Search

Timely diagnosis of eye diseases is paramount to obtaining the best treatment outcomes. OCT and OCT angiography (OCTA) have several advantages that lend themselves to early detection of ocular pathology; furthermore, the techniques produce large, feature-rich data volumes. However, the full clinical potential of both OCT and OCTA is stymied when complex data acquired using the techniques must be manually processed. Here, we propose an automated diagnostic framework based on structural OCT and OCTA data volumes that could substantially support the clinical application of these technologies.Cross sectional study.Five hundred twenty-six OCT and OCTA volumes were scanned from the eyes of 91 healthy participants, 161 patients with diabetic retinopathy (DR), 95 patients with age-related macular degeneration (AMD), and 108 patients with glaucoma.The diagnosis framework was constructed based on semisequential 3-dimensional (3D) convolutional neural networks. The trained framework classifies combined structural OCT and OCTA scans as normal, DR, AMD, or glaucoma. Fivefold cross-validation was performed, with 60% of the data reserved for training, 20% for validation, and 20% for testing. The training, validation, and test data sets were independent, with no shared patients. For scans diagnosed as DR, AMD, or glaucoma, 3D class activation maps were generated to highlight subregions that were considered important by the framework for automated diagnosis.The area under the curve (AUC) of the receiver operating characteristic curve and quadratic-weighted kappa were used to quantify the diagnostic performance of the framework.For the diagnosis of DR, the framework achieved an AUC of 0.95 ± 0.01. For the diagnosis of AMD, the framework achieved an AUC of 0.98 ± 0.01. For the diagnosis of glaucoma, the framework achieved an AUC of 0.91 ± 0.02.Deep learning frameworks can provide reliable, sensitive, interpretable, and fully automated diagnosis of eye diseases.Proprietary or commercial disclosure may be found after the references.

PURPOSE: To compare retinal vessel density in eyes with geographic atrophy (GA) secondary to age-related macular degeneration (AMD) to age-matched healthy eyes using projection-resolved optical coherence tomography angiography (PR-OCTA). DESIGN: Prospective cross-sectional study. METHODS: Study participants underwent macular 3×3-mm OCTA scans with spectral domain OCTA. Reflectance-compensated retinal vessel densities were calculated on projection-resolved superficial vascular complex (SVC), intermediate capillary plexus (ICP), and deep capillary plexus (DCP). Quantitative analysis using normalized deviation compared the retinal vessel density in GA regions, 500 μm GA rim regions, and non-GA regions to similar macular locations in control eyes. RESULTS: Ten eyes with GA and 10 control eyes were studied. Eyes with GA had significantly lower vessel density in the SVC (54.8±2.4% vs. 60.8±3.1%, P

Purpose To detect nonexudative choroidal neovascularization (CNV) in age-related macular degeneration (AMD) with OCT angiography (OCTA) and determine the risk of exudative CNV developing compared with eyes without nonexudative CNV. Design Prospective, longitudinal, observational study. Participants Consecutive patients with drusen and pigmentary changes in the study eye and exudative neovascular AMD in the fellow eye. Methods In this prospective observational study, participants underwent spectral-domain OCTA (AngioVue; Optovue, Inc, Fremont, CA), clinical examination, and structural OCT at baseline and 6-month intervals for 2 years. OCT angiography images were exported for custom processing to remove projection artifact and calculate CNV vessel area. Main Outcome Measures Rate of developing exudation in eyes with and without nonexudative CNV as detected by OCTA on regular follow-up. Results Sixty-three study participants were followed up every 6 months and 48 completed the 2-year study. Mean age was 78 years and 60.3% were female. On the baseline visit, 5 eyes (7.9%) were found to have nonexudative CNV by OCTA, and 3 of them demonstrated exudation. Of 58 eyes with a normal OCTA on baseline visit, 5 eyes developed nonexudative CNV during a follow-up visit. All 5 of these nonexudative CNV went on to develop exudation in subsequent visits. Overall, 8 of the 10 eyes with nonexudative CNV developed exudation with a mean time of 8 months and mean CNV area growth rate of 20% per month (P = 0.014, exponential model). Initiation of antiangiogenic treatment halted their growth. In comparison, exudation occurred in only 6 of the 53 eyes (11%) that lacked a precursor nonexudative CNV. Cox proportional hazard analysis showed that having nonexudative CNV detected was associated with an 18.1-fold increase in the rate of exudation subsequently developing (P Conclusions Nonexudative CNV frequently is detected by OCTA in the fellow eyes of those with exudative CNV. These lesions carry a high risk of exudation developing within the first year after detection and could benefit from close monitoring. The high risk of progression may justify prophylactic treatment; further studies are needed.

