Related Experiment Video
Updated: Jun 18, 2025
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
A Deep Learning Approach for Accurate Discrimination Between Optic Disc Drusen and Papilledema on Fundus Photographs
Kanchalika Sathianvichitr1, Raymond P Najjar, Tang Zhiqun
1Singapore Eye Research Institute (KS, RPN, TZ, DM), Singapore, Singapore; Duke-NUS Medical School (RPN, MJAG, DM), National University of Singapore, Singapore, Singapore; Department of Ophthalmology (RPN), Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore; Departments of Clinical Neurological Sciences and Ophthalmology (JAF), Western University, London, Canada; Department of Neuro-Ophthalmology (CWLY, DM), Singapore National Eye Centre, Singapore, Singapore; Ophthalmic Engineering & Innovation Laboratory (MJAG), Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore; Institute for Molecular and Clinical Ophthalmology (MJAG), Basel, Switzerland; Departments of Clinical Neurosciences and Surgery (FC), University of Calgary, Calgary, Canada; Department of Medicine (MYL), Emory University School of Medicine, Atlanta, Georgia; Department of Ophthalmology (MYL, NJN, VB), Emory Eye Center, Emory University School of Medicine, Atlanta, Georgia; Eye Center (WAL), Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; Save Sight Institute (CLF), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia; Department of Ophthalmology (SH, DM), Rigshospitalet, University of Copenhagen, Copenhagen, Denmark; Department of Neurology (NJN, VB), Emory University School of Medicine, Atlanta, Georgia; Department of Neurological Surgery (NJN), Emory University School of Medicine, Atlanta, Georgia; and Rothschild Foundation Hospital (CV-C, DM), Paris, France.
Background:
Optic disc drusen (ODD) represent an important differential diagnosis of papilledema caused by intracranial hypertension, but their distinction may be difficult in clinical practice. The aim of this study was to train, validate, and test a dedicated deep learning system (DLS) for binary classification of ODD vs papilledema (including various subgroups within each category), on conventional mydriatic digital ocular fundus photographs collected in a large international multiethnic population.
Methods:
This retrospective study included 4,508 color fundus images in 2,180 patients from 30 neuro-ophthalmology centers (19 countries) participating in the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI) Group. For training and internal validation, we used 857 ODD images and 3,230 papilledema images, in 1,959 patients. External testing was performed on an independent data set (221 patients), including 207 images with ODD (96 visible and 111 buried), provided by 3 centers of the Optic Disc Drusen Studies Consortium, and 214 images of papilledema (92 mild-to-moderate and 122 severe) from a previously validated study.
Results:
The DLS could accurately distinguish between all ODD and papilledema (all severities included): area under the receiver operating characteristic curve (AUC) 0.97 (95% confidence interval [CI], 0.96-0.98), accuracy 90.5% (95% CI, 88.0%-92.9%), sensitivity 86.0% (95% CI, 82.1%-90.1%), and specificity 94.9% (95% CI, 92.3%-97.6%). The performance of the DLS remained high for discrimination of buried ODD from mild-to-moderate papilledema: AUC 0.93 (95% CI, 0.90-0.96), accuracy 84.2% (95% CI, 80.2%-88.6%), sensitivity 78.4% (95% CI, 72.2%-84.7%), and specificity 91.3% (95% CI, 87.0%-96.4%).
Conclusions:
A dedicated DLS can accurately distinguish between ODD and papilledema caused by intracranial hypertension, even when considering buried ODD vs mild-to-moderate papilledema.
