Search

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 geog

Purpose: To describe the detailed retinal phenotype of KCNV2-associated retinopathy. Study design: Multicenter international retrospective case series. Methods: Review of retinal imaging including fundus autofluorescence (FAF) and optical coherence tomography (OCT), including qualitative and quantitative analyses. Results: Three distinct macular FAF features were identified: (1) centrally increased signal (n = 35, 41.7%), (2) decreased autofluorescence (n = 27, 31.1%), and (3) ring of increased signal (n = 37, 44.0%). Five distinct FAF groups were identified based on combinations of those features, with 23.5% of patients changing the FAF group over a mean (range) follow-up of 5.9 years (1.9-13.1 years). Qualitative assessment was performed by grading OCT into 5 grades: (1) continuous ellipsoid zone (EZ) (20.5%); (2) EZ disruption (26.1%); (3) EZ absence, without optical gap and with preserved retinal pigment epithelium complex (21.6%); (4) loss of EZ and a hyporeflective zone at the foveola (6.8%); and (5) outer retina and retinal pigment epithelium complex loss (25.0%). Eighty-six patients had scans available from both eyes, with 83 (96.5%) having the same grade in both eyes, and 36.1% changed OCT grade over a mean follow-up of 5.5 years. The annual rate of outer nuclear layer thickness change was similar for right and left eyes. Conclusions: KCNV2-associated retinopathy is a slowly progressive disease with early retinal changes, which are predominantly symmetric between eyes. The identification of a single OCT or FAF measurement as an endpoint to determine progression that applies to all patients may be challenging, although outer nuclear layer thickness is a potential biomarker. Findings suggest a potential window for intervention until 40 years of age.

Purpose: To investigate genetics, electrophysiology, and clinical course of KCNV2-associated retinopathy in a cohort of children and adults. Study design: This was a multicenter international clinical cohort study. Methods: Review of clinical notes and molecular genetic testing. Full-field electroretinography (ERG) recordings, incorporating the international standards, were reviewed and quantified and compared with age and recordings from control subjects. Results: In total, 230 disease-associated alleles were identified from 117 patients, corresponding to 75 different KCNV2 variants, with 28 being novel. The mean age of onset was 3.9 years old. All patients were symptomatic before 12 years of age (range, 0-11 years). Decreased visual acuity was present in all patients, and 4 other symptoms were common: reduced color vision (78.6%), photophobia (53.5%), nyctalopia (43.6%), and nystagmus (38.6%). After a mean follow-up of 8.4 years, the mean best-corrected visual acuity (BCVA ± SD) decreased from 0.81 ± 0.27 to 0.90 ± 0.31 logarithm of minimal angle of resolution. Full-field ERGs showed pathognomonic waveform features. Quantitative assessment revealed a wide range of ERG amplitudes and peak times, with a mean rate of age-associated reduction indistinguishable from the control group. Mean amplitude reductions for the dark-adapted 0.01 ERG, dark-adapted 10 ERG a-wave, and LA 3.0 30 Hz and LA3 ERG b-waves were 55%, 21%, 48%, and 74%, respectively compared with control values. Peak times showed stability across 6 decades. Conclusion: In KCNV2-associated retinopathy, full-field ERGs are diagnostic and consistent with largely stable peripheral retinal dysfunction. Report 1 highlights the severity of the clinical phenotype and established a large cohort of patients, emphasizing the unmet need for trials of novel therapeutics.