Integrating Machine Learning and Traditional Survival Analysis to Identify Key Predictors of Foveal Involvement in Geographic Atrophy.

Purpose: The purpose of this study was to investigate the incidence of foveal involvement in geographic atrophy (GA) secondary to age-related macular degeneration (AMD), using machine learning to assess the importance of risk factors. Methods: Retrospective, longitudinal cohort study. Patients diagnosed with foveal-sparing GA, having GA size ≥ 0.049 mm² and follow-up ≥ 6 months, were included. Baseline GA area, distance from the fovea, and perilesional patterns were measured using fundus autofluorescence. Optical coherence tomography assessed foveal involvement, structural biomarkers, and outer retinal layers thickness. Onset of foveal involvement was recorded. Foveal survival rates were estimated using Kaplan-Meier curves. Hazard ratios (HRs) were assessed with mixed model Cox regression. Variable Importance (VIMP) was ranked with Random Survival Forests (RSF), with higher scores indicating greater predictive significance. Results: One hundred sixty-seven eyes (115 patients, average age = 75.8 ± 9.47 years) with mean follow-up of 50 ± 29 months, were included in this study. Median foveal survival time was 45 months (95% confidence interval [CI] = 38-55). Incidences of foveal involvement were 26% at 24 months and 67% at 60 months. Risk factors were GA proximity to the fovea (HR = 0.97 per 10-µm increase, 95% CI = 0.96-0.98), worse baseline visual acuity (HR = 1.37 per 0.1 LogMAR increase, 95% CI = 1.21-1.53), and thinner outer nuclear layer (HR = 0.59 per 10-µm increase, 95% CI = 0.46-0.74). RSF analysis confirmed these as main predictors (VIMP = 16.7, P = 0.002; VIMP = 6.2, P = 0.003; and VIMP = 3.4, P = 0.01). Lesser baseline GA area (HR = 1.09 per 1-mm2 increase, 95% CI = 1.01-1.16) and presence of a double layer sign (HR = 0.42, 95% CI = 0.20-0.88) were protective but less influential. Conclusions: This study identifies anatomic and functional factors impacting the risk of foveal involvement in GA. These findings may help identify at-risk patients, enabling tailored preventive strategies.

Mitochondrial retinopathies and optic neuropathies: The impact of retinal imaging on modern understanding of pathogenesis, diagnosis, and management.

Advancements in ocular imaging have significantly broadened our comprehension of mitochondrial retinopathies and optic neuropathies by examining the structural and pathological aspects of the retina and optic nerve in these conditions. This article aims to review the prominent imaging characteristics associated with mitochondrial retinopathies and optic neuropathies, aiming to deepen our insight into their pathogenesis and clinical features. Preceding this exploration, the article provides a detailed overview of the crucial genetic and clinical features, which is essential for the proper interpretation of in vivo imaging. More importantly, we will provide a critical analysis on how these imaging modalities could serve as biomarkers for characterization and monitoring, as well as in guiding treatment decisions. However, these imaging methods have limitations, which will be discussed along with potential strategies to mitigate them. Lastly, the article will emphasize the potential advantages and future integration of imaging techniques in evaluating patients with mitochondrial eye disorders, considering the prospects of emerging gene therapies.

Photoreceptor Integrity in MEWDS: Longitudinal Structure-Function Correlations.

