The Clinical Usefulness of a Glaucoma Polygenic Risk Score in 4 Population-Based European Ancestry Cohorts.

PURPOSE: We used a polygenic risk score (PRS) to identify high-risk groups for primary open-angle glaucoma (POAG) within population-based cohorts. DESIGN: Secondary analysis of 4 prospective population-based studies. PARTICIPANTS: We included four European-ancestry cohorts: the United States-based Nurses' Health Study, Nurses' Health Study 2, and the Health Professionals Follow-up Study and the Rotterdam Study (RS) in The Netherlands. The United States cohorts included female nurses and male health professionals ≤ 55 years of age. The RS included residents ≤ 45 years of age living in Rotterdam, The Netherlands. METHODS: Polygenic risk score weights were estimated by applying the lassosum method on imputed genotype and phenotype data from the UK Biobank. This resulted in 144 020 variants, single nucleotide polymorphism and insertions or deletions, with nonzero ßs that we used to calculate a PRS in the target populations. Using multivariable Cox proportional hazard models, we estimated the relationship between the standardized PRS and relative risk for POAG. Additionally, POAG prediction was tested by calculating these models' concordance (Harrell's C statistic). Finally, we assessed the association between PRS tertiles and glaucoma-related traits. MAIN OUTCOME MEASURES: The relative risk for POAG and Harrell's C statistic. RESULTS: Among 1046 patients and 38 809‬ control participants, the relative risk (95% confidence interval) for POAG for participants in the highest PRS quintile was 3.99 (3.08-5.18) times higher in the United States cohorts and 4.89 (2.93-8.17) times higher in the RS, compared with participants with median genetic risk (third quintile). Combining age, sex, intraocular pressure of more than 25 mmHg, and family history resulted in a meta-analyzed concordance of 0.75 (95% CI, 0.73-0.75). Adding the PRS to this model improved the concordance to 0.82 (95% CI, 0.80-0.84). In a meta-analysis of all cohorts, patients in the highest tertile showed a larger cup-to-disc ratio at diagnosis, by 0.10 (95% CI, 0.06 0.14), and a 2.07-fold increased risk of requiring glaucoma surgery (95% CI, 1.19-3.60). CONCLUSIONS: Incorporating a PRS into a POAG predictive model improves identification concordance from 0.75 up to 0.82, supporting its potential for guiding more cost-effective screening strategies. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Pegcetacoplan Treatment and Consensus Features of Geographic Atrophy Over 24 Months.

Importance: Despite widespread availability and consensus on its advantages for detailed imaging of geographic atrophy (GA), spectral-domain optical coherence tomography (SD-OCT) might benefit from automated quantitative OCT analyses in GA diagnosis, monitoring, and reporting of its landmark clinical trials. Objective: To analyze the association between pegcetacoplan and consensus GA SD-OCT end points. Design, Setting, and Participants: This was a post hoc analysis of 11 614 SD-OCT volumes from 936 of the 1258 participants in 2 parallel phase 3 studies, the Study to Compare the Efficacy and Safety of Intravitreal APL-2 Therapy With Sham Injections in Patients With Geographic Atrophy (GA) Secondary to Age-Related Macular Degeneration (OAKS) and Study to Compare the Efficacy and Safety of Intravitreal APL-2 Therapy With Sham Injections in Patients With Geographic Atrophy (GA) Secondary to Age-Related Macular Degeneration (DERBY). OAKS and DERBY were 24-month, multicenter, randomized, double-masked, sham-controlled studies conducted from August 2018 to July 2020 among adults with GA with total area 2.5 to 17.5 mm2 on fundus autofluorescence imaging (if multifocal, at least 1 lesion ≥1.25 mm2). This analysis was conducted from September to December 2023. Interventions: Study participants received pegcetacoplan, 15 mg per 0.1-mL intravitreal injection, monthly or every other month, or sham injection monthly or every other month. Main Outcomes and Measures: The primary end point was the least squares mean change from baseline in area of retinal pigment epithelium and outer retinal atrophy in each of the 3 treatment arms (pegcetacoplan monthly, pegcetacoplan every other month, and pooled sham [sham monthly and sham every other month]) at 24 months. Feature-specific area analysis was conducted by Early Treatment Diabetic Retinopathy Study (ETDRS) regions of interest (ie, foveal, parafoveal, and perifoveal). Results: Among 936 participants, the mean (SD) age was 78.5 (7.22) years, and 570 participants (60.9%) were female. Pegcetacoplan, but not sham treatment, was associated with reduced growth rates of SD-OCT biomarkers for GA for up to 24 months. Reductions vs sham in least squares mean (SE) change from baseline of retinal pigment epithelium and outer retinal atrophy area were detectable at every time point from 3 through 24 months (least squares mean difference vs pooled sham at month 24, pegcetacoplan monthly: -0.86 mm2; 95% CI, -1.15 to -0.57; P < .001; pegcetacoplan every other month: -0.69 mm2; 95% CI, -0.98 to -0.39; P < .001). This association was more pronounced with more frequent dosing (pegcetacoplan monthly vs pegcetacoplan every other month at month 24: -0.17 mm2; 95% CI, -0.43 to 0.08; P = .17). Stronger associations were observed in the parafoveal and perifoveal regions for both pegcetacoplan monthly and pegcetacoplan every other month. Conclusions and Relevance: These findings offer additional insight into the potential effects of pegcetacoplan on the development of GA, including potential effects on the retinal pigment epithelium and photoreceptors. Trial Registration: ClinicalTrials.gov Identifiers: NCT03525600 and NCT03525613.

