Clinically Significant Nonperfusion Areas on Widefield OCT Angiography in Diabetic Retinopathy.

Purpose: To investigate the distribution of clinically significant nonperfusion areas (NPAs) on widefield OCT angiography (OCTA) images in patients with diabetes. Design: Prospective, cross-sectional, observational study. Participants: One hundred and forty-four eyes of 114 patients with diabetes. Methods: Nominal 20 × 23 mm OCTA images were obtained using a swept-source OCTA device (Xephilio OCT-S1), followed by the creation of en face images 20-mm (1614 pixels) in diameter centering on the fovea. The nonperfusion squares (NPSs) were defined as the 10 × 10 pixel squares without retinal vessels, and the ratio of eyes with the NPSs to all eyes in each square was referred to as the NPS ratio. The areas with probabilistic differences (APD) for proliferative diabetic retinopathy (PDR) and nonproliferative diabetic retinopathy (NPDR) (APD[PDR] and APD[NPDR]) were defined as sets of squares with higher NPS ratios in eyes with PDR and NPDR, respectively. The P ratio (NPSs within APD[PDR] but not APD[NPDR]/all NPSs) was also calculated. Main Outcome Measures: The probabilistic distribution of the NPSs and the association with diabetic retinopathy (DR) severity. Results: The NPSs developed randomly in eyes with mild and moderate NPDR and were more prevalent in the extramacular areas and the temporal quadrant in eyes with severe NPDR and PDR. The APD(PDR) was distributed mainly in the extramacular areas, sparing the areas around the vascular arcades and radially peripapillary capillaries. The APD(PDR) contained retinal neovascularization more frequently than the non-APD(PDR) (P = 0.023). The P ratio was higher in eyes with PDR than in those with NPDR (P < 0.001). The multivariate analysis designated the P ratio (odds ratio, 8.293 × 107; 95% confidence interval, 6.529 × 102-1.053 × 1013; P = 0.002) and the total NPSs (odds ratio, 1.002; 95% confidence interval, 1.001-1.003; P < 0.001) as independent risk factors of PDR. Most eyes with NPDR and 4-2-1 rule findings of DR severity had higher P ratios but not necessarily greater NPS numbers. Conclusions: The APD(PDR) is uniquely distributed on widefield OCTA images, and the NPA location patterns are associated with DR severity, independent of the entire area of NPAs. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Artificial Intelligence Detection of Diabetic Retinopathy: Subgroup Comparison of the EyeArt System with Ophthalmologists' Dilated Examinations.

Objective: To compare general ophthalmologists, retina specialists, and the EyeArt Artificial Intelligence (AI) system to the clinical reference standard for detecting more than mild diabetic retinopathy (mtmDR). Design: Prospective, pivotal, multicenter trial conducted from April 2017 to May 2018. Participants: Participants were aged ≥ 18 years who had diabetes mellitus and underwent dilated ophthalmoscopy. A total of 521 of 893 participants met these criteria and completed the study protocol. Testing: Participants underwent 2-field fundus photography (macula centered, disc centered) for the EyeArt system, dilated ophthalmoscopy, and 4-widefield stereoscopic dilated fundus photography for reference standard grading. Main Outcome Measures: For mtmDR detection, sensitivity and specificity of EyeArt gradings of 2-field, fundus photographs and ophthalmoscopy grading versus a rigorous clinical reference standard comprising Reading Center grading of 4-widefield stereoscopic dilated fundus photographs using the ETDRS severity scale. The AI system provided automatic eye-level results regarding mtmDR. Results: Overall, 521 participants (999 eyes) at 10 centers underwent dilated ophthalmoscopy: 406 by nonretina and 115 by retina specialists. Reading Center graded 207 positive and 792 eyes negative for mtmDR. Of these 999 eyes, 26 eyes were ungradable by the EyeArt system, leaving 973 eyes with both EyeArt and Reading Center gradings. Retina specialists correctly identified 22 of 37 eyes as positive (sensitivity 59.5%) and 182 of 184 eyes as negative (specificity 98.9%) for mtmDR versus the EyeArt AI system that identified 36 of 37 as positive (sensitivity 97%) and 162 of 184 eyes as negative (specificity of 88%) for mtmDR. General ophthalmologists correctly identified 35 of 170 eyes as positive (sensitivity 20.6%) and 607 of 608 eyes as negative (specificity 99.8%) for mtmDR compared with the EyeArt AI system that identified 164 of 170 as positive (sensitivity 96.5%) and 525 of 608 eyes as negative (specificity 86%) for mtmDR. Conclusions: The AI system had a higher sensitivity for detecting mtmDR than either general ophthalmologists or retina specialists compared with the clinical reference standard. It can potentially serve as a low-cost point-of-care diabetic retinopathy detection tool and help address the diabetic eye screening burden.

