Strong versus Weak Data Labeling for Artificial Intelligence Algorithms in the Measurement of Geographic Atrophy.

Purpose: To gain an understanding of data labeling requirements to train deep learning models for measurement of geographic atrophy (GA) with fundus autofluorescence (FAF) images. Design: Evaluation of artificial intelligence (AI) algorithms. Subjects: The Age-Related Eye Disease Study 2 (AREDS2) images were used for training and cross-validation, and GA clinical trial images were used for testing. Methods: Training data consisted of 2 sets of FAF images; 1 with area measurements only and no indication of GA location (Weakly labeled) and the second with GA segmentation masks (Strongly labeled). Main Outcome Measures: Bland-Altman plots and scatter plots were used to compare GA area measurement between ground truth and AI measurements. The Dice coefficient was used to compare accuracy of segmentation of the Strong model. Results: In the cross-validation AREDS2 data set (n = 601), the mean (standard deviation [SD]) area of GA measured by human grader, Weakly labeled AI model, and Strongly labeled AI model was 6.65 (6.3) mm2, 6.83 (6.29) mm2, and 6.58 (6.24) mm2, respectively. The mean difference between ground truth and AI was 0.18 mm2 (95% confidence interval, [CI], -7.57 to 7.92) for the Weakly labeled model and -0.07 mm2 (95% CI, -1.61 to 1.47) for the Strongly labeled model. With GlaxoSmithKline testing data (n = 156), the mean (SD) GA area was 9.79 (5.6) mm2, 8.82 (4.61) mm2, and 9.55 (5.66) mm2 for human grader, Strongly labeled AI model, and Weakly labeled AI model, respectively. The mean difference between ground truth and AI for the 2 models was -0.97 mm2 (95% CI, -4.36 to 2.41) and -0.24 mm2 (95% CI, -4.98 to 4.49), respectively. The Dice coefficient was 0.99 for intergrader agreement, 0.89 for the cross-validation data, and 0.92 for the testing data. Conclusions: Deep learning models can achieve reasonable accuracy even with Weakly labeled data. Training methods that integrate large volumes of Weakly labeled images with small number of Strongly labeled images offer a promising solution to overcome the burden of cost and time for data labeling. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

An Updated Simplified Severity Scale for Age-Related Macular Degeneration Incorporating Reticular Pseudodrusen: Age-Related Eye Disease Study Report Number 42.

PURPOSE: To update the Age-Related Eye Disease Study (AREDS) simplified severity scale for risk of late age-related macular degeneration (AMD), including incorporation of reticular pseudodrusen (RPD), and to perform external validation on the Age-Related Eye Disease Study 2 (AREDS2). DESIGN: Post hoc analysis of 2 clinical trial cohorts: AREDS and AREDS2. PARTICIPANTS: Participants with no late AMD in either eye at baseline in AREDS (n = 2719) and AREDS2 (n = 1472). METHODS: Five-year rates of progression to late AMD were calculated according to levels 0 to 4 on the simplified severity scale after 2 updates: (1) noncentral geographic atrophy (GA) considered part of the outcome, rather than a risk feature, and (2) scale separation according to RPD status (determined by validated deep learning grading of color fundus photographs). MAIN OUTCOME MEASURES: Five-year rate of progression to late AMD (defined as neovascular AMD or any GA). RESULTS: In the AREDS, after the first scale update, the 5-year rates of progression to late AMD for levels 0 to 4 were 0.3%, 4.5%, 12.9%, 32.2%, and 55.6%, respectively. As the final simplified severity scale, the 5-year progression rates for levels 0 to 4 were 0.3%, 4.3%, 11.6%, 26.7%, and 50.0%, respectively, for participants without RPD at baseline and 2.8%, 8.0%, 29.0%, 58.7%, and 72.2%, respectively, for participants with RPD at baseline. In external validation on the AREDS2, for levels 2 to 4, the progression rates were similar: 15.0%, 27.7%, and 45.7% (RPD absent) and 26.2%, 46.0%, and 73.0% (RPD present), respectively. CONCLUSIONS: The AREDS AMD simplified severity scale has been modernized with 2 important updates. The new scale for individuals without RPD has 5-year progression rates of approximately 0.5%, 4%, 12%, 25%, and 50%, such that the rates on the original scale remain accurate. The new scale for individuals with RPD has 5-year progression rates of approximately 3%, 8%, 30%, 60%, and 70%, that is, approximately double for most levels. This scale fits updated definitions of late AMD, has increased prognostic accuracy, seems generalizable to similar populations, but remains simple for broad risk categorization. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Imaging Modalities for Assessing the Vascular Component of Diabetic Retinal Disease: Review and Consensus for an Updated Staging System.

