Best Vitelliform Macular Dystrophy Natural History Study Report 1: Clinical Features and Genetic Findings.

PURPOSE: To analyze the genetic findings, clinical spectrum, and natural history of Best vitelliform macular dystrophy (BVMD) in a cohort of 222 children and adults. DESIGN: Single-center retrospective, consecutive, observational study. PARTICIPANTS: Patients with a clinical diagnosis of BVMD from pedigrees with a likely disease-causing monoallelic sequence variant in the BEST1 gene. METHODS: Data were extracted from electronic and physical case notes. Electrophysiologic assessment and molecular genetic testing were analyzed. MAIN OUTCOME MEASURES: Molecular genetic test findings and clinical findings including best-corrected visual acuity (BCVA), choroidal neovascularization (CNV) rates, and electrophysiologic parameters. RESULTS: Two hundred twenty-two patients from 141 families were identified harboring 69 BEST1 variants. Mean age at presentation was 26.8 years (range, 1.3-84.8 years) and most patients (61.5%) demonstrated deterioration of central vision. Major funduscopic findings included 128 eyes (30.6%) with yellow vitelliform lesions, 78 eyes (18.7%) with atrophic changes, 49 eyes (11.7%) with fibrotic changes, 48 eyes (11.5%) with mild pigmentary changes, and 43 eyes (10.3%) showing a vitelliruptive appearance. Mean BCVA was 0.37 logarithm of the minimum angle of resolution (logMAR; Snellen equivalent, 20/47) for the right eye and 0.33 logMAR (Snellen equivalent, 20/43) for the left eye at presentation, with a mean annual loss rate of 0.013 logMAR and 0.009 logMAR, respectively, over a mean follow-up of 9.7 years. Thirty-seven patients (17.3%) received a diagnosis of CNV over a mean follow-up of 8.0 years. Eyes with CNV that received treatment with an anti-vascular endothelial growth factor (VEGF) agent showed better mean BCVA compared with eyes that were not treated with an anti-VEGF agent (0.28 logMAR [Snellen equivalent, 20/38] vs. 0.62 logMAR [Snellen equivalent, 20/83]). Most eyes exhibited a hyperopic refractive error (78.7%), and 13 patients (6.1%) received a diagnosis of amblyopia. Among the 3 most common variants, p.(Ala243Val) was associated with a later age of onset, better age-adjusted BCVA, and less advanced Gass stages compared with p.(Arg218Cys) and p.(Arg218His). CONCLUSIONS: BVMD shows a wide spectrum of phenotypic variability. The disease is very slowly progressive, and the observed phenotype-genotype correlations allow for more accurate prognostication and counselling. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Can artificial intelligence accelerate the diagnosis of inherited retinal diseases? Protocol for a data-only retrospective cohort study (Eye2Gene).

INTRODUCTION: Inherited retinal diseases (IRD) are a leading cause of visual impairment and blindness in the working age population. Mutations in over 300 genes have been found to be associated with IRDs and identifying the affected gene in patients by molecular genetic testing is the first step towards effective care and patient management. However, genetic diagnosis is currently slow, expensive and not widely accessible. The aim of the current project is to address the evidence gap in IRD diagnosis with an AI algorithm, Eye2Gene, to accelerate and democratise the IRD diagnosis service. METHODS AND ANALYSIS: The data-only retrospective cohort study involves a target sample size of 10 000 participants, which has been derived based on the number of participants with IRD at three leading UK eye hospitals: Moorfields Eye Hospital (MEH), Oxford University Hospital (OUH) and Liverpool University Hospital (LUH), as well as a Japanese hospital, the Tokyo Medical Centre (TMC). Eye2Gene aims to predict causative genes from retinal images of patients with a diagnosis of IRD. For this purpose, 36 most common causative IRD genes have been selected to develop a training dataset for the software to have enough examples for training and validation for detection of each gene. The Eye2Gene algorithm is composed of multiple deep convolutional neural networks, which will be trained on MEH IRD datasets, and externally validated on OUH, LUH and TMC. ETHICS AND DISSEMINATION: This research was approved by the IRB and the UK Health Research Authority (Research Ethics Committee reference 22/WA/0049) 'Eye2Gene: accelerating the diagnosis of IRDs' Integrated Research Application System (IRAS) project ID: 242050. All research adhered to the tenets of the Declaration of Helsinki. Findings will be reported in an open-access format.

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.

Leber congenital amaurosis/early-onset severe retinal dystrophy: current management and clinical trials.

Leber congenital amaurosis (LCA) is a severe congenital/early-onset retinal dystrophy. Given its monogenic nature and the immunological and anatomical privileges of the eye, LCA has been particularly targeted by cutting-edge research. In this review, we describe the current management of LCA, and highlight the clinical trials that are on-going and planned. RPE65-related LCA pivotal trials, which culminated in the first Food and Drug Administration-approved and European Medicines Agency-approved ocular gene therapy, have paved the way for a new era of genetic treatments in ophthalmology. At present, multiple clinical trials are available worldwide applying different techniques, aiming to achieve better outcomes and include more genes and variants. Genetic therapy is not only implementing gene supplementation by the use of adeno-associated viral vectors, but also clustered regularly interspaced short palindromic repeats (CRISPR)-mediated gene editing and post-transcriptional regulation through antisense oligonucleotides. Pharmacological approaches intending to decrease photoreceptor degeneration by supplementing 11-cis-retinal and cell therapy's aim to replace the retinal pigment epithelium, providing a trophic and metabolic retinal structure, are also under investigation. Furthermore, optoelectric devices and optogenetics are also an option for patients with residual visual pathway. After more than 10 years since the first patient with LCA received gene therapy, we also discuss future challenges, such as the overlap between different techniques and the long-term durability of efficacy. The next 5 years are likely to be key to whether genetic therapies will achieve their full promise, and whether stem cell/cellular therapies will break through into clinical trial evaluation.

Treatments for dry age-related macular degeneration: therapeutic avenues, clinical trials and future directions.

Age-related macular degeneration (AMD) is the leading cause of irreversible blindness in the developed world. The identification of the central role of vascular endothelial growth factor (VEGF) in the pathogenesis of neovascular AMD and the introduction of anti-VEGF agents as gold-standard treatment, have drastically changed its prognosis-something yet to be seen in dry AMD. Several therapeutic avenues with a wide variability of targets are currently being investigated in dry AMD. The approaches being investigated to reduce the rate of disease progression include, (1) drugs with antioxidative properties, (2) inhibitors of the complement cascade, (3) neuroprotective agents, (4) visual cycle inhibitors, (5) gene therapy and (6) cell-based therapies. A number of early phase clinical trials have provided promising results, with many more ongoing and anticipated in the near future. In this review, we aim to provide an update of the interventional trials to date and future prospects for the treatment of dry AMD.

Structural evaluation in inherited retinal diseases.

Ophthalmic genetics is a field that has been rapidly evolving over the last decade, mainly due to the flourishing of translational medicine for inherited retinal diseases (IRD). In this review, we will address the different methods by which retinal structure can be objectively and accurately assessed in IRD. We review standard-of-care imaging for these patients: colour fundus photography, fundus autofluorescence imaging and optical coherence tomography (OCT), as well as higher-resolution and/or newer technologies including OCT angiography, adaptive optics imaging, fundus imaging using a range of wavelengths, magnetic resonance imaging, laser speckle flowgraphy and retinal oximetry, illustrating their utility using paradigm genotypes with on-going therapeutic efforts/trials.

KCNV2-Associated Retinopathy: Genetics, Electrophysiology, and Clinical Course-KCNV2 Study Group Report 1.

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.