Purpose: The purpose of this study was to investigate structure-function correlations in multiple evanescent white dot syndrome (MEWDS) using microperimetry (MP) and spectral-domain optical coherence tomography (SD-OCT). Methods: Single-center prospective observational study including 14 eyes from 13 patients with MEWDS monitored over a median of 49.5 days (interquartile range = 29-92 days). Investigations focused on best-corrected visual acuity (BCVA), foveal granularity, and the Photoreceptor Reflectivity Ratio (PRR) as a measure of photoreceptor integrity. MP assessed average retinal threshold sensitivity (RTS) and bivariate contour ellipse area (BCEA) for fixation stability. A linear mixed model was used to test associations and interactions among RTS, time, and clinical variables. A hierarchical linear mixed model was used to analyze structure-function relationships, addressing both individual and location-specific variations. Results: Overall, 2340 MP locations were tested. PRR revealed a transient decrease within 30 days post-presentation, indicative of early photoreceptor disruption, followed by a progressive increase, signaling recovery. Significantly lower foveal sensitivity (RTS = 14.8 ± 7.4 vs. 22.5 ± 4.4 decibel [dB], P = 0.04) and increased fixation spread (63% BCEA = 1.26 ± 0.97 vs. 0.48 ± 0.35 deg2, P = 0.06) were noted in eyes with foveal granularity compared to those without. A significant increase in RTS was demonstrated over time (0.066 dB/day, P < 0.001), with a central-to-peripheral gradient of improvement. The interaction between follow-up time and baseline BCVA (P < 0.001) indicated more rapid improvement in eyes with worse initial vision. There was a robust, nonlinear association between PRR and RTS across all tested locations (P < 0.001), becoming asymptotic for sensitivity losses exceeding 20 dB. Conclusions: Photoreceptor reflectivity accurately aligned with visual function in MEWDS on longitudinal examinations. The central-to-peripheral gradient of improvement may suggest specific vulnerabilities underlying the area around the disc.

Ocular complications of SAVI: A unique case of bilateral uveitis and retinal vasculitis.

Purpose: To describe a case of bilateral panuveitis in a patient with Stimulator of Interferon Genes (STING)-Associated Vasculitis with Onset in Infancy (SAVI). Observations: A 45-year-old patient diagnosed with SAVI presented bilateral panuveitis and uncontrolled secondary intraocular hypertension due to structural complications from uveitis. Multimodal imaging revealed the presence of intraretinal fluid and bilateral vasculitis. The patient was started with systemic methotrexate. Conclusions and importance: This case is essential to characterize ocular involvement in patients with SAVI. Awareness of these ocular manifestations is crucial for timely management and improvement of visual prognosis.

Retinal OCT biomarkers associated with reading performance in patients with persistent vs. resolved diabetic macular edema.

BACKGROUND: Recent advancements in imaging technologies, particularly structural optical coherence tomography (OCT), have improved the understanding of diabetic macular edema (DME) pathophysiology and provided valuable biomarkers for disease progression and visual outcomes. This prospective study aimed to investigate the association between specific retinal biomarkers identified through OCT imaging and reading performance metrics in patients with previously treated persistent versus resolved DME and good visual acuity. METHODS: Forty-nine eyes from 35 patients with a history of DME were enrolled. Reading performance was assessed using the Radner reading charts, which include standardized sentences with geometrically progressing print sizes. Structural alterations in the inner and outer retina, as well as the retinal pigment epithelium (RPE), were graded based on OCT images. RESULTS: Reading performance, measured as maximum reading speed, was associated with specific retinal biomarkers. The disruption of the ellipsoid zone (EZ) in the parafoveal region and the presence of disorganization of the inner retinal layers (DRIL) in the parafovea were correlated with reduced reading speed. These associations were independent of the presence of intraretinal or subretinal fluid. CONCLUSIONS: Understanding the relationship between retinal biomarkers and reading performance could contribute to a comprehensive evaluation of visual function and quality of life in patients with DME, leading to better management strategies and treatment outcomes.

Optical coherence tomography (OCT) and OCT-angiography in syndromic versus non-syndromic USH2A-associated retinopathy.

PURPOSE: To compare non-syndromic and syndromic forms of USH2A-related retinitis pigmentosa (RP) by means of structural optical coherence tomography (OCT) and OCT-angiography (OCTA). METHODS: Observational, cross-sectional, multicenter study. All patients underwent best corrected visual acuity (BCVA) measurement, OCT (Spectralis HRA + OCT, Heidelberg Engineering) and OCTA (OCT DRI Topcon Triton, Topcon Corporation). We compared subfoveal choroidal thickness (SCT), choroidal vascularity index (CVI), presence of cystroid macular edema (CME), macular vessel density (VD) at the superficial and deep capillary plexa, as well as VD of the radial peripapillary capillary (RPC) network, between syndromic and non-syndromic patients with USH2A-associated retinopathy. RESULTS: Thirty-four eyes from 18 patients (7 females) were included. Thirteen patients (72.2%) were affected by Usher syndrome type 2, whereas the remaining 5 subjects (27.8%) had non-syndromic retinitis pigmentosa (nsRP). Syndromic patients were younger than nsRP (p = 0.01) and had a worse visual acuity than those with the exclusively retinal phenotype. Patients with Usher syndrome type 2 had a higher prevalence of CME and a thicker choroid compared to nsRP, although these results were not statistically significant (p = 0.775 and p = 0.122, respectively). Similarly, none of the other quantitative OCT and OCTA parameters was statistically different between the two groups. CONCLUSIONS: Despite their younger age, patients with Usher syndrome type 2 displayed similar choroidal and microvascular changes compared to those with nsRP.