Purpose: To review the evidence for imaging modalities in assessing the vascular component of diabetic retinal disease (DRD), to inform updates to the DRD staging system. Design: Standardized narrative review of the literature by an international expert workgroup, as part of the DRD Staging System Update Effort, a project of the Mary Tyler Moore Vision Initiative. Overall, there were 6 workgroups: Vascular Retina, Neural Retina, Systemic Health, Basic and Cellular Mechanisms, Visual Function, and Quality of Life. Participants: The Vascular Retina workgroup, including 16 participants from 4 countries. Methods: Literature review was conducted using standardized evidence grids for 5 modalities: standard color fundus photography (CFP), widefield color photography (WFCP), standard fluorescein angiography (FA), widefield FA (WFFA), and OCT angiography (OCTA). Summary levels of evidence were determined on a validated scale from I (highest) to V (lowest). Five virtual workshops were held for discussion and consensus. Main Outcome Measures: Level of evidence for each modality. Results: Levels of evidence for standard CFP, WFCP, standard FA, WFFA, and OCTA were I, II, I, I, and II respectively. Traditional vascular lesions on standard CFP should continue to be included in an updated staging system, but more studies are required before they can be used in posttreatment eyes. Widefield color photographs can be used for severity grading within the area covered by standard CFPs, although these gradings may not be directly interchangeable with each other. Evaluation of the peripheral retina on WFCP can be considered, but the method of grading needs to be clarified and validated. Standard FA and WFFA provide independent prognostic value, but the need for dye administration should be considered. OCT angiography has significant potential for inclusion in the DRD staging system, but various barriers need to be addressed first. Conclusions: This study provides evidence-based recommendations on the utility of various imaging modalities for assessment of the vascular component of DRD, which can inform future updates to the DRD staging system. Although new imaging modalities offer a wealth of information, there are still major gaps and unmet research needs that need to be addressed before this potential can be realized. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Comparison of Standard 7-Field, Clarus, and Optos Ultrawidefield Imaging Systems for Diabetic Retinopathy (COCO Study).

Purpose: The purpose of this study was to compare diabetic retinopathy (DR) severity levels assessed from 7 standard-field stereoscopic color photographs on a 35° fundus camera to both Clarus and Optos ultrawidefield color images. Design: Cross-sectional, comparative imaging study. Participants: Participants with DR imaged at a single-center retina practice. Methods: Participants were imaged on 3 cameras at a single visit with the Topcon 35° fundus camera, Clarus, and Optos. The DR Severity Scale (DRSS) level was determined within the 7-field (7F) area of each image set using the ETDRS scale. An additional global DRSS was assigned for both Clarus and Optos images using the entire visible retina. Weighted kappa (wκ) measured the agreement between cameras. Main Outcome Measures: The primary outcome was a 3-way comparison of DRSS level within the 7F area imaged on the 3 cameras. Secondary outcomes included a comparison of the DRSS obtained with standard 7F imaging to the global DRSS of Clarus and Optos and a comparison of the global DRSS between Clarus and Optos only. Results: Ninety-seven eyes (50 participants) were evaluated. Agreement within 1-step of ETDRS levels between standard 7F imaging and Clarus 7F was 90.1% (wκ = 0.65), and with Optos 7F in 85.9%, (wκ = 0.58). Agreement within 1-step between standard 7F imaging and Clarus global was 88.9% of eyes (wκ = 0.63), and Optos global was 85.7%, (wκ = 0.54). Agreement between Clarus and Optos global DR level within 1-step was 89.1% (wκ = 0.68). Intergrader agreement for the 7F ETDRS level was 96% for standard 7F imaging, 98% for Clarus, and 95.5% for Optos. Conclusions: These findings suggest that when evaluating the 7F area on Clarus and Optos, DR severity grades are comparable to standard 7F imaging. However, it is important to understand the unique attributes and differences of each fundus camera when changing the type of system used in a clinical setting due to upgrading equipment. Additionally, if the facility has access to > 1 device, there should not be an exchange between cameras for the same patient. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Local and Global Associations of Reticular Pseudodrusen in Age-Related Macular Degeneration.

PURPOSE: To investigate the spatial distribution of reticular pseudodrusen (RPD) in eyes with age-related macular degeneration (AMD) and their correlation with functional measures, retinal thickness, and changes over time. DESIGN: Longitudinal, cohort study. PARTICIPANTS: Thirty-five participants with RPD and spectrum of AMD severity (including no AMD). METHODS: Multimodal imaging was graded by a reading center, including evaluation of color fundus imaging to assess AMD severity scores. Reticular pseudodrusen presence on OCT volumes was confirmed on en face imaging and the RPD extent was contoured on infrared images. One study eye per participant underwent rod-mediated dark adaptation, measuring rod intercept time (RIT) at 5° and/or 12° superior to the fovea. MAIN OUTCOME MEASURES: The primary outcome was RIT and OCT thickness measures which were correlated with RPD area. RESULTS: A total of 51 eyes had ≥ 1 visit with RPD detected (mean follow-up, 2.19 ± 2.04 years; range, 0-5 years), totaling 169 eye-based visits with RPD. Of the 51 eyes with RPD, 5 (9.8%) developed geographic atrophy and 17 (33.3%) progressed to neovascular AMD. Larger RPD areas were detected more frequently in AMD severity scores 6-7. Reticular pseudodrusen area within an eye generally increased over time. The lesion distribution showed a predilection for the superior retina, especially the outer superior subfield of the ETDRS grid, with the central subfield having least involvement. Reticular pseudodrusen area was inversely correlated with central subfield thickness and positively correlated with RIT at 5° (P = 0.001; r2 = 0.01) and 12° (P = 0.004; r2 = 0.01). Rod-mediated dark adaptation at 5° reached the test ceiling in > 85% of visits, irrespective of RPD lesion presence/absence at the test location. Retinal thickness decreased monotonically, with the central subfield demonstrating the greatest percentage change over 5 years (Δ = -5.47%). CONCLUSIONS: In AMD, RPD involve predominantly the superior retina but can involve all ETDRS subfields and evolve over time. Eyes with RPD exhibit structural and functional impairments that can be measured beyond the boundaries of the RPD lesions, suggesting changes associated with RPD are associated with both local changes and a more widespread process. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Critical Dependence on Area in Relationship between ARMS2/HTRA1 Genotype and Faster Geographic Atrophy Enlargement: Age-Related Eye Disease Study 2 Report Number 33.