Purpose To investigate ophthalmologists’ rate of attestation to meaningful use (MU) of their electronic health record (EHR) systems in the Medicare EHR Incentive Program and their continuity and success in receiving payments in comparison with other specialties. Design Administrative database study. Participants Eligible professionals participating in the Medicare EHR Incentive Program. Methods Based on publicly available data sources, subsets of payment and attestation data were created for ophthalmologists and for other specialties. The number of eligible professionals attesting was determined using the attestation data for each year and stage of the program. The proportion of attestations by EHR vendor was calculated using all attestations for each vendor. Main Outcome Measures Numbers of ophthalmologists attesting by year and stage of the Medicare EHR Incentive Program, incentive payments, and number of attestations by EHR vendor. Results In the peak year of participation, 51.6% of ophthalmologists successfully attested to MU, compared with 37.1% of optometrists, 50.2% of dermatologists, 54.5% of otolaryngologists, and 64.4% of urologists. Across the 6 years of the program, ophthalmologists received an average of $17 942 in incentive payments compared with $11 105 for optometrists, $16 617 for dermatologists, $20 203 for otolaryngologists, and $23 821 for urologists. Epic and Nextgen were the most frequently used EHRs for attestation by ophthalmologists. Conclusions Ophthalmology as a specialty performed better than optometry and dermatology, but worse than otolaryngology and urology, in terms of the proportion of eligible professionals attesting to MU of EHRs. Ophthalmologists were more likely to remain in the program after their initial year of attestation compared with all eligible providers. The top 4 EHR vendors accounted for 50% of attestations by ophthalmologists.

Purpose To use OCT angiography (OCTA)-derived quantitative metrics to assess the response of choroidal neovascularization (CNV) to pro re nata (PRN) anti–vascular endothelial growth factor (VEGF) treatment in neovascular age-related macular degeneration (AMD). Design Prospective, longitudinal cohort study. Participants Fourteen eyes from 14 study participants with treatment-naive neovascular AMD were enrolled. Methods Participants were evaluated monthly and treated with intravitreal anti-VEGF agents under a PRN protocol for 1 year. At each visit, two 3 × 3-mm2 OCTA scans were obtained. Custom image processing was applied to segment the outer retinal slab, suppress projection artifact, and automatically detect CNV. Choroidal neovascularization membrane area and CNV vessel area were calculated. Main Outcome Measures Individual and mean CNV membrane area and CNV vessel area at each visit; within-visit repeatability determined by coefficient of variation. Results Eight eyes showed the entire CNV to be within the 3 × 3-mm2 scanning area and had adequate image quality for CNV quantification. One patient (patient 2) was excluded from analysis because of the presence of a large subretinal hemorrhage overlying the CNV membrane. In the remaining patients, CNV vessel area was reduced by 39%, 50%, 43%, and 41% at months 1, 3, 6, and 12, respectively. Choroidal neovascularization membrane area was reduced by 39%, 51%, 54%, and 45% at months 1, 3, 6, and 12. At month 6, mean change from baseline was not statistically significant for CNV vessel area, whereas it was statistically significant for CNV membrane area. Neither metric was significantly different compared with baseline at month 12. Individual analyses revealed each CNV had a unique response under PRN treatment. Within-visit repeatability was 7.96% (coefficient of variation) for CNV vessel area and 7.37% for CNV membrane area. Conclusions In this small exploratory study of CNV response to PRN anti-VEGF treatment, both CNV vessel area and membrane area were reduced compared with baseline after 3 months. After 1 year of follow-up, these reductions were no longer statistically significant. When anti-VEGF treatment was withheld, increasing CNV vessel area over time often resulted in exudation, but it was not possible to determine exactly when exudation occurs.