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3500 Inherited Retinal Disease Patients from the United Kingdom.

Purpose: To quantify relevant fundus autofluorescence (FAF) image features cross-sectionally and longitudinally in a large cohort of inherited retinal diseases (IRDs) patients. Design: Retrospective study of imaging data (55-degree blue-FAF on Heidelberg Spectralis) from patients. Participants: Patients with a clinical and molecularly confirmed diagnosis of IRD who have undergone FAF 55-degree imaging at Moorfields Eye Hospital (MEH) and the Royal Liverpool Hospital (RLH) between 2004 and 2019. Methods: Five FAF features of interest were defined: vessels, optic disc, perimacular ring of increased signal (ring), relative hypo-autofluorescence (hypo-AF) and hyper-autofluorescence (hyper-AF). Features were manually annotated by six graders in a subset of patients based on a defined grading protocol to produce segmentation masks to train an AI model, AIRDetect, which was then applied to the entire MEH imaging dataset. Main Outcome Measures: Quantitative FAF imaging features including area in mm 2 and vessel metrics, were analysed cross-sectionally by gene and age, and longitudinally to determine rate of progression. AIRDetect feature segmentation and detection were validated with Dice score and precision/recall, respectively. Results: A total of 45,749 FAF images from 3,606 IRD patients from MEH covering 170 genes were automatically segmented using AIRDetect. Model-grader Dice scores for disc, hypo-AF, hyper-AF, ring and vessels were respectively 0.86, 0.72, 0.69, 0.68 and 0.65. The five genes with the largest hypo-AF areas were CHM , ABCC6 , ABCA4 , RDH12 , and RPE65 , with mean per-patient areas of 41.5, 30.0, 21.9, 21.4, and 15.1 mm 2 . The five genes with the largest hyper-AF areas were BEST1 , CDH23 , RDH12 , MYO7A , and NR2E3 , with mean areas of 0.49, 0.45, 0.44, 0.39, and 0.34 mm 2 respectively. The five genes with largest ring areas were CDH23 , NR2E3 , CRX , EYS and MYO7A, with mean areas of 3.63, 3.32, 2.84, 2.39, and 2.16 mm 2 . Vessel density was found to be highest in EFEMP1 , BEST1 , TIMP3 , RS1 , and PRPH2 (10.6%, 10.3%, 9.8%, 9.7%, 8.9%) and was lower in Retinitis Pigmentosa (RP) and Leber Congenital Amaurosis genes. Longitudinal analysis of decreasing ring area in four RP genes ( RPGR, USH2A, RHO, EYS ) found EYS to be the fastest progressor at -0.18 mm 2 /year. Conclusions: We have conducted the first large-scale cross-sectional and longitudinal quantitative analysis of FAF features across a diverse range of IRDs using a novel AI approach.

Deep-learning automated quantification of longitudinal OCT scans demonstrates reduced RPE loss rate, preservation of intact macular area and predictive value of isolated photoreceptor degeneration in geographic atrophy patients receiving C3 inhibition treatment.