PURPOSE: To analyze ARMS2/HTRA1 as a risk factor for faster geographic atrophy (GA) enlargement according to (1) GA area and (2) contiguous enlargement versus progression to multifocality. DESIGN: Age-Related Eye Disease Study 2 (AREDS2) cohort analysis. PARTICIPANTS: Eyes with GA: 546 eyes of 406 participants. METHODS: Geographic atrophy area was measured from color fundus photographs at annual visits. Mixed-model regression of square root of GA area and proportional hazards regression of progression to multifocality were analyzed by ARMS2 genotype. MAIN OUTCOME MEASURES: Change in square root GA area and progression to multifocality. RESULTS: Geographic atrophy enlargement was significantly faster with ARMS2 risk alleles (P < 0.0001) at 0.224 mm/year (95% CI, 0.195-0.252 mm/year), 0.298 mm/year (95% CI, 0.271-0.324 mm/year), and 0.317 mm/year (95% CI, 0.279-0.355 mm/year), for 0 to 2 risk alleles, respectively. However, a significant interaction (P = 0.011) was observed between genotype and baseline area. In eyes with very small area (< 1.9 mm2), enlargement was significantly faster with ARMS2 risk alleles (P < 0.0001) at 0.193 mm/year (95% CI, 0.162-0.225 mm/year) versus 0.304 mm/year (95% CI, 0.280-0.329 mm/year) for 0 versus 1 to 2 risk alleles, respectively. With moderately small (1.9-3.8 mm2) or medium to large (≥ 3.8 mm2) area, enlargement was not significantly faster with ARMS2 risk alleles (P = 0.66 and P = 0.70, respectively). In nonmultifocal GA, enlargement was significantly faster with ARMS2 risk alleles (P = 0.001) at 0.175 mm/year (95% CI, 0.142-0.209 mm/year), 0.226 mm/year (95% CI, 0.193-0.259 mm/year), and 0.287 mm/year (95% CI, 0.237-0.337 mm/year) with 0 to 2 risk alleles, respectively. ARMS2 genotype was not associated significantly with progression to multifocal GA. CONCLUSIONS: The relationship between ARMS2/HTRA1 genotype and faster GA enlargement depends critically on GA area: risk alleles represent a strong risk factor for faster enlargement only in eyes with very small area. They increase the growth rate more through contiguous enlargement than progression to multifocality. ARMS2/HTRA1 genotype is more important in increasing risk of progression to GA and initial GA enlargement (contiguously) than in subsequent enlargement or progression to multifocality. These findings may explain some discrepancies between previous studies and have implications for both research and clinical practice. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Association of macular pigment optical density with retinal layer thicknesses in eyes with and without manifest primary open-angle glaucoma.

OBJECTIVE: To investigate associations between baseline macular pigment optical density (MPOD) and retinal layer thicknesses in eyes with and without manifest primary open-angle glaucoma (POAG) in the Carotenoids in Age-Related Eye Disease Study 2 (CAREDS2). METHODS AND ANALYSIS: MPOD was measured at CAREDS baseline (2001-2004) via heterochromatic flicker photometry (0.5° from foveal centre). Peripapillary retinal nerve fibre layer (RNFL), macular ganglion cell complex (GCC), ganglion cell layer (GCL), inner plexiform layer (IPL), and RNFL thicknesses were measured at CAREDS2 (2016-2019) via spectral-domain optical coherence tomography. Associations between MPOD and retinal thickness were assessed using multivariable linear regression. RESULTS: Among 742 eyes (379 participants), manifest POAG was identified in 50 eyes (32 participants). In eyes without manifest POAG, MPOD was positively associated with macular GCC, GCL and IPL thicknesses in the central subfield (P-trend ≤0.01), but not the inner or outer subfields. Among eyes with manifest POAG, MPOD was positively associated with macular GCC, GCL, IPL and RNFL in the central subfield (P-trend ≤0.03), but not the inner or outer subfields, and was positively associated with peripapillary RNFL thickness in the superior and temporal quadrants (P-trend≤0.006). CONCLUSION: We observed a positive association between MPOD and central subfield GCC thickness 15 years later. MPOD was positively associated with peripapillary RNFL superior and temporal quadrant thicknesses among eyes with manifest POAG. Our results linking low MPOD to retinal layers that are structural indicators of early glaucoma provide further evidence that carotenoids may be protective against manifest POAG.