Purpose To determine the sensitivity and specificity of OCT angiography (OCTA) in the detection of choroidal neovascularization (CNV) in age-related macular degeneration (AMD). Design Prospective case series. Subjects A prospective series of 72 eyes were studied, which included eyes with treatment-naive CNV due to AMD, non-neovascular AMD, and normal controls. Methods All eyes underwent OCTA with a spectral domain OCT. The 3-dimensional angiogram was segmented into separate en face views including the inner retinal angiogram, outer retinal angiogram, and choriocapillaris angiogram. Detection of abnormal flow in the outer retina served as candidate CNV with OCTA. Masked graders reviewed structural OCT alone, en face OCTA alone, and en face OCTA combined with cross-sectional OCTA for the presence of CNV. Main Outcome Measure The sensitivity and specificity of CNV detection compared to the gold standard of fluorescein angiography and OCT was determined for structural spectral domain OCT alone, en face OCTA alone, and with en face OCTA combined with cross-sectional OCTA. Results Of 32 eyes with CNV, both graders identified 26 true positives with en face OCTA alone, resulting in a sensitivity of 81.3%. Four of the 6 false negatives had large subretinal hemorrhage and sensitivity improved to 94% for both graders if eyes with subretinal hemorrhage were excluded. The addition of cross-sectional OCTA along with en face OCTA improved the sensitivity to 100% for both graders. Structural OCT alone also had a sensitivity of 100%. The specificity of en face OCTA alone was 92.5% for grader A and 97.5% for grader B. The specificity of structural OCT alone was 97.5% for grader A and 85% for grader B. Cross-sectional OCTA combined with en face OCTA had a specificity of 97.5% for grader A and 100% for grader B. Conclusions Sensitivity and specificity for CNV detection with en face OCTA combined with cross-sectional OCTA approaches that of the gold standard of fluorescein angiography with OCT, and it is better than en face OCTA alone. Structural OCT alone has excellent sensitivity for CNV detection. False positives from structural OCT can be mitigated with the addition of flow information with OCTA.

Purpose: To examine the efficacy of a deep learning-based algorithm to quantify the nonperfusion area (NPA) on montaged widefield OCT angiography (OCTA) for assessment of diabetic retinopathy (DR) severity. Design: Cross-sectional study. Participants: One hundred thirty-seven participants with a full range of DR severity and 26 healthy participants. Methods: A deep learning-based algorithm was developed for detecting and quantifying NPA in the superficial vascular complex on widefield OCTA comprising 3 horizontally montaged 6 × 6-mm OCTA scans from the nasal, macular, and temporal regions. We trained the algorithm on 978 volumetric OCTA scans from all participants using 5-fold cross-validation. The algorithm can distinguish NPA from shadow artifacts. The F1 score evaluated segmentation accuracy. The area under the receiver operating characteristic curve and sensitivity with specificity fixed at 95% quantified network performance to distinguish patients with diabetes from healthy control participants, referable DR from nonreferable DR (nonproliferative DR [NPDR] less than moderate severity), and severe DR (severe NPDR, proliferative DR, or DR with edema) from nonsevere DR (mild to moderate NPDR). Main Outcome Measures: Widefield OCTA NPA, visual acuity (VA), and DR severities. Results: Automatically segmented NPA showed high agreement with the manually delineated ground truth, with a mean ± standard deviation F1 score of 0.78 ± 0.05 in nasal, 0.82 ± 0.07 in macular, and 0.78 ± 0.05 in temporal scans. The extrafoveal avascular area (EAA) in the macular scan showed the best sensitivity at 54% for differentiating those with diabetes from healthy control participants, whereas montaged widefield OCTA scan showed significantly higher sensitivity than macular scans (P < 0.0001, McNemar’s test) for detecting eyes with DR at 66%, referable DR at 63%, and severe DR at 62%. Montaged widefield OCTA showed the highest correlation (Spearman ρ = 0.74; P < 0.0001) between EAA and DR severity. The macular scan showed the strongest negative correlation (Pearson ρ = –0.42; P < 0.0001) between EAA and best-corrected VA. Conclusions: A deep learning-based algorithm for montaged widefield OCTA can detect NPA accurately and can improve the detection of clinically important DR.