Rate and Predictors of Misclassification of Active Diabetic Macular Edema as Detected by an Automated Retinal Image Analysis System.

INTRODUCTION: The aim of this work is to estimate the sensitivity, specificity, and misclassification rate of an automated retinal image analysis system (ARIAS) in diagnosing active diabetic macular edema (DME) and to identify factors associated with true and false positives. METHODS: We conducted a cross-sectional study of prospectively enrolled patients with diabetes mellitus (DM) referred to a tertiary medical retina center for screening or management of DME. All patients underwent two-field fundus photography (macula- and disc-centered) with a true-color confocal camera; images were processed by EyeArt V.2.1.0 (Woodland Hills, CA, USA). Active DME was defined as the presence of intraretinal or subretinal fluid on spectral-domain optical coherence tomography (SD-OCT). Sensitivity and specificity and their 95% confidence intervals (CIs) were calculated. Variables associated with true (i.e., DME labeled as present by ARIAS + fluid on SD-OCT) and false positives (i.e., DME labeled as present by ARIAS + no fluid on SD-OCT) of active DME were explored. RESULTS: A total of 298 eyes were included; 92 eyes (31%) had active DME. ARIAS sensitivity and specificity were 82.61% (95% CI 72.37-89.60) and 84.47% (95% CI 78.34-89.10). The misclassification rate was 16%. Factors associated with true positives included younger age (p = 0.01), shorter DM duration (p = 0.006), presence of hard exudates (p = 0.005), and microaneurysms (p = 0.002). Factors associated with false positives included longer DM duration (p = 0.01), worse diabetic retinopathy severity (p = 0.008), history of inactivated DME (p < 0.001), and presence of hard exudates (p < 0.001), microaneurysms (p < 0.001), or epiretinal membrane (p = 0.06). CONCLUSIONS: The sensitivity of ARIAS was diminished in older patients and those without DME-related fundus lesions, while the specificity was reduced in cases with a history of inactivated DME. ARIAS performed well in screening for naïve DME but is not effective in surveillance inactivated DME.

Structural OCT and OCT angiography biomarkers associated with the development and progression of geographic atrophy in AMD.

BACKGROUND: Geographic atrophy (GA) is an advanced, irreversible, and progressive form of age-related macular degeneration (AMD). Structural optical coherence tomography (OCT) and OCT angiography (OCTA) have been largely used to characterize this stage of AMD and, more importantly, to define biomarkers associated with the development and progression of GA in AMD. METHODS: Articles pertaining to OCT and OCTA biomarkers related to the development and progression of GA with relevant key words were used to search in PubMed, Researchgate, and Google Scholar. The articles were selected based on their relevance, reliability, publication year, published journal, and accessibility. RESULTS: Previous reports have highlighted various OCT and OCTA biomarkers linked to the onset and advancement of GA. These biomarkers encompass characteristics such as the size, volume, and subtype of drusen, the presence of hyperreflective foci, basal laminar deposits, incomplete retinal pigment epithelium and outer retinal atrophy (iRORA), persistent choroidal hypertransmission defects, and the existence of subretinal drusenoid deposits (also referred to as reticular pseudodrusen). Moreover, biomarkers associated with the progression of GA include thinning of the outer retina, photoreceptor degradation, the distance between retinal pigment epithelium and Bruch's membrane, and choriocapillaris loss. CONCLUSION: The advent of novel treatment strategies for GA underscores the heightened need for prompt diagnosis and precise monitoring of individuals with this condition. The utilization of structural OCT and OCTA becomes essential for identifying distinct biomarkers associated with the initiation and progression of GA.