Prevalence of Macular Atrophy in the MARINA Study of Ranibizumab versus Sham for Neovascular Age-Related Macular Degeneration.

OBJECTIVE: Determine prevalence, progression rates, and associations of newly detectable macular atrophy (MA) in patients with choroidal neovascularization (CNV) secondary to neovascular age-related macular degeneration (nAMD) with/without ranibizumab treatment. DESIGN: Post hoc analysis of MA in patients with occult/minimally classic nAMD who received monthly intravitreal ranibizumab (0.3 or 0.5 mg) or sham injections for 24 months (M) in MARINA, a phase III trial in treatment-naive patients (NCT00056836). PARTICIPANTS: Seven hundred six patients with nAMD: ranibizumab 0.3 mg, n = 236; 0.5 mg, n = 237; sham, n = 233. METHODS: Macular atrophy, assessed by color fundus photographs/fluorescein angiography, was classified as "within," "adjacent," or "nonadjacent" to the original CNV lesion. Factors associated with MA were assessed by multivariate logistic regression. MAIN OUTCOME MEASURES: Prevalence/incidence of newly detectable MA over time, association with CNV area, MA progression rate, association of MA with visual acuity (VA), changes in CNV/leakage area, and factors predictive of new MA at 24M. RESULTS: At 24M, new MA was detected in 36.8%, 40.4%, and 21.0% of eyes for ranibizumab 0.3 mg, 0.5 mg, and sham, respectively, most frequently within the area of the baseline CNV lesion (93.2%, 85.0%, and 69.0%). Rate of MA progression was similar across arms (∼ 0.3 to 0.4 mm/year). There was strong association between absence of fibrosis and detectable MA (odds ratio, 2.7; 95% confidence interval [CI], 1.29-5.56), whereas an association was not identified between detectable MA and baseline VA, baseline fellow eye atrophy, ranibizumab treatment, or change in leakage/CNV area at 24M. Ranibizumab-treated eyes gained VA with (0.3 mg: 5.3 letters [95% CI, -3.3, 13.8]; 0.5 mg: 9.8 [4.7-15.0]) or without new MA (0.3 mg: 6.4 [4.1-8.6]; 0.5 mg: 8.0 [5.3-10.6]), whereas VA in sham-treated eyes deteriorated with/without new MA (-14.7 [-23.6, -5.8] and -14.0 [-16.9, -11.1], respectively). CONCLUSIONS: New MA was more frequently detected in ranibizumab-treated than sham-treated eyes. Macular atrophy progression was similar across arms. Multivariate analysis showed that absence of fibrosis was the only variable associated with increased MA. Regardless of MA presence/location at baseline or throughout the study, ranibizumab-treated eyes showed clinically significant improvements in VA, whereas VA in sham-treated eyes worsened. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.

Reticular Pseudodrusen Status, ARMS2/HTRA1 Genotype, and Geographic Atrophy Enlargement: Age-Related Eye Disease Study 2 Report 32.

PURPOSE: To determine whether reticular pseudodrusen (RPD) status, ARMS2/HTRA1 genotype, or both are associated with altered geographic atrophy (GA) enlargement rate and to analyze potential mediation of genetic effects by RPD status. DESIGN: Post hoc analysis of an Age-Related Eye Disease Study 2 cohort. PARTICIPANTS: Eyes with GA: n = 771 from 563 participants. METHODS: Geographic atrophy area was measured from fundus photographs at annual visits. Reticular pseudodrusen presence was graded from fundus autofluorescence images. Mixed-model regression of square root of GA area was performed by RPD status, ARMS2 genotype, or both. MAIN OUTCOME MEASURES: Change in square root of GA area. RESULTS: Geographic atrophy enlargement was significantly faster in eyes with RPD (P < 0.0001): 0.379 mm/year (95% confidence interval [CI], 0.329-0.430 mm/year) versus 0.273 mm/year (95% CI, 0.256-0.289 mm/year). Enlargement was also significantly faster in individuals carrying ARMS2 risk alleles (P < 0.0001): 0.224 mm/year (95% CI, 0.198-0.250 mm/year), 0.287 mm/year (95% CI, 0.263-0.310 mm/year), and 0.307 mm/year (95% CI, 0.273-0.341 mm/year) for 0, 1, and 2, respectively. In mediation analysis, the direct effect of ARMS2 genotype was 0.074 mm/year (95% CI, 0.009-0.139 mm/year), whereas the indirect effect of ARMS2 genotype via RPD status was 0.002 mm/year (95% CI, -0.006 to 0.009 mm/year). In eyes with incident GA, RPD presence was not associated with an altered likelihood of central involvement (P = 0.29) or multifocality (P = 0.16) at incidence. In eyes with incident noncentral GA, RPD presence was associated with faster GA progression to the central macula (P = 0.009): 157 µm/year (95% CI, 126-188 µm/year) versus 111 µm/year (95% CI, 97-125 µm/year). Similar findings were observed in the Age-Related Eye Disease Study. CONCLUSIONS: Geographic atrophy enlargement is faster in eyes with RPD and in individuals carrying ARMS2/HTRA1 risk alleles. However, RPD status does not mediate the association between ARMS2/HTRA1 genotype and faster enlargement. Reticular pseudodrusen presence and ARMS2/HTRA1 genotype are relatively independent risk factors, operating by distinct mechanisms. Reticular pseudodrusen presence does not predict central involvement or multifocality at GA incidence but is associated with faster progression toward the central macula. Reticular pseudodrusen status should be considered for improved predictions of enlargement rate. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.