OBJECTIVE: To evaluate the role of automated optical coherence tomography (OCT) segmentation, using a validated deep-learning model, for assessing the effect of C3 inhibition on the area of geographic atrophy (GA); the constituent features of GA on OCT (photoreceptor degeneration (PRD), retinal pigment epithelium (RPE) loss and hypertransmission); and the area of unaffected healthy macula.To identify OCT predictive biomarkers for GA growth. METHODS: Post hoc analysis of the FILLY trial using a deep-learning model for spectral domain OCT (SD-OCT) autosegmentation. 246 patients were randomised 1:1:1 into pegcetacoplan monthly (PM), pegcetacoplan every other month (PEOM) and sham treatment (pooled) for 12 months of treatment and 6 months of therapy-free monitoring. Only participants with Heidelberg SD-OCT were included (n=197, single eye per participant).The primary efficacy endpoint was the square root transformed change in area of GA as complete RPE and outer retinal atrophy (cRORA) in each treatment arm at 12 months, with secondary endpoints including RPE loss, hypertransmission, PRD and intact macular area. RESULTS: Eyes treated PM showed significantly slower mean change of cRORA progression at 12 and 18 months (0.151 and 0.277 mm, p=0.0039; 0.251 and 0.396 mm, p=0.039, respectively) and RPE loss (0.147 and 0.287 mm, p=0.0008; 0.242 and 0.410 mm, p=0.00809). PEOM showed significantly slower mean change of RPE loss compared with sham at 12 months (p=0.0313). Intact macular areas were preserved in PM compared with sham at 12 and 18 months (p=0.0095 and p=0.044). PRD in isolation and intact macula areas was predictive of reduced cRORA growth at 12 months (coefficient 0.0195, p=0.01 and 0.00752, p=0.02, respectively) CONCLUSION: The OCT evidence suggests that pegcetacoplan slows progression of cRORA overall and RPE loss specifically while protecting the remaining photoreceptors and slowing the progression of healthy retina to iRORA.

Evaluating the Effects of C3 Inhibition on Geographic Atrophy Progression from Deep-Learning OCT Quantification: A Split-Person Study.

INTRODUCTION: To evaluate the effect pegcetacoplan, a C3 and C3b inhibitor, on the rate of progression of geographic atrophy (GA) as assessed by spectral domain optical coherence tomography (SD-OCT) using a split-person study design and deep-learning quantification. METHODS: A post hoc analysis of phase 2 FILLY trial data comparing study (treated monthly, treated every other month and sham-treated) and fellow (untreated) eyes in a split-person study design was performed. This analysis included 288 eyes from 144 patients with bilateral GA from the FILLY phase 2 trial (Clinical Trials identifier: NCT02503332). Only patients with bilateral GA and without evidence of choroidal neovascularisation in either eye were included. Patient study eyes were treated with sham injections or with pegcetacoplan monthly (PM) or every other month (PEOM) for 12 months. SD-OCT scans of study and fellow eyes taken at baseline and 12 months were used for the analysis. The main outcomes were the annual change in the area of retinal pigment epithelial and outer retinal atrophy (RORA), its constituent features (photoreceptor degeneration [PRD], retinal pigment epithelium [RPE] loss, hypertransmission) and intact macula as compared to the untreated fellow eye. RESULTS: Annual GA growth was reduced in eyes treated with PM versus untreated fellow eyes for OCT features, including RORA (study eye 0.792 vs. fellow eye 1.13 mm2; P = 0.003), PRD (0.739 vs. 1.23 mm2; P = 0.015), RPE-loss (0.789 vs. 1.17 mm2; P = 0.007) and intact macula (- 0.735 vs. - 1.29 mm2; P = 0.011). Similar (but not statistically significant) trends were observed with the PEOM treatment or when GA was quantified with fundus autofluorescence (FAF). The sham treatment demonstrated no effect. Pearson correlation coefficients showed concordance in the enlargement rate of GA between the study and fellow eyes in the sham (R = 0.64) and PEOM (R = 0.68) groups, but not in the PM group (R = 0.21). CONCLUSIONS: Pegcetacoplan-treated eyes demonstrated a reduction in spatial GA progression compared to their untreated counterparts. This effect was more evident on OCT than with FAF. TRIAL REGISTRATION: Clinical Trials identifier: NCT02503332.

