June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Deep reinforcement learning for optimized visual field analysis
Author Affiliations & Notes
  • Yudong Tao
    Electrical and Computer Engineering, University of Miami, Coral Gables, Florida, United States
    University of Miami Health System Bascom Palmer Eye Institute, Miami, Florida, United States
  • Mohamed Khodeiry
    University of Miami Health System Bascom Palmer Eye Institute, Miami, Florida, United States
  • Rui Ma
    Electrical and Computer Engineering, University of Miami, Coral Gables, Florida, United States
  • Karam Alawa
    Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, Iowa, United States
  • Ximena Mendoza
    University of Miami Health System Bascom Palmer Eye Institute, Miami, Florida, United States
  • Xiangxiang Liu
    University of Miami Health System Bascom Palmer Eye Institute, Miami, Florida, United States
  • Mei-Ling Shyu
    Electrical and Computer Engineering, University of Miami, Coral Gables, Florida, United States
  • Richard K Lee
    University of Miami Health System Bascom Palmer Eye Institute, Miami, Florida, United States
  • Footnotes
    Commercial Relationships   Yudong Tao, None; Mohamed Khodeiry, None; Rui Ma, None; Karam Alawa, None; Ximena Mendoza, None; Xiangxiang Liu, None; Mei-Ling Shyu, None; Richard Lee, None
  • Footnotes
    Support  NIH Center Core Grant P30EY014801, a Research to Prevent Blindness Unrestricted Grant, and Walter G. Ross Foundation
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 1008. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Yudong Tao, Mohamed Khodeiry, Rui Ma, Karam Alawa, Ximena Mendoza, Xiangxiang Liu, Mei-Ling Shyu, Richard K Lee; Deep reinforcement learning for optimized visual field analysis. Invest. Ophthalmol. Vis. Sci. 2021;62(8):1008.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Existing visual field testing algorithms rely on manually crafted rules to determine the contrast sensitivity of a light stimulus at each step as well as the stopping criterion, which is suboptimal in terms of testing accuracy and speed. We developed and tested a deep reinforcement learning (DRL)-based visual field testing algorithm that achieves greater performance gain in terms of testing accuracy, speed, and robustness than the Zippy Estimation by Sequential Testing (ZEST) algorithm.

Methods : Our algorithm formulates the procedure of white-on-white static automated perimetry (SAP) as a reinforcement learning problem, with the perimeter modeled as an intelligent agent that could interact with the patient. At each step, the agent can choose to present a stimulus with a specific intensity to the patient or activate a stop signal to end the test and predict the sensitivity. By training the agent on our visual field dataset with 275 normal and 433 glaucomatous visual fields, a new rule is learned by the agent. This rule can guide the agent to perform a series of optimized actions in each test, which leads to the highest testing accuracy with the fewest number of stimuli presentations.

Results : The proposed algorithm was evaluated on both synthetic datasets and our patient visual field dataset under different prior distributions. Experimental results show that our algorithm is 9.4% faster and 5.6% more accurate than ZEST (p = 0.025). Meanwhile, our algorithm can generalize better than ZEST when the distribution of testing data is different from the initial distribution.

Conclusions : Our results demonstrate that our DRL-based visual field testing algorithm performs better than ZEST. By maintaining higher accuracy with reduced testing time, our algorithm increases clinic efficiency, improves patient satisfaction, and improves testing results with less patient fatigue. Moreover, the improved generalization ability our algorithm ensures test reliability and robustness of our algorithm.

This is a 2021 ARVO Annual Meeting abstract.

×
×

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.

×