Association of Metformin With the Development of Age-Related Macular Degeneration.

Importance: Age-related macular degeneration (AMD) is a leading cause of blindness with no treatment available for early stages. Retrospective studies have shown an association between metformin and reduced risk of AMD. Objective: To investigate the association between metformin use and age-related macular degeneration (AMD). Design, Setting, and Participants: The Diabetes Prevention Program Outcomes Study is a cross-sectional follow-up phase of a large multicenter randomized clinical trial, Diabetes Prevention Program (1996-2001), to investigate the association of treatment with metformin or an intensive lifestyle modification vs placebo with preventing the onset of type 2 diabetes in a population at high risk for developing diabetes. Participants with retinal imaging at a follow-up visit 16 years posttrial (2017-2019) were included. Analysis took place between October 2019 and May 2022. Interventions: Participants were randomly distributed between 3 interventional arms: lifestyle, metformin, and placebo. Main Outcomes and Measures: Prevalence of AMD in the treatment arms. Results: Of 1592 participants, 514 (32.3%) were in the lifestyle arm, 549 (34.5%) were in the metformin arm, and 529 (33.2%) were in the placebo arm. All 3 arms were balanced for baseline characteristics including age (mean [SD] age at randomization, 49 [9] years), sex (1128 [71%] male), race and ethnicity (784 [49%] White), smoking habits, body mass index, and education level. AMD was identified in 479 participants (30.1%); 229 (14.4%) had early AMD, 218 (13.7%) had intermediate AMD, and 32 (2.0%) had advanced AMD. There was no significant difference in the presence of AMD between the 3 groups: 152 (29.6%) in the lifestyle arm, 165 (30.2%) in the metformin arm, and 162 (30.7%) in the placebo arm. There was also no difference in the distribution of early, intermediate, and advanced AMD between the intervention groups. Mean duration of metformin use was similar for those with and without AMD (mean [SD], 8.0 [9.3] vs 8.5 [9.3] years; P = .69). In the multivariate models, history of smoking was associated with increased risks of AMD (odds ratio, 1.30; 95% CI, 1.05-1.61; P = .02). Conclusions and Relevance: These data suggest neither metformin nor lifestyle changes initiated for diabetes prevention were associated with the risk of any AMD, with similar results for AMD severity. Duration of metformin use was also not associated with AMD. This analysis does not address the association of metformin with incidence or progression of AMD.

Extramacular Drusen and Progression of Age-Related Macular Degeneration: Age Related Eye Disease Study 2 Report 30.

PURPOSE: To identify the prevalence of extramacular drusen and their role in the progression of age-related macular degeneration (AMD). DESIGN: Retrospective analysis of a prospective cohort study. PARTICIPANTS: The study was conducted in 4168 eyes (2998 participants) with intermediate AMD in one or both eyes enrolled in the Age-Related Eye Disease Study 2 (AREDS2), a 5-year multicenter study of nutritional supplements. METHODS: Baseline 3-field 30-degree color photographs were evaluated for drusen characteristics outside the macular grid, including size, area, and location. The characteristics of extramacular drusen were compared with those of drusen within the macula. MAIN OUTCOME MEASURES: Progression rates to late AMD. RESULTS: Although extramacular drusen were observed in 3624 (86.9%) eyes, they represented a small area (< 0.5 mm2) in 50.3% of eyes, with only 17.5% exhibiting an area of > 1 disc area. Eyes with extramacular drusen exhibited larger macular drusen size and area than eyes without extramacular drusen (P < 0.001). Extramacular drusen were not associated with progression to late AMD. The hazard ratio adjusted for baseline age, sex, smoking, AMD severity level, and reticular pseudodrusen for 4043 eyes at risk of developing late AMD over 5 years was 1.17 (95% confidence interval [CI], 0.88-1.54; P = 0.27) for geographic atrophy and 0.96 (95% CI, 0.76-1.2; P = 0.7) for neovascular AMD. CONCLUSIONS: Extramacular drusen are commonly observed in eyes with AMD and are more frequent with an increasing drusen burden within the macula. In eyes with intermediate AMD, extramacular drusen do not confer additional risk to previously identified risk factors in progression to late AMD.

Implementation of a Large-Scale Image Curation Workflow Using Deep Learning Framework.

