A new platform designed for glaucoma screening: identifying the risk of glaucomatous optic neuropathy using fundus photography with deep learning architecture together with intraocular pressure measurements

In this report, we describe a particular condition of a 52-year-old man who showed advanced bilateral glaucomatous-like optic disc damage, even though the intraocular pressure resulted normal during all examinations performed. Visual field test, steady-state pattern electroretinogram, retinal nerve fiber layer and retinal tomographic evaluations were performed to evaluate the optic disc damage. Over a 4-year observational period, his visual acuity decreased to 12/20 in the right eye and counting fingers in the left eye. Visual fields were severely compromised, and intraocular pressure values were not superior to 14 mm Hg during routine examinations. An accurate anamnesis and the suspicion of this disease represent a crucial aspect to establish the correct diagnosis. In fact, our patient strongly rubbed his eyes for more than 10 h per day. Recurrent and continuous eye rubbing can induce progressive optic neuropathy, causing severe visual field damage similar to the pathology of advanced glaucoma.

Download Full-text

Intraocular Pressure and Glaucomatous Optic Neuropathy in High Myopia

Investigative Opthalmology & Visual Science ◽

10.1167/iovs.17-21942 ◽

2017 ◽

Vol 58 (13) ◽

pp. 5897 ◽

Cited By ~ 18

Author(s):

Jost B. Jonas ◽

Natsuko Nagaoka ◽

Yu Xin Fang ◽

Pascal Weber ◽

Kyoko Ohno-Matsui

Keyword(s):

Intraocular Pressure ◽

Optic Neuropathy ◽

High Myopia ◽

Glaucomatous Optic Neuropathy

Download Full-text

Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography

British Journal of Ophthalmology ◽

10.1136/bjophthalmol-2020-316290 ◽

2021 ◽

pp. bjophthalmol-2020-316290

Author(s):

Bing Li ◽

Huan Chen ◽

Bilei Zhang ◽

Mingzhen Yuan ◽

Xuemin Jin ◽

...

Keyword(s):

Deep Learning ◽

Learning System ◽

Age Related Macular Degeneration ◽

Fundus Photography ◽

Glaucomatous Optic Neuropathy ◽

Test Set ◽

Receiver Operating Characteristic Curves ◽

Age Related ◽

Test Sets ◽

External Test

AimTo explore and evaluate an appropriate deep learning system (DLS) for the detection of 12 major fundus diseases using colour fundus photography.MethodsDiagnostic performance of a DLS was tested on the detection of normal fundus and 12 major fundus diseases including referable diabetic retinopathy, pathologic myopic retinal degeneration, retinal vein occlusion, retinitis pigmentosa, retinal detachment, wet and dry age-related macular degeneration, epiretinal membrane, macula hole, possible glaucomatous optic neuropathy, papilledema and optic nerve atrophy. The DLS was developed with 56 738 images and tested with 8176 images from one internal test set and two external test sets. The comparison with human doctors was also conducted.ResultsThe area under the receiver operating characteristic curves of the DLS on the internal test set and the two external test sets were 0.950 (95% CI 0.942 to 0.957) to 0.996 (95% CI 0.994 to 0.998), 0.931 (95% CI 0.923 to 0.939) to 1.000 (95% CI 0.999 to 1.000) and 0.934 (95% CI 0.929 to 0.938) to 1.000 (95% CI 0.999 to 1.000), with sensitivities of 80.4% (95% CI 79.1% to 81.6%) to 97.3% (95% CI 96.7% to 97.8%), 64.6% (95% CI 63.0% to 66.1%) to 100% (95% CI 100% to 100%) and 68.0% (95% CI 67.1% to 68.9%) to 100% (95% CI 100% to 100%), respectively, and specificities of 89.7% (95% CI 88.8% to 90.7%) to 98.1% (95%CI 97.7% to 98.6%), 78.7% (95% CI 77.4% to 80.0%) to 99.6% (95% CI 99.4% to 99.8%) and 88.1% (95% CI 87.4% to 88.7%) to 98.7% (95% CI 98.5% to 99.0%), respectively. When compared with human doctors, the DLS obtained a higher diagnostic sensitivity but lower specificity.ConclusionThe proposed DLS is effective in diagnosing normal fundus and 12 major fundus diseases, and thus has much potential for fundus diseases screening in the real world.