Development and international validation of custom-engineered and code-free deep-learning models for detection of plus disease in retinopathy of prematurity: a retrospective study.

BACKGROUND: Retinopathy of prematurity (ROP), a leading cause of childhood blindness, is diagnosed through interval screening by paediatric ophthalmologists. However, improved survival of premature neonates coupled with a scarcity of available experts has raised concerns about the sustainability of this approach. We aimed to develop bespoke and code-free deep learning-based classifiers for plus disease, a hallmark of ROP, in an ethnically diverse population in London, UK, and externally validate them in ethnically, geographically, and socioeconomically diverse populations in four countries and three continents. Code-free deep learning is not reliant on the availability of expertly trained data scientists, thus being of particular potential benefit for low resource health-care settings. METHODS: This retrospective cohort study used retinal images from 1370 neonates admitted to a neonatal unit at Homerton University Hospital NHS Foundation Trust, London, UK, between 2008 and 2018. Images were acquired using a Retcam Version 2 device (Natus Medical, Pleasanton, CA, USA) on all babies who were either born at less than 32 weeks gestational age or had a birthweight of less than 1501 g. Each images was graded by two junior ophthalmologists with disagreements adjudicated by a senior paediatric ophthalmologist. Bespoke and code-free deep learning models (CFDL) were developed for the discrimination of healthy, pre-plus disease, and plus disease. Performance was assessed internally on 200 images with the majority vote of three senior paediatric ophthalmologists as the reference standard. External validation was on 338 retinal images from four separate datasets from the USA, Brazil, and Egypt with images derived from Retcam and the 3nethra neo device (Forus Health, Bengaluru, India). FINDINGS: Of the 7414 retinal images in the original dataset, 6141 images were used in the final development dataset. For the discrimination of healthy versus pre-plus or plus disease, the bespoke model had an area under the curve (AUC) of 0·986 (95% CI 0·973-0·996) and the CFDL model had an AUC of 0·989 (0·979-0·997) on the internal test set. Both models generalised well to external validation test sets acquired using the Retcam for discriminating healthy from pre-plus or plus disease (bespoke range was 0·975-1·000 and CFDL range was 0·969-0·995). The CFDL model was inferior to the bespoke model on discriminating pre-plus disease from healthy or plus disease in the USA dataset (CFDL 0·808 [95% CI 0·671-0·909, bespoke 0·942 [0·892-0·982]], p=0·0070). Performance also reduced when tested on the 3nethra neo imaging device (CFDL 0·865 [0·742-0·965] and bespoke 0·891 [0·783-0·977]). INTERPRETATION: Both bespoke and CFDL models conferred similar performance to senior paediatric ophthalmologists for discriminating healthy retinal images from ones with features of pre-plus or plus disease; however, CFDL models might generalise less well when considering minority classes. Care should be taken when testing on data acquired using alternative imaging devices from that used for the development dataset. Our study justifies further validation of plus disease classifiers in ROP screening and supports a potential role for code-free approaches to help prevent blindness in vulnerable neonates. FUNDING: National Institute for Health Research Biomedical Research Centre based at Moorfields Eye Hospital NHS Foundation Trust and the University College London Institute of Ophthalmology. TRANSLATIONS: For the Portuguese and Arabic translations of the abstract see Supplementary Materials section.

SynthEye: Investigating the Impact of Synthetic Data on Artificial Intelligence-assisted Gene Diagnosis of Inherited Retinal Disease.