Purpose: The curation of images using human resources is time intensive but an essential step for developing artificial intelligence (AI) algorithms. Our goal was to develop and implement an AI algorithm for image curation in a high-volume setting. We also explored AI tools that will assist in deploying a tiered approach, in which the AI model labels images and flags potential mislabels for human review. Design: Implementation of an AI algorithm. Participants: Seven-field stereoscopic images from multiple clinical trials. Methods: The 7-field stereoscopic image protocol includes 7 pairs of images from various parts of the central retina along with images of the anterior part of the eye. All images were labeled for field number by reading center graders. The model output included classification of the retinal images into 8 field numbers. Probability scores (0-1) were generated to identify misclassified images, with 1 indicating a high probability of a correct label. Main Outcome Measures: Agreement of AI prediction with grader classification of field number and the use of probability scores to identify mislabeled images. Results: The AI model was trained and validated on 17 529 images and tested on 3004 images. The pooled agreement of field numbers between grader classification and the AI model was 88.3% (kappa, 0.87). The pooled mean probability score was 0.97 (standard deviation [SD], 0.08) for images for which the graders agreed with the AI-generated labels and 0.77 (SD, 0.19) for images for which the graders disagreed with the AI-generated labels (P < 0.0001). Using receiver operating characteristic curves, a probability score of 0.99 was identified as a cutoff for distinguishing mislabeled images. A tiered workflow using a probability score of < 0.99 as a cutoff would include 27.6% of the 3004 images for human review and reduce the error rate from 11.7% to 1.5%. Conclusions: The implementation of AI algorithms requires measures in addition to model validation. Tools to flag potential errors in the labels generated by AI models will reduce inaccuracies, increase trust in the system, and provide data for continuous model development.

Retinal Thickness and Morphology Changes on OCT in Youth with Type 2 Diabetes: Findings from the TODAY Study.

Objective: To evaluate changes in retinal thickness and morphology using OCT in youth with type 2 diabetes (T2D) and to identify systemic biomarkers correlating with these changes. Design: Retrospective subgroup analysis of a prospective study. Participants: Participants who underwent OCT imaging in the Treatment Options for Type 2 Diabetes in Adolescents and Youth (TODAY) trial and its follow-up study TODAY2. Methods: In 2010-2011 (TODAY) and 2017-2018 (TODAY2), 6 × 6-mm macular volume OCT scans were acquired, segmented, and analyzed to generate total retinal thickness, inner retinal thickness, and outer retinal thickness. The main retinal morphologies graded were intraretinal cystoid spaces, subretinal fluid, and posterior vitreous detachment (PVD). Main Outcome Measures: Changes in total and individual retinal layer thickness and development of abnormal vitreomacular morphology between TODAY and TODAY2. Results: Participants had a mean age of 17.9 ± 2.4 years and glycated hemoglobin (HbA1c) of 8.2 ± 2.8% in TODAY and a mean age of 25.0 ± 2.4 years and mean HbA1c of 9.5 ± 2.8% in TODAY2. Longitudinally between assessments, there were overall decreases in outer retinal thickness from 167.2 ± 11.5 microns to 158.4 ± 12.8 microns (P < 0.001) and in photoreceptor thickness from 30.3 ± 2.9 microns to 29.8 ± 4.1 microns (P = 0.04) in the central subfield, while in the inner subfield, we noted a decrease in outer retinal thickness from 150.5 ± 10.1 microns to 144.9 ± 10.5 microns (P < 0.001) and an increase in inner retinal thickness from 136.9 ± 11.5 microns to 137.4 ± 12.6 microns (P = 0.01). Multivariate analysis showed that in the center subfield, HbA1c increases were associated with increases in total retinal thickness (r: 0.67, P = 0.001), whereas fasting glucose was positively correlated with inner retinal thickness (r: 0.02, P = 0.02). In the inner subfield, both systolic (r: -0.22, P < 0.001) and diastolic (r: -0.22, P = 0.003) blood pressures were negatively correlated with total retinal thickness. There was an increase in PVD (18.9%) and cystoid spaces (4.2%). Conclusions: Youth with T2D develop retinal thickness changes on OCT, including increases in total retinal and inner retinal thickness in the center subfield that correlate with HbA1c and fasting glucose, respectively. Taken together with the increased prevalence of abnormal vitreomacular morphology in this cohort at risk, these findings emphasize the importance of controlling risk factors to prevent the development of sight-threatening retinal complications.

Total retinal thickness: a neglected factor in the evaluation of inner retinal thickness.

