Accurate, fast, data efficient and interpretable glaucoma diagnosis with automated spatial analysis of the whole cup to disc profile.

Ian J C MacCormickBryan M WilliamsYalin ZhengKun LiBaidaa Al-BanderSilvester CzannerRob CheesemanColin Eric WilloughbyEmery N BrownGeorge L SpaethGabriela Czanner

Published in: PloS one (2019)

The spatial probabilistic algorithm is highly accurate, highly data efficient and it extends to any imaging hardware in which the boundaries of cup and disc can be segmented, thus making the algorithm particularly applicable to research into disease mechanisms, and also glaucoma screening in low resource settings.

Keyphrases

machine learning
deep learning
high resolution
big data
electronic health record
optic nerve
artificial intelligence
high throughput
data analysis
optical coherence tomography