Global experience of faricimab in clinical settings - a review.

INTRODUCTION: Faricimab is a bispecific antibody that acts to reduce neoangiogenesis in exudative retinal vascular disorders. It is approved for use in neovascular age-related macular degeneration and diabetic macular edema. We review the published efficacy and safety of faricimab in clinical settings. AREAS COVERED: A comprehensive literature review was conducted. Based on the 14 published real-world studies, 1127 patients (1204 eyes) were treated with faricimab. The majority of studies (14) included pre-treated patients. Most studies (13) showed central macular thickness improvement. However visual acuity improved in only half of the studies analyzed. Four studies demonstrated an extension of the treatment. Only 4 eyes (0.33%) reported intraocular inflammation and 3 eyes (0.24%) reported retinal pigment epithelial tear. EXPERT OPINION: The clinical experience with faricimab to date has the potential to provide a stable visual outcome with reduced treatment burden in cases that are resistant to other approved anti-VEGF agents. There are no major safety concerns based on this data analysis.

Distinct Pathways of Macular Atrophy in Type 3 Macular Neovascularization Associated With AMD.

Purpose: To explore the occurrence of macular atrophy (MA) in eyes with age-related macular degeneration (AMD)-associated Type 3 macular neovascularization (MNV) treated with anti-vascular endothelial growth factor (anti-VEGF) therapy. Importantly, we aimed at describing the existence of separate pathways leading to MA. Methods: We analyzed 41 participants (41 eyes) with treatment-naïve Type 3 MNV who were followed up for a duration of 12 months after beginning the anti-VEGF therapy. At the one-year follow-up visit, optical coherence tomography (OCT) scans were reviewed for the presence of MA. MA regions of interest (ROIs) were selected and traced back to their original dominant baseline lesion (i.e., precursor) through previous serially captured OCT scans. Baseline lesions included precursors associated with the development and exudation of MNV and causes external to the neovascularization itself. Results: At the one-year follow-up visit, MA was graded to be present in 38 (92.7%) out of 41 eyes. These 78 MA ROIs were divided into two subgroups according to the precursor lesion, yielding a group of 53 MA lesions with precursors associated with the development and exudation of MNV (i.e., MA caused by physical harm from Type 3 neovessels, collapse of a serous pigment epithelium detachment, and fibrosis) and 25 MA regions with precursors external to the neovascularization itself (i.e., MA caused by drusen or subretinal drusenoid deposits). Conclusions: Eyes with Type 3 MNV are commonly complicated by MA and precursors of MA include causes associated with the development and exudation of MNV, as well as lesions unrelated to the neovascularization process itself.

Enhancing Diabetic Macular Edema Treatment Outcomes: Exploring the ESASO Classification and Structural OCT Biomarkers.

INTRODUCTION: This study assessed the European School of Advanced Studies in Ophthalmology (ESASO) classification's prognostic value for diabetic macular edema (DME) in predicting intravitreal therapy outcomes. METHODS: In this retrospective, multicenter study, patients aged > 50 years with type 1 or 2 diabetes and DME received intravitreal antivascular endothelial growth factor (anti-VEGF) agents (ranibizumab, bevacizumab, and aflibercept) or steroids (dexamethasone). The primary outcome was visual acuity (VA) change post-treatment, termed as functional response, measured 4-6 weeks post-third anti-VEGF or 12-16 weeks post-steroid injection, stratified by initial DME stage. RESULTS: Of the 560 eyes studied (62% male, mean age 66.7 years), 31% were classified as stage 1 (early), 50% stage 2 (advanced), 17% stage 3 (severe), and 2% stage 4 (atrophic). Visual acuity (VA; decimal) improved by 0.12-0.15 decimals in stages 1-2 but only 0.03 decimal in stage 3 (all p < 0.0001) and 0.01 in stage 4 (p = 0.38). Even in eyes with low baseline VA ≤ 0.3, improvements were significant only in stages 1 and 2 (0.12 and 0.17 decimals, respectively). Central subfield thickness (CST) improvement was greatest in stage 3 (-229 µm, 37.6%, p < 0.0001), but uncorrelated with VA gains, unlike stages 1 and 2 (respectively: -142 µm, 27.4%; - 5 µm, 12%; both p < 0.0001). Stage 4 showed no significant CST change. Baseline disorganization of retinal inner layers and focal damage of the ellipsoid zone/external limiting membrane did not influence VA improvement in stages 1 and 2. Treatment patterns varied, with 61% receiving anti-VEGF and 39% dexamethasone, influenced by DME stage, with no significant differences between therapeutic agents. CONCLUSION: The ESASO classification, which views the retina as a neurovascular unit and integrates multiple biomarkers, surpasses single biomarkers in predicting visual outcomes. Significant functional improvement occurred only in stages 1 and 2, suggesting reversible damage, whereas stages 3 and 4 likely reflect irreversible damage.