AIM: To determine whether macular retinal nerve fibre layer (mRNFL) and ganglion cell-inner plexiform layer (GC-IPL) thicknesses vary by ethnicity after accounting for total retinal thickness. METHODS: We included healthy participants from the UK Biobank cohort who underwent macula-centred spectral domain-optical coherence tomography scans. mRNFL and GC-IPL thicknesses were determined for groups from different self-reported ethnic backgrounds. Multivariable regression models adjusting for covariables including age, gender, ethnicity and refractive error were built, with and without adjusting for total retinal thickness. RESULTS: 20237 participants were analysed. Prior to accounting for total retinal thickness, mRNFL thickness was on average 0.9 µm (-1.2, -0.6; p<0.001) lower among Asians and 1.5 µm (-2.3, -0.6; p<0.001) lower among black participants compared with white participants. Prior to accounting for total retinal thickness, the average GC-IPL thickness was 1.9 µm (-2.5, -1.4; p<0.001) lower among Asians compared with white participants, and 2.4 µm (-3.9, -1.0; p=0.001) lower among black participants compared with white participants. After accounting for total retinal thickness, the layer thicknesses were not significantly different among ethnic groups. When considered as a proportion of total retinal thickness, mRNFL thickness was ~0.1 and GC-IPL thickness was ~0.2 across age, gender and ethnic groups. CONCLUSIONS: The previously reported ethnic differences in layer thickness among groups are likely driven by differences in total retinal thickness. Our results suggest using layer thickness ratio (retinal layer thicknesses/total retinal thickness) rather than absolute thickness values when comparing retinal layer thicknesses across groups.

Long-term Outcomes of Adding Lutein/Zeaxanthin and ω-3 Fatty Acids to the AREDS Supplements on Age-Related Macular Degeneration Progression: AREDS2 Report 28.

Importance: After the Age-Related Eye Disease Study 2 (AREDS2) study, the beta carotene component was replaced by lutein/zeaxanthin for the development of the revised AREDS supplement. However, it is unknown if the increased risk of lung cancer observed in those assigned beta carotene persists beyond the conclusion of the AREDS2 trial and if there is a benefit of adding lutein/zeaxanthin to the original AREDS supplement that can be observed with long-term follow-up. Objective: To assess 10-year risk of developing lung cancer and late age-related macular degeneration (AMD). Design, Setting, and Participants: This was a multicenter epidemiologic follow-up study of the AREDS2 clinical trial, conducted from December 1, 2012, to December 31, 2018. Included in the analysis were participants with bilateral or unilateral intermediate AMD for an additional 5 years after clinical trial. Eyes/participants were censored at the time of late AMD development, death, or loss to follow-up. Data were analyzed from November 2019 to March 2022. Interventions: During the clinical trial, participants were randomly assigned primarily to lutein/zeaxanthin and/or ω-3 fatty acids or placebo and secondarily to no beta carotene vs beta carotene and low vs high doses of zinc. In the epidemiologic follow-up study, all participants received AREDS2 supplements with lutein/zeaxanthin, vitamins C and E, and zinc plus copper. Outcomes were assessed at 6-month telephone calls. Analyses of AMD progression and lung cancer development were conducted using proportional hazards regression and logistic regression, respectively. Main Outcomes and Measures: Self-reported lung cancer and late AMD validated with medical records. Results: This study included 3882 participants (mean [SD] baseline age, 72.0 [7.7] years; 2240 women [57.7%]) and 6351 eyes. At 10 years, the odds ratio (OR) of having lung cancer was 1.82 (95% CI, 1.06-3.12; P = .02) for those randomly assigned to beta carotene and 1.15 (95% CI, 0.79-1.66; P = .46) for lutein/zeaxanthin. The hazard ratio (HR) for progression to late AMD comparing lutein/zeaxanthin with no lutein/zeaxanthin was 0.91 (95% CI, 0.84-0.99; P = .02) and comparing ω-3 fatty acids with no ω-3 fatty acids was 1.01 (95% CI, 0.93-1.09; P = .91). When the lutein/zeaxanthin main effects analysis was restricted to those randomly assigned to beta carotene, the HR was 0.80 (95% CI, 0.68-0.92; P = .002). A direct analysis of lutein/zeaxanthin vs beta carotene showed the HR for late AMD was 0.85 (95% CI, 0.73-0.98; P = .02). The HR for low vs high zinc was 1.04 (95% CI, 0.94-1.14; P = .49), and the HR for no beta carotene vs beta carotene was 1.04 (95% CI, 0.94-1.15; P = .48). Conclusions and Relevance: Results of this long-term epidemiologic follow-up study of the AREDS2 cohort suggest that lutein/zeaxanthin was an appropriate replacement for beta carotene in AREDS2 supplements. Beta carotene usage nearly doubled the risk of lung cancer, whereas there was no statistically significant increased risk with lutein/zeaxanthin. When compared with beta carotene, lutein/zeaxanthin had a potential beneficial association with late AMD progression.

Reticular Pseudodrusen: The Third Macular Risk Feature for Progression to Late Age-Related Macular Degeneration: Age-Related Eye Disease Study 2 Report 30.

