Related Experiment Video
Updated: Feb 13, 2026
The Rodent Model of Nonarteritic Anterior Ischemic Optic Neuropathy rNAION
Published on: November 20, 2016
Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs
Zhixi Li1, Yifan He2, Stuart Keel3
1State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou 510060, China.
Purpose:
To assess the performance of a deep learning algorithm for detecting referable glaucomatous optic neuropathy (GON) based on color fundus photographs.
Design:
A deep learning system for the classification of GON was developed for automated classification of GON on color fundus photographs.
Participants:
We retrospectively included 48 116 fundus photographs for the development and validation of a deep learning algorithm.
Methods:
This study recruited 21 trained ophthalmologists to classify the photographs. Referable GON was defined as vertical cup-to-disc ratio of 0.7 or more and other typical changes of GON. The reference standard was made until 3 graders achieved agreement. A separate validation dataset of 8000 fully gradable fundus photographs was used to assess the performance of this algorithm.
Main Outcome Measures:
The area under receiver operator characteristic curve (AUC) with sensitivity and specificity was applied to evaluate the efficacy of the deep learning algorithm detecting referable GON.
Results:
In the validation dataset, this deep learning system achieved an AUC of 0.986 with sensitivity of 95.6% and specificity of 92.0%. The most common reasons for false-negative grading (n = 87) were GON with coexisting eye conditions (n = 44 [50.6%]), including pathologic or high myopia (n = 37 [42.6%]), diabetic retinopathy (n = 4 [4.6%]), and age-related macular degeneration (n = 3 [3.4%]). The leading reason for false-positive results (n = 480) was having other eye conditions (n = 458 [95.4%]), mainly including physiologic cupping (n = 267 [55.6%]). Misclassification as false-positive results amidst a normal-appearing fundus occurred in only 22 eyes (4.6%).
Conclusions:
A deep learning system can detect referable GON with high sensitivity and specificity. Coexistence of high or pathologic myopia is the most common cause resulting in false-negative results. Physiologic cupping and pathologic myopia were the most common reasons for false-positive results.
Related Concept Videos
03:02Colors and Magnetism
When atoms or molecules absorb light at the proper frequency, their electrons are excited to higher-energy orbitals. For many main group atoms and molecules, the absorbed photons are in the ultraviolet range of the electromagnetic spectrum, which cannot be detected by the human eye. For coordination compounds, the energy difference between the d orbitals often allows photons in the visible range to be absorbed and emitted, which is seen as colors by the human...
01:24Color Vision
01:29Self-Efficacy
01:14Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
01:27Associative Learning
Classical conditioning, also known...
01:22Purposive Learning