Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder

• Published in: Scientific reports Vol. 9; no. 1; pp. 18113 - 12
• Main Authors: Berchuck, Samuel I., Mukherjee, Sayan, Medeiros, Felipe A.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 02.12.2019; Nature Publishing Group
• Subjects: 639/705/531; 692/308/409; Aged; Glaucoma; Glaucoma - diagnosis; Glaucoma - physiopathology; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted; Middle Aged; Models, Biological; multidisciplinary; Science; Science (multidisciplinary); Visual field; Visual Field Tests - methods; Visual Fields

In this manuscript we develop a deep learning algorithm to improve estimation of rates of progression and prediction of future patterns of visual field loss in glaucoma. A generalized variational auto-encoder (VAE) was trained to learn a low-dimensional representation of standard automated perimetry...