Purpose: Rare disease diagnosis is challenging in medical image-based artificial intelligence due to a natural class imbalance in datasets, leading to biased prediction models. Inherited retinal diseases (IRDs) are a research domain that particularly faces this issue. This study investigates the applicability of synthetic data in improving artificial intelligence-enabled diagnosis of IRDs using generative adversarial networks (GANs). Design: Diagnostic study of gene-labeled fundus autofluorescence (FAF) IRD images using deep learning. Participants: Moorfields Eye Hospital (MEH) dataset of 15 692 FAF images obtained from 1800 patients with confirmed genetic diagnosis of 1 of 36 IRD genes. Methods: A StyleGAN2 model is trained on the IRD dataset to generate 512 × 512 resolution images. Convolutional neural networks are trained for classification using different synthetically augmented datasets, including real IRD images plus 1800 and 3600 synthetic images, and a fully rebalanced dataset. We also perform an experiment with only synthetic data. All models are compared against a baseline convolutional neural network trained only on real data. Main Outcome Measures: We evaluated synthetic data quality using a Visual Turing Test conducted with 4 ophthalmologists from MEH. Synthetic and real images were compared using feature space visualization, similarity analysis to detect memorized images, and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score for no-reference-based quality evaluation. Convolutional neural network diagnostic performance was determined on a held-out test set using the area under the receiver operating characteristic curve (AUROC) and Cohen's Kappa (κ). Results: An average true recognition rate of 63% and fake recognition rate of 47% was obtained from the Visual Turing Test. Thus, a considerable proportion of the synthetic images were classified as real by clinical experts. Similarity analysis showed that the synthetic images were not copies of the real images, indicating that copied real images, meaning the GAN was able to generalize. However, BRISQUE score analysis indicated that synthetic images were of significantly lower quality overall than real images (P < 0.05). Comparing the rebalanced model (RB) with the baseline (R), no significant change in the average AUROC and κ was found (R-AUROC = 0.86[0.85-88], RB-AUROC = 0.88[0.86-0.89], R-k = 0.51[0.49-0.53], and RB-k = 0.52[0.50-0.54]). The synthetic data trained model (S) achieved similar performance as the baseline (S-AUROC = 0.86[0.85-87], S-k = 0.48[0.46-0.50]). Conclusions: Synthetic generation of realistic IRD FAF images is feasible. Synthetic data augmentation does not deliver improvements in classification performance. However, synthetic data alone deliver a similar performance as real data, and hence may be useful as a proxy to real data. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references.

Charles Bonnet syndrome in patients with Stargardt disease: prevalence and risk factors.

AIMS: To describe the prevalence of the Charles Bonnet syndrome (CBS) and search for potential CBS risk factors in a Dutch Stargardt disease (STGD1) cohort. METHODS: Eighty-three patients with STGD1 were screened for CBS. They underwent a full eye examination. All patients completed the social functioning domain of the 36-Item Short Form Health Survey questionnaire. Participants suspected of CBS were interviewed to further evaluate their visual hallucinations. RESULTS: CBS prevalence was 8.4%. Six out of seven patients with CBS were women. CBS was not associated with age (p=0.279, Mann-Whitney). Patients with CBS had a significant lower social functioning score (p<0.05, Mann-Whitney). All seven patients with CBS were in the category of vision impairment (visual acuity <6/12, but ≥3/60). Moreover, first hallucinations manifested after a drop in visual acuity. The retinal atrophic area of the worst eye tended to be lower in the CBS group (range 0.11-9.86 mm2) as compared with controls (range 0-180 mm2). There was no relation between the position of the scotoma and the location of the visual hallucinations. CONCLUSION: The relative high CBS prevalence in STGD1 suggests that CBS may be more prevalent in younger ophthalmic patients than currently presumed. In this specific group of patients, we established social isolation and acquired vision impairment as risk factors for CBS. There was a female preponderance among patients with CBS. Age and retinal pigment epithelium atrophy were not identified as significant risk factors. We should actively diagnose CBS in patients of any age who fulfil the criteria for the category vision impairment, especially in cases where social isolation is suspected.

Enablers and Barriers to Deployment of Smartphone-Based Home Vision Monitoring in Clinical Practice Settings.