Optical coherence tomographic angiography (OCTA) is a novel technology capable of imaging retinal vasculature three-dimensionally at capillary scale without the need to inject any extrinsic dye contrast. However, projection artifacts cause superficial retinal vascular patterns to be duplicated in deeper layers, thus interfering with the clean visualization of some retinal plexuses and vascular pathologies. Projection-resolved OCTA (PR-OCTA) uses post-processing algorithms to reduce projection artifacts. With PR-OCTA, it is now possible to resolve up to 4 distinct retinal vascular plexuses in the living human eye. The technology also allows us to detect and distinguish between various retinal and optic nerve diseases. For example, optic nerve diseases such as glaucoma primarily reduces the capillary density in the superficial vascular complex, which comprises the nerve fiber layer plexus and the ganglion cell layer plexus. Outer retinal diseases such as retinitis pigmentosa primarily reduce the capillary density in the deep vascular complex, which comprises the intermediate capillary plexus and the deep capillary plexus. Retinal vascular diseases such as diabetic retinopathy and vein occlusion affect all plexuses, but with different patterns of capillary loss and vascular malformations. PR-OCTA is also useful in distinguishing various types of choroidal neovascularization and monitoring their response to anti-angiogenic medications. In retinal angiomatous proliferation and macular telangiectasia type 2, PR-OCTA can trace the pathologic vascular extension into deeper layers as the disease progress through stages. Plexus-specific visualization and measurement of retinal vascular changes are improving our ability to diagnose, stage, monitor, and assess treatment response in a wide variety of optic nerve and retinal diseases. These applications will be further enhanced with the continuing improvement of the speed and resolution of the OCT platforms, as well as the development of software algorithms to reduce artifacts, improve image quality, and make quantitative measurements.