A Deep Learning Network for Classifying Arteries and Veins in Montaged Widefield OCT Angiograms.

Purpose: To propose a deep-learning-based method to differentiate arteries from veins in montaged widefield OCT angiography (OCTA). Design: Cross-sectional study. Participants: A total of 232 participants, including 109 participants with diabetic retinopathy (DR), 64 participants with branch retinal vein occlusion (BRVO), 27 participants with diabetes but without DR, and 32 healthy participants. Methods: We propose a convolutional neural network (CAVnet) to classify retinal blood vessels on montaged widefield OCTA en face images as arteries and veins. A total of 240 retinal angiograms from 88 eyes were used to train CAVnet, and 302 retinal angiograms from 144 eyes were used for testing. This method takes the OCTA images as input and outputs the segmentation results with arteries and veins down to the level of precapillary arterioles and postcapillary venules. The network also identifies their intersections. We evaluated the agreement (in pixels) between segmentation results and the manually graded ground truth using sensitivity, specificity, F1-score, and Intersection over Union (IoU). Measurements of arterial and venous caliber or tortuosity are made on our algorithm's output of healthy and diseased eyes. Main Outcome Measures: Classification of arteries and veins, arterial and venous caliber, and arterial and venous tortuosity. Results: For classification and identification of arteries, the algorithm achieved average sensitivity of 95.3%, specificity of 99.6%, F1 score of 94.2%, and IoU of 89.3%. For veins, the algorithm achieved average sensitivity of 94.4%, specificity of 99.7%, F1 score of 94.1%, and IoU of 89.2%. We also achieved an average sensitivity of 76.3% in identifying intersection points. The results show CAVnet has high accuracy on differentiating arteries and veins in DR and BRVO cases. These classification results are robust across 2 instruments and multiple scan volume sizes. Outputs of CAVnet were used to measure arterial and venous caliber or tortuosity, and pixel-wise caliber and tortuosity maps were generated. Differences between healthy and diseased eyes were demonstrated, indicating potential clinical utility. Conclusions: The CAVnet can classify arteries and veins and their branches with high accuracy and is potentially useful in the analysis of vessel type-specific features on diseases such as branch retinal artery occlusion and BRVO.

Alterations in the Choroidal Sublayers in Relationship to Severity and Progression of Diabetic Retinopathy: A Swept-Source OCT Study.