Central Bouquet Hemorrhages in Pathologic Myopia: Clinical Characteristics and Prognostic Relevance.

PURPOSE: To compare the clinical implications of central bouquet hemorrhages (CBHs) to primarily subretinal hemorrhages, both occurring in the setting of pathologic myopia with lacquer crack formation. DESIGN: Multicenter retrospective cohort study. PARTICIPANTS: Twenty-five eyes (11 primarily subretinal hemorrhages and 14 CBH) were monitored over a median of 35 (interquartile range [IQR], 9.50-54) months. MAIN OUTCOMES MEASURES: Comprehensive ophthalmic examinations and OCT were reviewed. The study employed linear mixed-effects models to compare the impact of CBH versus primarily subretinal hemorrhages on baseline visual acuity (VA), rate of VA improvement, and final VA, adjusting for the follow-up period. Times of hemorrhages reabsorbtion and rate of ellipsoid zone (EZ) layer disruption on OCT were recorded. RESULTS: Eyes with CBH exhibited significantly worse baseline VA (0.93 ± 0.45 logarithm of the minimum angle of resolution [logMAR]; 20/160 Snellen vs. 0.36 ± 0.26 logMAR [20/50 Snellen], P < 0.001), a slower rate of VA improvement (P = 0.04), and a trend toward worse final VA (0.48 ± 0.47 logMAR [20/60 Snellen] vs. 0.16 ± 0.16 logMAR [20/30 Snellen], P = 0.06) compared with eyes with primarily subretinal hemorrhages. The CBH group experienced longer median reabsorption times (10 [IQR, 4.6-23.3] months vs. 2.3 [IQR, 2-3.2] months), and a higher prevalence of EZ layer disruption (86% vs. 0%), than the group with primarily subretinal hemorrhages. Central bouquet hemorrhage reabsorption was followed by the appearance of vertical hyperreflective lines in the central fovea in 67% of eyes, persisting for up to 6 years of follow-up. CONCLUSIONS: Central bouquet hemorrhage signifies a distinct condition in pathologic myopia, characterized by worse visual outcomes, prolonged structural impact, and possible irreversible damage, compared with primarily subretinal hemorrhages. Central bouquet hemorrhage regression should be taken into account in the differential diagnosis of vertical hyperreflective lesions in the central fovea on OCT in eyes with pathologic myopia. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Clinical and Imaging Biomarkers Associated with Outer Retinal Atrophy Onset in Exudative Age-Related Macular Degeneration: A Real-Word Prospective Study.

