Related Experiment Video
Updated: Jan 23, 2026
07:22
Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
Published on: March 11, 2016
11.9K
Evaluation of a Deep Learning System For Identifying Glaucomatous Optic Neuropathy Based on Color Fundus Photographs
Lama A Al-Aswad1, Rahul Kapoor1, Chia Kai Chu1
1Columbia University Medical Center, Harkness Eye Institute, New York, NY.
Journal of Glaucoma
|June 25, 2019
Summary
A deep learning system, Pegasus, demonstrated superior diagnostic performance in identifying glaucomatous optic neuropathy compared to most ophthalmologists. Its high sensitivity and speed make it a promising tool for screening this condition.
Area of Science:
- Ophthalmology
- Artificial Intelligence
- Medical Diagnostics
Background:
- Glaucomatous optic neuropathy is a leading cause of irreversible blindness.
- Accurate and timely diagnosis is crucial for effective management and prevention of vision loss.
- Current diagnostic methods rely on expert interpretation of fundus photographs, which can be time-consuming and subject to inter-observer variability.
Purpose of the Study:
- To evaluate the diagnostic performance of a deep learning system named Pegasus for identifying glaucomatous optic neuropathy.
- To compare the performance of Pegasus against a panel of ophthalmologists and a consensus group.
Main Methods:
- A retrospective study involving 110 color fundus photographs from the Singapore Malay Eye Study.
- Six ophthalmologists and the Pegasus deep learning system graded the photographs.
- Performance was assessed using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC), compared against a gold standard diagnosis.
Main Results:
- Pegasus achieved an AUROC of 92.6%, outperforming 5 of 6 ophthalmologists (AUROCs 69.6%-84.9%) and the "best case" consensus (89.1%).
- Pegasus demonstrated high sensitivity (83.7%) and specificity (88.2%), with perfect intraobserver agreement (1.00).
- The deep learning system operated approximately 10 times faster than the ophthalmologists.
Conclusions:
- The Pegasus deep learning system shows comparable or superior diagnostic performance to ophthalmologists in identifying glaucomatous optic neuropathy.
- Pegasus's high sensitivity and efficiency suggest its potential as a valuable screening tool.
- Further validation with larger patient cohorts is warranted.
Related Concept Videos
03:02Colors and Magnetism
14.0K
Color in Coordination Complexes
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...
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...
14.0K
01:24Color Vision
1.4K
Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.
1.4K
01:14Avoidance Learning and Learned Helplessness
2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
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...
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...
2.5K
01:25Learning Disabilities
580
Learning disabilities are cognitive disorders caused by neurological impairments that affect cognitive functions like language and reading, without indicating overall intellectual or developmental challenges. These disabilities differ from global intellectual or developmental disabilities as they are limited to distinct cognitive functions. Common learning disabilities include dysgraphia, dyslexia, and dyscalculia, each of which impacts unique aspects of learning.
Dyslexia
Dyslexia is a...
Dyslexia
Dyslexia is a...
580
01:27Associative Learning
1.3K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
1.3K
01:22Purposive Learning
453
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
453