Download Full-text

Predicting glaucoma prior to its onset using deep learning

10.1101/828681 ◽

2019 ◽

Author(s):

Anshul Thakur ◽

Michael Goldbaum ◽

Siamak Yousefi

Keyword(s):

Deep Learning ◽

Visual Field ◽

Optic Neuropathy ◽

Disease Onset ◽

Visual Fields ◽

Learning Model ◽

Glaucomatous Optic Neuropathy ◽

Learning Models ◽

Fundus Photographs ◽

Deep Learning Model

AbstractPurposeTo assess the accuracy of deep learning models to predict glaucoma development from fundus photographs several years prior to disease onset.DesignA deep learning model for prediction of glaucomatous optic neuropathy or visual field abnormality from color fundus photographs.ParticipantsWe retrospectively included 66,721 fundus photographs from 3,272 eyes of 1,636 subjects to develop deep leaning models.MethodFundus photographs and visual fields were carefully examined by two independent readers from the optic disc and visual field reading centers of the ocular hypertension treatment study (OHTS). When an abnormality was detected by the readers, subject was recalled for re-testing to confirm the abnormality and further confirmation by an endpoint committee. Using OHTS data, deep learning models were trained and tested using 85% of the fundus photographs and further validated (re-tested) on the remaining (held-out) 15% of the fundus photographs.Main Outcome MeasuresAccuracy and area under the receiver-operating characteristic curve (AUC).ResultsThe AUC of the deep learning model in predicting glaucoma development 4-7 years prior to disease onset was 0.77 (95% confidence interval 0.75, 0.79). The accuracy of the model in predicting glaucoma development about 1-3 years prior to disease onset was 0.88 (0.86, 0.91). The accuracy of the model in detecting glaucoma after onset was 0.95 (0.94, 0.96).ConclusionsDeep learning models can predict glaucoma development prior to disease onset with reasonable accuracy. Eyes with visual field abnormality but not glaucomatous optic neuropathy had a higher tendency to be missed by deep learning algorithms.

Download Full-text

Reduction of Intraocular Pressure and Glaucoma Progression

50 Studies Every Ophthalmologist Should Know ◽

10.1093/med/9780190050726.003.0014 ◽

2020 ◽

pp. 79-84

Author(s):

Alan D. Penman ◽

Kimberly W. Crowder ◽

William M. Watkins

Keyword(s):

Intraocular Pressure ◽

Optic Neuropathy ◽

Open Angle Glaucoma ◽

Controlled Clinical Trial ◽

Glaucomatous Optic Neuropathy ◽

Delayed Treatment ◽

Lowering Therapy ◽

Risk Of Progression ◽

Modest Reduction

The Early Manifest Glaucoma Trial (EMGT) was a randomized, placebo-controlled clinical trial in patients with newly detected, previously untreated, primary open-angle glaucoma (POAG) to determine whether immediate institution of intraocular pressure (IOP)–lowering therapy reduces the risk of progression compared to delayed treatment or observation. The study showed that IOP-lowering therapy offered a definitive benefit in patients with early glaucoma by delaying progression of glaucomatous optic neuropathy, especially in eyes with higher IOPs (>21 mm Hg) at baseline. Even modest reduction in IOP decreased the risk of progression. However, a large percentage of treated eyes still showed progression during follow-up. The progression of glaucomatous optic neuropathy was highly variable and difficult to predict for an individual patient.

Download Full-text

Considerations When Using a Deep Learning System to Diagnose Glaucomatous Optic Neuropathy

JAMA Ophthalmology ◽

10.1001/jamaophthalmol.2020.0023 ◽

2020 ◽

Vol 138 (4) ◽

pp. 419

Author(s):

Lin Sun

Keyword(s):

Deep Learning ◽

Optic Neuropathy ◽

Learning System ◽

Glaucomatous Optic Neuropathy

Download Full-text

Steroid glaucoma

Clinical Medicine (Russian Journal) ◽

10.30629/0023-2149-2021-99-7-8-420-428 ◽

2022 ◽

Vol 99 (7-8) ◽

pp. 420-428

Author(s):

A. M. Nagornova ◽

A. V. Seleznеv ◽

I. A. Bulakh ◽

A. Yu. Brezhnev ◽

A. V. Kuroyedov

Keyword(s):

Intraocular Pressure ◽

Ocular Hypertension ◽

Optic Neuropathy ◽

Clinical Picture ◽

Pressure Level ◽

Glaucomatous Optic Neuropathy ◽

Proven Case

Glucocorticosteroids are widely used in clinical and ophthalmic practice, but their unjustifi ed and uncontrollable use is unacceptable. Prescription of steroids has to be controlled strictly and the level of intraocular pressure must be diagnosed, because one of the signifi cant side eff ect of steroids is increased intraocular pressure level and, as a result, the development of glaucomatous optic neuropathy. This review deals with the pathogenesis of an increase in the level of intraocular pressure against various forms of glucocorticosteroids intake, describes the time and duration of their ocular-hypertensive eff ect. The available data on the features of the clinical picture of steroid glaucoma, depending on the routes of their entry, have been studied in detail. The tactics of treating patients with ocular hypertension or a proven case of steroid glaucoma are described.