INTRODUCTION: Macular neovascularization (MNV) secondary to age-related macular degeneration (AMD) is well managed by anti-vascular endothelial growth factor (anti-VEGF) intravitreal injections. However, outer retinal atrophy represents an unavoidable occurrence detected during follow-up. Several imaging metrics have been proposed as clinically relevant in stratifying the risk of onset of outer retinal atrophy. The main goal of this study is to evaluate the impact of noninvasive imaging metrics on the assessment of outer retinal atrophy onset in a large cohort of eyes with neovascular AMD managed in a real-world setting. METHODS: This study was a prospective, observational, case series. We included patients affected by newly diagnosed neovascular AMD, requiring anti-VEGF intravitreal injections. We collected clinical and imaging data, with a planned follow-up of 24 months. The multimodal imaging protocol included optical coherence tomography, optical coherence tomography angiography, and fundus autofluorescence. We collected noninvasive imaging metrics and we assessed the relationship with the morphological and functional outcome evaluated at 12-month and 24-month time points. RESULTS: We included 370 eyes of 370 patients with exudative AMD (210 male; mean age 79 ± 8 years). MNV were classified as follows: type 1, 198 (54%); type 2, 89 (24%); polypoidal choroidal vasculopathy, 29 (7%); and type 3, 54 (15%). A total of 120 out of 370 eyes (33%) showed complete outer retinal atrophy at the end of the 2-year follow-up. The presence of intraretinal fluid, thinning of the Sattler choroidal layer, late anti-VEGF switch, the overall number of anti-VEGF injections, and the perfusion characteristics of the MNV were found to be the most relevant factors associated with the onset of outer retinal atrophy. The other collected metrics were found to be less clinically relevant, also showing no cumulative effect in the multivariate analysis (p > 0.05). CONCLUSIONS: We identified imaging metrics significantly associated with the 2-year risk onset of outer retinal atrophy. These metrics might pave the way for the development of future customized anti-VEGF treatment strategies.

Macular Neovascularization Secondary to Subclinical Angioid Streaks in Age-Related Macular Degeneration: Treatment Response to Anti-VEGF at 2-Year Follow-up.

INTRODUCTION: To characterize the response to antivascular endothelial growth factor (VEGF) treatment of macular neovascularization (MNV) secondary to age-related macular degeneration (AMD) with subclinical angioid streaks (AS) during a 2-year follow-up. METHODS: Retrospective, longitudinal, case-control, and multicentric study. Among a cohort of neovascular AMD population, we selected patients with subclinical AS and treatment-naïve MNV treated with anti-VEGF for a 2-year follow-up. An age- and sex-matched control group with treatment-naïve MNV secondary to AMD without subclinical AS was selected. Demographics and differences in treatment response (i.e., number of injections needed, anatomical and functional outcomes) between the two groups were analyzed. RESULTS: Among 102 eyes of 102 patients with neovascular AMD, 34 eyes of 34 patients (82 ± 6 years old) were included in the subclinical AS group, whereas 68 eyes of 68 patients (81 ± 6 years old, p = 0.342) in the control group. All eyes with subclinical AS presented RPD compared to 56% of eyes without subclinical AS (p < 0.001). During the 2-year follow-up, eyes with subclinical AS needed more injections (10.6 ± 3.2 vs 8.3 ± 3.1 injections for eyes with and without subclinical AS, respectively, p < 0.001). Visual acuity (VA) decreased during the treatment (from 0.53 ± 0.37 at the baseline to 0.69 ± 0.45 LogMAR at 2-year follow-up, p = 0.044) in eyes with subclinical AS; no VA changes were observed in the control group (p = 0.798). RPE atrophy at the end of the 2-year follow-up affected 74% of cases with subclinical AS and 29% of cases of the control group (p < 0.001). CONCLUSIONS: MNVs secondary to AMD with subclinical AS are characterized by worse functional and anatomical outcomes after 2-year anti-VEGF treatment compared to MNV secondary to AMD without subclinical AS, supporting the different pathophysiological mechanisms involved in this recently described AMD phenotype.

Multimodal Imaging of Vitreo-Retinal Lymphoma: A Comprehensive Review.