PURPOSE: To analyze reticular pseudodrusen (RPD) as an independent risk factor for progression to late age-related macular degeneration (AMD), alongside traditional macular risk factors (soft drusen and pigmentary abnormalities) considered simultaneously. DESIGN: Post hoc analysis of 2 clinical trial cohorts: Age-Related Eye Disease Study (AREDS) and AREDS2. PARTICIPANTS: Eyes with no late AMD at baseline in AREDS (6959 eyes, 3780 participants) and AREDS2 (3355 eyes, 2056 participants). METHODS: Color fundus photographs (CFPs) from annual visits were graded for soft drusen, pigmentary abnormalities, and late AMD. Presence of RPD was from grading of fundus autofluorescence images (AREDS2) and deep learning grading of CFPs (AREDS). Proportional hazards regression analyses were performed, considering AREDS AMD severity scales (modified simplified severity scale [person] and 9-step scale [eye]) and RPD presence simultaneously. MAIN OUTCOME MEASURES: Progression to late AMD, geographic atrophy (GA), and neovascular AMD. RESULTS: In AREDS, for late AMD analyses by person, in a model considering the simplified severity scale simultaneously, RPD presence was associated with a higher risk of progression: hazard ratio (HR), 2.15 (95% confidence interval [CI], 1.75-2.64). However, the risk associated with RPD presence differed at different severity scale levels: HR, 3.23 (95% CI, 1.60-6.51), HR, 3.81 (95% CI, 2.38-6.10), HR, 2.28 (95% CI, 1.59-3.27), and HR, 1.64 (95% CI, 1.20-2.24), at levels 0-1, 2, 3, and 4, respectively. Considering the 9-step scale (by eye), RPD presence was associated with higher risk: HR, 2.54 (95% CI, 2.07-3.13). The HRs were 5.11 (95% CI, 3.93-6.66) at levels 1-6 and 1.78 (95% CI, 1.43-2.22) at levels 7 and 8. In AREDS2, by person, RPD presence was not associated with higher risk: HR, 1.18 (95% CI, 0.90-1.56); by eye, it was HR, 1.57 (95% CI, 1.31-1.89). In both cohorts, RPD presence carried a higher risk for GA than neovascular AMD. CONCLUSIONS: Reticular pseudodrusen represent an important risk factor for progression to late AMD, particularly GA. However, the added risk varies markedly by severity level, with highly increased risk at lower/moderate levels and less increased risk at higher levels. Reticular pseudodrusen status should be included in updated AMD classification systems, risk calculators, and clinical trials.

Artificial Intelligence Algorithms in Diabetic Retinopathy Screening.

PURPOSE OF REVIEW: In this review, we focus on artificial intelligence (AI) algorithms for diabetic retinopathy (DR) screening and risk stratification and factors to consider when implementing AI algorithms in the clinic. RECENT FINDINGS: AI algorithms have been adopted, and have received regulatory approval, for automated detection of referable DR with clinically acceptable diagnostic performance. While these metrics are an important first step, performance metrics that go beyond measures of technical accuracy are needed to fully evaluate the impact of AI algorithm on patient outcomes. Recent advances in AI present an exciting opportunity to improve patient care. Using DR as an example, we have reviewed factors to consider in the implementation of AI algorithms in real-world clinical practice. These include real-world evaluation of safety, efficacy, and equity (bias); impact on patient outcomes; ethical, logistical, and regulatory factors.

Redefining the Spectrum of Pentosan Polysulfate Retinopathy: Multimodal Imaging Findings from a Cross-Sectional Screening Study.

PURPOSE: There is growing evidence of a direct association between pentosan polysulfate (PPS) therapy and the development of macular changes. Using standardized visual acuity (VA) testing and multimodal imaging, we investigated the impact of PPS therapy on vision and described an expanded spectrum of imaging findings among PPS users. DESIGN: Cross-sectional screening study. PARTICIPANTS: Thirty-nine patients who were current or recent users of PPS. METHODS: The participants underwent a brief eye examination and answered a comprehensive medical and ophthalmic history questionnaire. Color fundus photography, fundus autofluorescence (FAF), and spectral-domain OCT (SD-OCT) were performed. The images were evaluated by expert graders at Wisconsin Reading Center. Abnormalities were categorized as definite toxicity (DT) if seen on both FAF and SD-OCT and as questionable toxicity (QT) if seen on either FAF or SD-OCT. MAIN OUTCOME MEASURES: ETDRS and Snellen VA, the dosage and duration of PPS exposure, and the prevalence of retinal toxicity on imaging. RESULTS: The mean ETDRS and Snellen VA of the study cohort were 85 letters and 20/22, respectively. The mean PPS daily dose was 282 mg (range, 88-400 mg), whereas the mean cumulative dose was 915 g (range, 19-3650 g) over a mean period of 8.8 years (range, 2 months-25 years). There was evidence of retinopathy in 41% of the eyes; DT was identified in 24 eyes (31%) and QT in 8 eyes (10%). Retinal pigment epithelium (RPE) abnormalities (thickening or thinning or both) were present in all eyes with DT. Retinal pigment epithelium atrophy was seen in 7 eyes (9%). In addition to well-established findings, the unique SD-OCT features of this cohort included interdigitation zone abnormalities and the presence of a flying saucer-type defect. Fundus autofluorescence abnormalities were seen in 24 eyes (30.8%), with 20 (66.7%) of these exhibiting abnormalities located outside the central subfield and extending beyond the arcades. CONCLUSIONS: Findings from the masked grading of multimodal imaging at a centralized reading center suggest a wider phenotypic spectrum of structural abnormalities among patients taking PPS. Macular changes selectively involve the RPE and outer retina, with a range of findings often seen beyond the arcades. The subtle and atypical findings in this cohort should prompt clinicians to consider lowering the threshold for diagnosing PPS retinopathy.