax, Nova Scotia, Canada
  • David T Wong
    University of Toronto Temerty Faculty of Medicine, Toronto, Ontario, Canada
  • Rajeev Hemant Muni
    University of Toronto Temerty Faculty of Medicine, Toronto, Ontario, Canada
  • Footnotes
    Commercial Relationships   Ryan S. Huang None; Andrew Mihalache None; Marko Popovic PSI Foundation, Fighting Blindness , Code F (Financial Support); Colyn Munn Emagix, Code P (Patent); Yonatan Serlin Emagix, Code P (Patent); Isabela Martins Melo None; Aurora Pecaku None; Lyna Kamintsky Emagix, Code P (Patent); Alon Friedman Emagix, Code P (Patent); David Wong AbbVie, Alcon, Apellis, Bayer, Bausch Health, Biogen, Boehringer Ingelheim, Novartis, Ripple Therapeutics, Roche, Topcon, Zeiss, Code C (Consultant/Contractor), Novartis, Roche, Code F (Financial Support); Rajeev Muni Alcon, Apellis, AbbVie, Bayer, Bausch Health, Roche, Code C (Consultant/Contractor), Alcon, AbbVie, Bayer, Novartis, Roche, Code F (Financial Support)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 4391. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ryan S. Huang, Andrew Mihalache, Marko Popovic, Colyn Munn, Yonatan Serlin, Isabela Martins Melo, Aurora Pecaku, Lyna Kamintsky, Alon Friedman, David T Wong, Rajeev Hemant Muni; Prediction of Visual Acuity Response to Ranibizumab in Age-Related Macular Degeneration Using Artificial Intelligence-Based Analysis of Fluorescein Angiography. Invest. Ophthalmol. Vis. Sci. 2024;65(7):4391.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Quantification of vascular parameters from intravenous fluorescein angiography may provide insight into treatment prognosis in neovascular age-related macular degeneration (nAMD). We hypothesize that baseline blood-retinal-barrier (BRB) permeability can predict improvement in best-corrected visual acuity (BCVA) in response to ranibizumab in patients with nAMD.

Methods : A prospective cohort study was conducted at a single center in Toronto, Canada involving patients over 50 years with nAMD. At baseline, patients were imaged with fluorescein angiography using an ultra-widefield scanning laser ophthalmoscope. Images were processed using the artificial intelligence RETICAD system to extract quantitative retinal vascular parameters, including BRB permeability, perfusion, and blood flow. All nAMD patients were treated using a pro re nata regimen of ranibizumab and final outcomes were measured at 12 months of follow up. Associations between quantitative vascular parameters with functional and anatomical outcomes were examined using univariable and multivariable regression models. Receiver-operating characteristic (ROC) curves and area-under-the-curve (AUC) values were used to determine the predictive value of fluorescein angiography parameters for improvement in BCVA following treatment.

Results : The study population included 60 eyes from 60 patients with confirmed nAMD, and seven eyes from seven heathy controls. Among patients with nAMD, most were female (n=37, 61.7%), Caucasian (n=44, 73.3%), and had a mean age of 80.8 ± 8.0 years. On multivariable analysis, baseline central BRB permeability was associated with the change in BCVA from baseline to 12 months (p=0.034) and the number of injections over 12 months (p=0.003). Patients with improved BCVA had significantly lower baseline values of central (p=0.003) and peripheral (p=0.007) BRB permeability compared to those with no improvement. ROC analysis revealed baseline BRB permeability was a strong predictor of BCVA improvement (AUC=0.85).

Conclusions : Baseline quantitative fluorescein angiography parameters, particularly BRB permeability, were predictive of improvement in BCVA following ranibizumab treatment. Future work should explore associations between quantitative fluorescein angiography parameters and functional and anatomical outcomes in diverse nAMD patient populations.

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

×
×

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.

×