Purpose: To examine the association of baseline choroidal sublayers metrics with the risk of diabetic retinopathy (DR) progression over 2 years, with adjustment for confounding factors that affect choroidal measurements. Design: Prospective, observational cohort study. Participants: One hundred three eyes from 62 patients with diabetes mellitus (DM). Methods: Patients were followed up at 6-month intervals for at least 2 years. Choroidal metrics including choroidal area, choroidal thickness (CT), and choroidal vascularity index were measured for both (1) the choriocapillaris plus Sattler's layer and (2) the Haller's layer within the subfoveal and parafoveal region. Cox proportional models were constructed to estimate the relationship between baseline choroidal metrics and DR progression, adjusted for intereye correlation, established risk factors (i.e., duration of DM, glycated hemoglobin [HbA1c] level, body mass index [BMI], use of insulin, and mean arterial blood pressure [MABP]) and confounding factors of choroidal measurements (i.e., age and axial length). Additional predictive value of choroidal metrics was assessed using the C-statistic. Main Outcome Measures: Hazard ratios (HRs) calculated by Cox proportional hazards model to demonstrate the associations between baseline choroidal metrics and DR progression. Results: After adjusting for age, axial length, and intereye correlation, choroidal metrics in Haller's layer at baseline that were associated with a higher risk of DR progression included increases in subfoveal choroidal area (HR, 2.033; 95% confidence interval [CI], 1.179-3.505; P = 0.011), subfoveal plus parafoveal choroidal area (HR, 1.909; 95% CI, 1.096-3.326; P = 0.022), subfoveal CT (HR, 2.032; 95% CI, 1.181-3.498; P = 0.010), and subfoveal plus parafoveal CT (HR, 1.908; 95% CI, 1.097-3.319; P = 0.022). These associations remained statistically significant after additionally adjusting for duration of DM, HbA1c level, BMI, use of insulin, and MABP. Addition of these choroidal metrics significantly improved the discrimination for DR progression when compared with established risk factors alone (e.g., duration of DM and HbA1c; increase in C-statistic ranged from 8.08% to 9.67% [P < 0.05]). Conclusions: Eyes with a larger choroidal area and CT in Haller's layer at baseline were associated with a higher risk of DR progression over 2 years.

Relationship between diabetic retinopathy microalbuminuria and other modifiable risk factors.

BACKGROUND: Diabetic Retinopathy (DR) is an important microvascular complication of diabetes that can lead to irreversible blindness. Microalbuminuria is strongly associated with diabetic retinopathy and can be used as a reliable marker of diabetic retinopathy. AIM: To assess the association between DR, microalbuminuria, and other modifiable risk factors in patients with type 2 diabetes. METHODOLOGY: 3090 patients with T2DM visiting North Delhi Diabetes Centre, New Delhi between July 2016 to October 2019 were evaluated for the clinical and biochemical parameters that included urinary albumin, HbA1C, lipid profiles, serum creatinine estimation and underwent biothesiometry. RESULTS: 3090 patients (1350 females and 1740 males), with mean age of 52.7 ± 9.2 years and diabetes duration ranging from 1 to 19 years (mean 9.4 ± 6), duration of less than 5 years, 6-10 years and more than 10 years in 52%, 26% and in 22%, respectively. Duration of diabetes was strong predictor of retinopathy (p = 0.001). The HbA1c and BMI in patients with DR was significantly higher than in those without DR. 18.2% patients were diagnosed to have retinopathy. Peripheral neuropathy was observed in 24.2% and was positively associated with DR (p = 0.002). 33.9% and 4.5% patients had microalbuminuria macroalbuminuria, respectively and 9.7% patients had creatinine >1.3 mg/dL. There was significant positive relationship between different grades of retinopathy and albuminuria. CONCLUSIONS: Our study is a large real-world study that demonstrates that HbA1c, BMI, duration of diabetes, microalbuminuria and peripheral neuropathy are relatively, yet cohesively contributing factors towards varying grade of retinopathy.

Comparison of Ultra-Widefield Imaging and Standard Imaging in Assessment of Early Treatment Diabetic Retinopathy Severity Scale.

