June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Deep learning prediction of 24-2 visual field map using en-face OCT-Angiography microvascular images in glaucoma
Author Affiliations & Notes
  • Alireza Kamalipour
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Sasan Moghimi
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Pooya Khosravi
    University of California Irvine, Irvine, California, United States
  • Takashi Nishida
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Cristiana Vasile
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Michael Saheb Kashaf
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Jo-Hsuan Wu
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Eleonora Micheletti
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Gopikasree Gunasegaran
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Golnoush Mahmoudinezhad
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Evan Walker
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Elizabeth Li
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Kelvin Du
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Mark Christopher
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Linda M Zangwill
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Robert N Weinreb
    Ophthalmology, University of California San Diego, La Jolla, California, United States
  • Footnotes
    Commercial Relationships   Alireza Kamalipour Fight for Sight Foundation, Code F (Financial Support); Sasan Moghimi National Eye Institute, Code F (Financial Support), University of California Tobacco-Related Disease Research Program, Code F (Financial Support); Pooya Khosravi None; Takashi Nishida Topcon, Code C (Consultant/Contractor); Cristiana Vasile None; Michael Saheb Kashaf None; Jo-Hsuan Wu None; Eleonora Micheletti None; Gopikasree Gunasegaran None; Golnoush Mahmoudinezhad None; Evan Walker None; Elizabeth Li None; Kelvin Du None; Mark Christopher National Eye Institute, Code F (Financial Support); Linda Zangwill Abbvie Inc. Topcon, Code C (Consultant/Contractor), National Eye Institute, Code F (Financial Support), Carl Zeiss Meditec Inc., Code F (Financial Support), Heidelberg Engineering GmbH, Code F (Financial Support), Optovue Inc., Code F (Financial Support), Topcon Medical Systems Inc., Code F (Financial Support), Zeiss Meditec, AiSight Health, Code P (Patent); Robert Weinreb Abbvie, Aerie Pharmaceuticals, Allergan, Amydis, Equinox, Eyenovia, Iantrek, IOPtic, Implandata, Nicox, and Topcon, Code C (Consultant/Contractor), National Eye Institute, Code F (Financial Support), Heidelberg Engineering, Code F (Financial Support), Carl Zeiss Meditec, Code F (Financial Support), Konan Medical, Code F (Financial Support), Optovue, Code F (Financial Support), Zilia, Centervue, and Topcon, Code F (Financial Support), Toromedes, Carl Zeiss Meditec., Code P (Patent)
  • Footnotes
    Support  Fight for Sight foundation, National Eye Institute R01EY029058, R01EY034148, R01EY11008, R01EY19869, R01EY027510, R01EY026574, R21EY031125, EY018926, EY14267, K99EY030942, P30EY022589, University of California Tobacco-Related Disease Research Program T31IP1511, and an unrestricted grant from Research to Prevent Blindness (New York, NY).
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 1309. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Alireza Kamalipour, Sasan Moghimi, Pooya Khosravi, Takashi Nishida, Cristiana Vasile, Michael Saheb Kashaf, Jo-Hsuan Wu, Eleonora Micheletti, Gopikasree Gunasegaran, Golnoush Mahmoudinezhad, Evan Walker, Elizabeth Li, Kelvin Du, Mark Christopher, Linda M Zangwill, Robert N Weinreb; Deep learning prediction of 24-2 visual field map using en-face OCT-Angiography microvascular images in glaucoma. Invest. Ophthalmol. Vis. Sci. 2023;64(8):1309.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop deep learning models to predict the severity and pointwise patterns of 24-2 visual field (VF) damage in glaucoma using optic nerve head (ONH) and macular OCT-Angiography (OCTA) images.

Methods : This study included 3990 OCTA (1850 ONH, 2140 macula)-VF pairs from 465 Diagnostic Innovations in Glaucoma Study (DIGS) participants (842 eyes). Deep learning models were developed to predict individual 24-2 sensitivity thresholds using en-face ONH and macular OCTA images. Visual field indices, including mean deviation (MD), pattern standard deviation (PSD), and pointwise total deviation values, were then generated using the predicted sensitivity thresholds. The models' accuracy was evaluated using mean absolute error (MAE) and Pearson's correlation coefficient (r) and compared to linear regression (LR) models. An external independent dataset of 1394 clinic patients (2436 eyes) including 6227 OCTA (2033 ONH, 4194 macula)-VF pairs was used to evaluate the models' generalizability.

Results : The ONH deep learning models’ predictions had the respective MAE of 2.23 dB and r of 0.83 for MD and 2.59 dB and 0.78 for PSD. The MAE and r for the clinic dataset were 2.69 dB and 0.78 for MD and 2.50 dB, and 0.74 for PSD. The macular deep learning models had an MAE of 2.15 dB, an r of 0.78 for MD and 2.29 dB, and 0.68 for PSD. The respective MAE and r for the clinic dataset were 2.85 dB and 0.69 for MD and 2.62 dB and 0.69 for PSD (Figure 1). All investigated models significantly improved global and pointwise estimates of VF prediction compared to their respective LR models (P < 0.05).

Conclusions : Deep learning models can predict the severity and patterns of functional loss based on OCTA images. Artificial intelligence methods that accurately estimate the severity and patterns of glaucomatous functional loss from microvascular structure show promise in reducing the time and costs of VF testing, individualizing the frequency and test strategies of VF assessment, and preventing the development of irreversible blindness associated with the disease.

This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.

 

Figure 1. Models’ performance for the prediction of 24-2 visual field maps based on different image inputs (top: optic nerve head [ONH], bottom: macula) and test sets (left: DIGS, right: Clinic). Scatterplots demonstrate the relationship between models’ predictions and actual mean deviation values. DL: deep learning, LR: linear regression.

Figure 1. Models’ performance for the prediction of 24-2 visual field maps based on different image inputs (top: optic nerve head [ONH], bottom: macula) and test sets (left: DIGS, right: Clinic). Scatterplots demonstrate the relationship between models’ predictions and actual mean deviation values. DL: deep learning, LR: linear regression.

×
×

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.

×