Objective: To compare the diagnostic performance of an artificial intelligence deep learning system with that of expert neuro-ophthalmologists in classifying optic disc appearance.
Methods: The deep learning system was previously trained and validated on 14,341 ocular fundus photographs from 19 international centers. The performance of the system was evaluated on 800 new fundus photographs (400 normal optic discs, 201 papilledema [disc edema from elevated intracranial pressure], 199 other optic disc abnormalities) and compared with that of 2 expert neuro-ophthalmologists who independently reviewed the same randomly presented images without clinical information. Area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were calculated.
Results: The system correctly classified 678 of 800 (84.7%) photographs, compared with 675 of 800 (84.4%) for Expert 1 and 641 of 800 (80.1%) for Expert 2. The system yielded areas under the receiver operating characteristic curve of 0.97 (95% confidence interval [CI] = 0.96-0.98), 0.96 (95% CI = 0.94-0.97), and 0.89 (95% CI = 0.87-0.92) for the detection of normal discs, papilledema, and other disc abnormalities, respectively. The accuracy, sensitivity, and specificity of the system's classification of optic discs were similar to or better than the 2 experts. Intergrader agreement at the eye level was 0.71 (95% CI = 0.67-0.76) between Expert 1 and Expert 2, 0.72 (95% CI = 0.68-0.76) between the system and Expert 1, and 0.65 (95% CI = 0.61-0.70) between the system and Expert 2.
Interpretation: The performance of this deep learning system at classifying optic disc abnormalities was at least as good as 2 expert neuro-ophthalmologists. Future prospective studies are needed to validate this system as a diagnostic aid in relevant clinical settings. ANN NEUROL 2020;88:785-795.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/ana.25839 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Ruthenium-106 brachytherapy and central uveal melanoma.
Int Ophthalmol
January 2025
Department of Ophthalmology, Staedtisches Klinikum Dessau, Brandenburg Medical School Theodor Fontane, Dessau, Germany.
Purpose: Uveal melanoma (UM) is the most common primary ocular malignancy. The size and location of the tumor are decisive for brachytherapy with the β-emitting ruthenium-106 (Ru-106) plaque. The treatment of juxtapapillary and juxtafoveolar UM may be challenging because of the proximity or involvement of the macula and optic nerve and high recurrence rates.
View Article and Find Full Text PDFLong-Term Effects of COVID-19 on Optic Disc and Retinal Microvasculature Assessed by Optical Coherence Tomography Angiography.
Diagnostics (Basel)
January 2025
Department of Ophthalmology, Haseki Training and Research Hospital, 34096 Istanbul, Turkey.
: To evaluate the long-term effects of coronavirus disease (COVID-19) on optic disc and macular microvasculature. : 40 post-COVID-19 and 40 healthy subjects were included. Optical coherence tomography angiography (OCTA) was performed for all subjects at the first visit and repeated in the fourth and twelfth months.
View Article and Find Full Text PDFRetinal ganglion cells encode the direction of motion outside their classical receptive field.
Proc Natl Acad Sci U S A
January 2025
Department of Brain Sciences, Weizmann Institute of Science, Rehovot 7610001, Israel.
Retinal ganglion cells (RGCs) typically respond to light stimulation over their spatially restricted receptive field. Using large-scale recordings in the mouse retina, we show that a subset of non- direction-selective (DS) RGCs exhibit asymmetric activity, selective to motion direction, in response to a stimulus crossing an area far beyond the classic receptive field. The extraclassical response arises via inputs from an asymmetric distal zone and is enhanced by desensitization mechanisms and an inherent DS component, creating a network of neurons responding to motion toward the optic disc.
View Article and Find Full Text PDFGlaucoma Screening and Referral Risk Factors in a High-Risk Population: Follow-up Study of the Manhattan Vision Screening Study (NYC-SIGHT).
J Glaucoma
November 2024
Columbia University, Department of Ophthalmology, Vagelos College of Physicians and Surgeons, 630 W. 168th Street, New York, NY 10032.
Prcis: Community-based eye health screenings that incorporated fundus photography and optometric exams in a high-risk NYC population effectively identified a higher than average number of participants that required an in-office glaucoma evaluation.
Purpose: To report glaucoma screening rates and risk factors associated with referral for in-office glaucoma evaluation in the Manhattan Vision Screening and Follow-up Study (NYC-SIGHT).
Methods: In this 5-year, cluster-randomized clinical trial, eligible individuals aged 40 and older were recruited from affordable housing developments and senior centers.
Black posterior vitreous detachment: A 10-year historical cohort of pigmented uveal tumors.
Heliyon
January 2025
Faculty of Medical and Health Sciences, Tel Aviv University, Israel.
Objective: Pigmentary posterior vitreous detachment (PVD), referred to as "black PVD," is a rare entity describing PVD along with pigment dispersion in the vitreous. There are a few case reports describing pigmentary PVD, yet the association between pigmentary PVD and uveal and optic disc tumors was not described before. The aim of this study was to report the clinical features of patients with pigmentary PVD associated with these tumors.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!