Purpose: To compare Early Treatment Diabetic Retinopathy Study (ETDRS) severity levels between standard 7-field imaging and ultra-widefield (UWF) imaging and to incorporate peripheral diabetic retinopathy (DR) lesions into the ETDRS grading system. Design: Cross-sectional Study. Participants: Paired images from 192 eyes (189 participants) with diabetic retinopathy were included. Methods: The ETDRS levels were determined by masked graders in 3 ways: standard 7-field imaging, UWF within the 7-field region (7-field UWF imaging), and the entire UWF image (global ETDRS imaging). Main Outcome Measures: Percentage agreement between 7-field and UWF imaging for ETDRS levels. Results: Of the 166 paired images evaluated, exact agreement was found in 48.8% of eyes between standard 7-field and 7-field UWF ETDRS levels with a weighted κ value of 0.59 (95% confidence interval [CI], 0.5-0.68). Agreement rates varied with DR severity and were least in early DR (30.8%) and moderate nonproliferative DR (26.5%) groups. In 156 eyes with 7-field UWF ETDRS and global UWF ETDRS levels, exact agreement was found in 143 eyes (92%), with a weighted κ value of 0.9 (95% CI, 0.9-0.98). The peripheral lesions contributed to a higher DR severity in 8% and changed the eye to a proliferative DR level in 2%. Reproducibility of the 3 ETDRS evaluations was comparable with a weighted κ value of 0.57 with standard 7-field imaging, 0.65 with 7-field UWF imaging, and 0.60 with global ETDRS scale imaging. Conclusions: Moderate agreement was found in the ETDRS DR severity scale between standard 7-field and UWF imaging, indicating caution in interchanging data from the 2 methods. Both methods showed good reproducibility for clinical trial outcome of 2-step change. The global ETDRS scale provides a comprehensive score to incorporate peripheral changes into the ETDRS scale. The implications of the global scale on progression rate are yet to be determined.

Temporal Trends in the Treatment of Proliferative Diabetic Retinopathy: An AAO IRIS® Registry Analysis.

Purpose: This study examined how treatment patterns for proliferative diabetic retinopathy (PDR) have changed over time using clinical registry data from the AAO IRIS® Registry (Intelligent Research in Sight). Design: A retrospective cohort analysis using the IRIS Registry database spanning 2013-2017. Participants: A total of 141 317 patients with newly diagnosed PDR (International Classification of Diseases [ICD], Tenth Revision, codes E08.35, E09.35, E10.35, E11.35, and E13.35 and ICD, Ninth Revision, code 362.02) were included. Methods: Comparison analyses were conducted using Tukey and chi-square tests, and time-trend analyses were conducted using Mann-Kendall tests and Theil-Sen slopes. Main Outcome Measures: Patient characteristics including age, gender, and laterality; whether patients received intravitreal anti-vascular endothelial growth factor injections (IVI) only, panretinal photocoagulation (PRP) only, both IVI and PRP (IVI+PRP), or observation; intravitreal drug data; and diabetic macular edema (DME) status were compared. Results: From 2013-2017, the average age of PDR diagnosis was 59.2 years, with 53.3% of patients being male. Sixty-two thousand one hundred five newly diagnosed PDR patients (43.9%) received IVI, 32 293 patients (27.1%) received PRP, 27 664 patients (19.6%) received IVI+PRP, and 13 255 patients (9.4%) underwent observation. In 2013, more PDR patients undergoing treatment received PRP only (47.5%) than IVI only (37.3%) or IVI+PRP (15.1%). From 2013 to 2017, the percentage of patients treated with PRP only decreased by 5.6% per year (P = 0.05) and the percentage of patients treated with IVI only increased by 3.9% per year (P = 0.05). By 2017, most patients received IVI only (52.9%). Patients with PDR with DME were more likely than patients without DME to receive IVI only (64.3% vs. 31.5%; P < 0.001). Among patients receiving IVI and IVI+PRP, bevacizumab (69.8%) was the most common intravitreal medication given followed by aflibercept (18.4%) then ranibizumab (11.7%). Conclusions: In this cohort analysis of the IRIS Registry, IVI surpassed PRP as the more common method of treating newly diagnosed PDR from 2013 to 2017, with bevacizumab administered in more than two thirds of IVIs.

Quantification of Nonperfusion Area in Montaged Widefield OCT Angiography Using Deep Learning in Diabetic Retinopathy.

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.