PURPOSE: Vitreoretinal lymphoma (VRL) is a rare lymphoma affecting the vitreous and the retina. Clinical diagnosis is challenging and often delayed and may lead to aggravated prognosis. This study aims to review multimodal imaging findings in VRL. METHODS: We performed a comprehensive narrative review of the multimodal imaging findings that might be useful in the detection of VRL lesions. RESULTS: The most frequent ocular manifestations of VRL are vitritis, and retinal and sub-retinal Pigmented Epithelium (RPE) infiltrations. Color Fundus Photography (CFP) detects vitreous haze, optic nerve, retinal and sub-RPE infiltration. Ultra-wide field imaging allows visualization of different patterns of vitreous haze and monitoring of VRL evolution through the detection of chorio-retinal atrophy (CRA). Fundus Autofluorescence shows granular hypo- and hyper-autofluorescent pattern. Optical Coherence Tomography (OCT) reveals vitreous cells, vertical hyper-reflective lesions and sub-RPE infiltrates. Fluorescein Angiography (FA) shows hypo or hyperfluorescent round lesions at the late stages of the examination, while Indocyanine Green Angiography (ICGA) detects round areas of focal hypo-fluorescence in the early phases that gradually enlarge in the late phases. B-scan ultrasonography detects vitreous opacities and homogeneous hyperreflective corpuscular material in the vitreous, and is a strongly recommended tool in suspecting VRL and is particularly useful when vitreous haze is impeding retinal examination. CONCLUSION: Diagnostic vitrectomy with cytopathological analysis remains the gold standard for VRL diagnosis, however multimodal imaging allows the identification of suggestive retinal and vitreal lesions for early suspicion, diagnosis, and treatment and monitoring disease progression and response to treatment.

Assessing Diabetic Retinopathy Staging With AI: A Comparative Analysis Between Pseudocolor and LED Imaging.

Purpose: To compare the diagnostic performance of artificial intelligence (AI)-based diabetic retinopathy (DR) staging system across pseudocolor, simulated white light (SWL), and light-emitting diode (LED) camera imaging modalities. Methods: A cross-sectional investigation involved patients with diabetes undergoing imaging with an iCare DRSplus confocal LED camera and an Optos confocal, ultra-widefield pseudocolor camera, with and without SWL. Macula-centered and optic nerve-centered 45 × 45-degree photographs were processed using EyeArt v2.1. Human graders established the ground truth (GT) for DR severity on dilated fundus exams. Sensitivity and weighted Cohen's weighted kappa (wκ) were calculated. An ordinal generalized linear mixed model identified factors influencing accurate DR staging. Results: The study included 362 eyes from 189 patients. The LED camera excelled in identifying sight-threatening DR stages (sensitivity = 0.83, specificity = 0.95 for proliferative DR) and had the highest agreement with the GT (wκ = 0.71). The addition of SWL to pseudocolor imaging resulted in decreased performance (sensitivity = 0.33, specificity = 0.98 for proliferative DR; wκ = 0.55). Peripheral lesions reduced the likelihood of being staged in the same or higher DR category by 80% (P < 0.001). Conclusions: Pseudocolor and LED cameras, although proficient, demonstrated non-interchangeable performance, with the LED camera exhibiting superior accuracy in identifying advanced DR stages. These findings underscore the importance of implementing AI systems trained for ultra-widefield imaging, considering the impact of peripheral lesions on correct DR staging. Translational Relevance: This study underscores the need for artificial intelligence-based systems specifically trained for ultra-widefield imaging in diabetic retinopathy assessment.

Phenotypic characterization of predictors for development and progression of geographic atrophy using optical coherence tomography.

PURPOSE: To evaluate the impact of optical coherence tomography (OCT) phenotypes preceding atrophy related to age-related macular degeneration (AMD) on the progression of atrophic lesions. METHODS: In this observational retrospective cohort study, a total of 70 eyes of 60 consecutive patients with intermediate AMD with a minimum follow-up of 24 months were included. The atrophy was quantified using fundus autofluorescence, also considering the directionality of atrophy as centrifugal and centripetal progression rates.Main outcome measures were geographic atrophy (GA) progression rate (mm2/year) and square root-transformation GA (mm2/year). RESULTS: The best-fit model for GA (OR: 1.81, p<0.001) and square root-transformation GA (OR: 1.36, p<0.001) areas revealed that the main baseline predictor was the presence of an RPE-basal lamina-(BL)-Bruch's membrane (BrM) splitting. Large drusen at baseline appeared protective for the GA area lesion expansion over time (OR: 0.52, p<0.001) when considered with other confounders. CONCLUSION: A thin RPE-BL-BrM splitting without evidence of neovascularization on OCT angiography likely represents an OCT signature for late basal laminar deposits. Identifying this phenotype can help identify individuals with a higher risk of rapid progression and atrophy expansion.