Abstract
Presentation Description :
Structural (disc photos and/or optical coherence tomography) and functional (standard automated perimetry) tests are typically employed to help clinicians diagnose glaucoma. However, the interpretation of their results is often subjective and lacks a reference standard. Machine learning and deep learning have recently been used to improve the objectivity and repeatability of methods to diagnose glaucoma based upon structural and functional tests. In this talk we will discuss some of these methods, their strengths and limitations, as well as future directions on how to improve their performance in a real-world clinical setting.
This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.