IMPORTANCE: Telemedicine is accelerating the remote detection and monitoring of medical conditions, such as vision-threatening diseases. Meaningful deployment of smartphone apps for home vision monitoring should consider the barriers to patient uptake and engagement and address issues around digital exclusion in vulnerable patient populations. OBJECTIVE: To quantify the associations between patient characteristics and clinical measures with vision monitoring app uptake and engagement. DESIGN, SETTING, AND PARTICIPANTS: In this cohort and survey study, consecutive adult patients attending Moorfields Eye Hospital receiving intravitreal injections for retinal disease between May 2020 and February 2021 were included. EXPOSURES: Patients were offered the Home Vision Monitor (HVM) smartphone app to self-test their vision. A patient survey was conducted to capture their experience. App data, demographic characteristics, survey results, and clinical data from the electronic health record were analyzed via regression and machine learning. MAIN OUTCOMES AND MEASURES: Associations of patient uptake, compliance, and use rate measured in odds ratios (ORs). RESULTS: Of 417 included patients, 236 (56.6%) were female, and the mean (SD) age was 72.8 (12.8) years. A total of 258 patients (61.9%) were active users. Uptake was negatively associated with age (OR, 0.98; 95% CI, 0.97-0.998; P = .02) and positively associated with both visual acuity in the better-seeing eye (OR, 1.02; 95% CI, 1.00-1.03; P = .01) and baseline number of intravitreal injections (OR, 1.01; 95% CI, 1.00-1.02; P = .02). Of 258 active patients, 166 (64.3%) fulfilled the definition of compliance. Compliance was associated with patients diagnosed with neovascular age-related macular degeneration (OR, 1.94; 95% CI, 1.07-3.53; P = .002), White British ethnicity (OR, 1.69; 95% CI, 0.96-3.01; P = .02), and visual acuity in the better-seeing eye at baseline (OR, 1.02; 95% CI, 1.01-1.04; P = .04). Use rate was higher with increasing levels of comfort with use of modern technologies (ß = 0.031; 95% CI, 0.007-0.055; P = .02). A total of 119 patients (98.4%) found the app either easy or very easy to use, while 96 (82.1%) experienced increased reassurance from using the app. CONCLUSIONS AND RELEVANCE: This evaluation of home vision monitoring for patients with common vision-threatening disease within a clinical practice setting revealed demographic, clinical, and patient-related factors associated with patient uptake and engagement. These insights inform targeted interventions to address risks of digital exclusion with smartphone-based medical devices.

Clinically relevant deep learning for detection and quantification of geographic atrophy from optical coherence tomography: a model development and external validation study.

BACKGROUND: Geographic atrophy is a major vision-threatening manifestation of age-related macular degeneration, one of the leading causes of blindness globally. Geographic atrophy has no proven treatment or method for easy detection. Rapid, reliable, and objective detection and quantification of geographic atrophy from optical coherence tomography (OCT) retinal scans is necessary for disease monitoring, prognostic research, and to serve as clinical endpoints for therapy development. To this end, we aimed to develop and validate a fully automated method to detect and quantify geographic atrophy from OCT. METHODS: We did a deep-learning model development and external validation study on OCT retinal scans at Moorfields Eye Hospital Reading Centre and Clinical AI Hub (London, UK). A modified U-Net architecture was used to develop four distinct deep-learning models for segmentation of geographic atrophy and its constituent retinal features from OCT scans acquired with Heidelberg Spectralis. A manually segmented clinical dataset for model development comprised 5049 B-scans from 984 OCT volumes selected randomly from 399 eyes of 200 patients with geographic atrophy secondary to age-related macular degeneration, enrolled in a prospective, multicentre, phase 2 clinical trial for the treatment of geographic atrophy (FILLY study). Performance was externally validated on an independently recruited dataset from patients receiving routine care at Moorfields Eye Hospital (London, UK). The primary outcome was segmentation and classification agreement between deep-learning model geographic atrophy prediction and consensus of two independent expert graders on the external validation dataset. FINDINGS: The external validation cohort included 884 B-scans from 192 OCT volumes taken from 192 eyes of 110 patients as part of real-life clinical care at Moorfields Eye Hospital between Jan 1, 2016, and Dec, 31, 2019 (mean age 78·3 years [SD 11·1], 58 [53%] women). The resultant geographic atrophy deep-learning model produced predictions similar to consensus human specialist grading on the external validation dataset (median Dice similarity coefficient [DSC] 0·96 [IQR 0·10]; intraclass correlation coefficient [ICC] 0·93) and outperformed agreement between human graders (DSC 0·80 [0·28]; ICC 0·79). Similarly, the three independent feature-specific deep-learning models could accurately segment each of the three constituent features of geographic atrophy: retinal pigment epithelium loss (median DSC 0·95 [IQR 0·15]), overlying photoreceptor degeneration (0·96 [0·12]), and hypertransmission (0·97 [0·07]) in the external validation dataset versus consensus grading. INTERPRETATION: We present a fully developed and validated deep-learning composite model for segmentation of geographic atrophy and its subtypes that achieves performance at a similar level to manual specialist assessment. Fully automated analysis of retinal OCT from routine clinical practice could provide a promising horizon for diagnosis and prognosis in both research and real-life patient care, following further clinical validation FUNDING: Apellis Pharmaceuticals.