Download Full-text

Ocular Hypertension: A Review And Evidence-Based Roadmap

Canadian Journal of Optometry ◽

10.15353/cjo.79.442 ◽

2017 ◽

Vol 79 (1) ◽

pp. 17

Author(s):

Andrew John Rixon

Keyword(s):

Risk Factor ◽

Intraocular Pressure ◽

Ocular Hypertension ◽

Optic Neuropathy ◽

Daily Practice ◽

Modifiable Risk Factor ◽

Glaucomatous Optic Neuropathy ◽

Study Group ◽

Evidence Based ◽

Management Decisions

Increased intraocular pressure is arguably the most important, and currently the only modifiable, risk factor for glaucomatous optic neuropathy. Ocular hypertension is often encountered by clinicians in daily practice and is expected to be seen with increasing frequency as the population ages. Awareness and understanding of the extensive research performed on this subject, with particular focus on the work of the Ocular Hypertension Study Group, are critical for comprehensively assessing the risk of conversion to glaucoma. Although management decisions can be complex, they can be aptly handled by the well-informed optometrist in consultation with their patients.

Download Full-text

Association of peripheral anterior synechia, intraocular pressure, and glaucomatous optic neuropathy in primary angle-closure diseases

International Journal of Ophthalmology ◽

10.18240/ijo.2021.10.09 ◽

2021 ◽

Vol 14 (10) ◽

pp. 1533-1538

Author(s):

Ming Zhang ◽

◽

Cong Ye ◽

Su-Jie Fan ◽

Yuan-Bo Liang ◽

...

Keyword(s):

Intraocular Pressure ◽

Optic Neuropathy ◽

Estimating Equation ◽

Angle Closure ◽

Independent Effect ◽

Generalized Estimating Equation ◽

Glaucomatous Optic Neuropathy ◽

Spherical Equivalent ◽

Primary Angle Closure ◽

Primary Angle Closure Glaucoma

AIM: To investigate the association of peripheral anterior synechiae (PAS) with intraocular pressure (IOP) and glaucomatous optic neuropathy (GON) in primary angle closure (PAC) and primary angle-closure glaucoma (PACG). METHODS: Totally 355 eyes (238 PAC and 117 PACG) of 181 patients were included in this retrospective analysis of baseline data from a randomized clinical trial. All patients had undergone a comprehensive ophthalmic examination. The extent of PAS in clock hours as determined on gonioscopy was documented. The independent effect of the extent of PAS on IOP and the prevalence of GON were determined using multivariable generalized estimating equation (GEE) models. RESULTS: The frequency of GON increased with the extent of PAS and a higher IOP. PAS were more extensive (8 vs 1 clock hour, P<0.001) and IOP higher (28.01 vs 18.00 mm Hg, P<0.001) in PACG compared to PAC. The prevalence of GON among the PAS quartiles were 10.2% (PAS<0.5 clock hours), 16.9% (PAS≥0.5 and PAS<3 clock hours), 29.6% (PAS≥3 and PAS<7 clock hours), and 74.4% (PAS≥7 clock hours), respectively. After adjusting for IOP, age, gender, spherical equivalent, average Shaffer score and number of medications, the odds ratio (OR) for GON was 4.4 (95%CI: 1.5-13.0; P=0.007) with PAS≥3 clock hours and 13.8 (95%CI: 4.3-43.6; P<0.001) with PAS≥7 clock hours as compared to eyes with PAS<0.5 clock hours. The frequency of GON increased linearly with the extent of PAS. Extent of PAS was also associated with higher IOP. Eyes with both PAS≥6 clock hours and IOP≥21 mm Hg had the highest risk of GON compared to eyes with both PAS<6 clock hours and IOP<21 mm Hg (OR=18.0, 95%CI: 7.5-43.4; P<0.001). CONCLUSION: The extent of PAS in PAC and PACG is an important predictor of higher IOP and is linearly associated with GON independent of IOP, suggesting other factors related to PAS formation may be involved in the development of GON in PACG.

Download Full-text