Objective To evaluate quantitative and qualitative differences in documentation of the ophthalmic examination between paper and electronic health record (EHR) systems. Design Comparative case series. Participants One hundred fifty consecutive pairs of matched paper and EHR notes, documented by 3 attending ophthalmologist providers. Methods An academic ophthalmology department implemented an EHR system in 2006. Database queries were performed to identify cases in which the same problems were documented by the same provider on different dates, using paper versus EHR methods. This was done for 50 consecutive pairs of examinations in 3 different diseases: age-related macular degeneration (AMD), glaucoma, and pigmented choroidal lesions (PCLs). Quantitative measures were used to compare completeness of documenting the complete ophthalmologic examination, as well as disease-specific critical findings using paper versus an EHR system. Qualitative differences in paper versus EHR documentation were illustrated by selecting representative paired examples. Main Outcome Measures (1) Documentation score, defined as the number of examination elements recorded for the slit-lamp examination, fundus examination, and complete ophthalmologic examination and for critical clinical findings for each disease. (2) Paired comparison of qualitative differences in paper versus EHR documentation. Results For all 3 diseases (AMD, glaucoma, PCL), the number of complete examination findings recorded was significantly lower with paper than the EHR system ( P ≤0.004). Among the 3 individual examination sections (general, slit lamp, fundus) for the 3 diseases, 5 of the 9 possible combinations had significantly lower mean documentation scores with paper than EHR notes. For 2 of the 3 diseases, the number of critical clinical findings recorded was significantly lower using paper versus EHR notes ( P ≤0.022). All (150/150) paper notes relied on graphical representations using annotated hand-drawn sketches, whereas no (0/150) EHR notes contained drawings. Instead, the EHR systems documented clinical findings using textual descriptions and interpretations. Conclusions There were quantitative and qualitative differences in the nature of paper versus EHR documentation of ophthalmic findings in this study. The EHR notes included more complete documentation of examination elements using structured textual descriptions and interpretations, whereas paper notes used graphical representations of findings. Financial Disclosure(s) The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Purpose To determine specific retinal precursor lesions and sequence of events preceding the onset of geographic atrophy (GA) in eyes with age-related macular degeneration (AMD). Design Retrospective review. Participants All participants in the Age-Related Eye Disease Study (AREDS) at 2 clinical centers (Devers Eye Institute, Portland, Oregon, and University of Wisconsin, Madison, Wisconsin) in whom GA initially appeared in at least one eye a minimum of 4 years after the baseline study visit. Methods All stereoscopic fundus photographs taken before the appearance of GA in the involved (study) eye were reviewed. Fundus features at the site of future GA were graded and recorded. Three graders reviewed photographs, with independent grading and adjudication by mutual agreement. Features graded included drusen (classified by size and confluence), focal hyperpigmentation, hypopigmentation, and refractile deposits. The time between first appearance of these features and initial appearance of GA was recorded. Main Outcome Measure Appearance of GA. Results Of all AREDS participants at the 2 sites, 95 eyes of 77 developed GA at least 4 years after entrance into the study. Average time from baseline to initial appearance of GA was 6.6 years (range, 4–11). Drusen were found in 100% of eyes at the site of later developing GA, drusen >125 μm in diameter in 96% of eyes, confluent drusen in 94%, hyperpigmentation in 96%, drusen > 250 μm in 83%, hypopigmentation in 82%, and refractile deposits in 23%. Time from lesion appearance to onset of GA varied by lesion type, ranging from 5.9 years for drusen confluence to 2.5 years for hypopigmentation or refractile deposits. Lesions generally followed a uniform sequence of appearance. Conclusions By focusing on the location of initial GA appearance and then retrospectively analyzing prior photographs, we were able to identify specific precursor lesions and the most common sequence of events leading to GA formation in eyes with AMD. The progression was usually characterized by large drusen formation and development of hyperpigmentation, followed by regression of drusen, appearance of hypopigmentation, and ultimately development of GA, sometimes preceded by the appearance of refractile deposits.

Purpose To report a case of retinal occlusive disease producing binasal visual field defects in a patient with sickle cell (SC) disease. Design Retrospective case report. Methods A 21-year-old man with SC disease presented with binasal field defects and 20/20 acuity in each eye. Results Initial ophthalmoscopy and fluorescein angiography revealed no abnormalities. Optical coherence tomography (OCT) demonstrated bilateral temporal inner retinal hyperreflectivity, and multifocal electroretinography (mfERG) confirmed retinal dysfunction. Several weeks later, ophthalmoscopy and angiography demonstrated macular arteriolar occlusive disease. Conclusions Simultaneous bilateral macular occlusive events are uncommon in patients particularly with SC disease. Although the binasal field defects raised the suspicion of a process affecting the optic nerves, the OCT and mfERG proved essential in diagnosing retinal rather than optic nerve disease.

Presenting features A 38-year-old man with a history of intravenous drug use was admitted to the hospital for treatment of an arm abscess. He noted that his right eye was "blood shot" and painful, but denied recent ocular trauma. He had photophobia and felt that his vision had become worse. Physical examination revealed a red right eye; there was hyperemia of the conjunctiva without surrounding vesicles, and the cornea was cloudy (Figure 1). Figure 1Examination of the right eye revealing hyperemia of the conjunctiva and a cloudy cornea. Visual acuity was normal in the left eye but decreased (20/200) in the right eye. Fundoscopic examination was otherwise unremarkable. The rest of the physical examination was normal except for a tender painful swelling and cellulitis on the left forearm. Laboratory findings revealed antibodies to human immunodeficiency virus (HIV). What is the diagnosis?