To analyze the clinical characteristics, natural history, and genetics of CRB1-associated retinal dystrophies. Multicenter international retrospective cohort study. Review of clinical notes, ophthalmic images, and genetic testing results of 104 patients (91 probands) with disease-causing CRB1 variants. Macular optical coherence tomography (OCT) parameters, visual function, fundus characteristics, and associations between variables were the main outcome measures. The mean age of the cohort at the first visit was 19.8 ± 16.1 (median 15) years, with a mean follow-up of 9.6 ± 10 years. Based on history, imaging, and clinical examination, 26 individuals were diagnosed with retinitis pigmentosa (RP; 25%), 54 with early-onset severe retinal dystrophy / Leber congenital amaurosis (EOSRD/LCA; 52%), and 24 with macular dystrophy (MD; 23%). Severe visual impairment was most frequent after 40 years of age for patients with RP and after 20 years of age for EOSRD/LCA. Longitudinal analysis revealed a significant difference between baseline and follow-up best-corrected visual acuity in the 3 subcohorts. Macular thickness decreased in most patients with EOSRD/LCA and MD, whereas the majority of patients with RP had increased perifoveal thickness. A subset of individuals with CRB1 variants present with mild, adult-onset RP. EOSRD/LCA phenotype was significantly associated with null variants, and 167_169 deletion was exclusively present in the MD cohort. The poor OCT lamination may have a degenerative component, as well as being congenital. Disease symmetry and reasonable window for intervention highlight CRB1 retinal dystrophies as a promising target for trials of novel therapeutics.

To examine the genetic and clinical features in children and adults with X-linked retinoschisis (XLRS). Single-center consecutive, retrospective, observational study. Adults and children with molecularly confirmed XLRS followed up between 1999 and 2020. Analysis of genetic, clinical, and retinal imaging findings, including OCT and fundus autofluorescence (FAF), cross-sectionally and longitudinally, was performed. RS1, variants, type of variants and phenotype correlations, age of onset, complications rates and types, fundoscopy findings, OCT metrics, FAF patterns, correlations including between best corrected visual acuity (BCVA) and age, and OCT characteristics. One hundred thirty-two male patients were identified harboring 66 retinoschisin 1 variants, with 7 being novel. The mean age at onset was 16.5 years (range, 0-58 years). Seventy-one patients (71/75 [94.7%]) were symptomatic at presentation; all had decreased best-corrected visual acuity (BCVA). Funduscopy findings were symmetric in 104 patients (104/108 [96.3%]), with the most common finding being macular schisis (82.4%), whereas peripheral retinoschisis was present in 38.9% and macular atrophy was present in 11.1%. Twenty patients (18.5%) demonstrated complications (vitreous hemorrhage, retinal detachment, or both). Mean BCVA was 0.65 logarithm of the minimum angle of resolution (logMAR; Snellen equivalent, 20/89) in the right eye and 0.64 logMAR (Snellen equivalent, 20/87) in the left eye. Mean BCVA change over a mean interval of 6.7 years was 0.04 and 0.01 logMAR for right and left eyes, respectively. A normal FAF pattern was identified in 16 of 106 eyes (15.1%); 45 eyes (42.5%) showed a spoke-wheel pattern, 13 eyes (12.3%) showed foveal hyperautofluorescence, and 18 eyes (17.0%) showed a central reduction in signal. In total, 14 patients demonstrated evidence of progression on FAF over time. On OCT, foveoschisis was observed in 172 eyes (172/215 [80%]), parafoveal schisis was observed in 171 eyes (171/215 [79.5%]), and foveal atrophy was observed in 44 eyes (44/215 [20.5%]). Cystoid changes were localized to the inner nuclear layer (172/181 eyes [95%]), the outer nuclear layer (97/181 [53.6%]), and the ganglion cell layer (92/181 [50.8%]). Null variants were associated with worse final BCVA and aforementioned complications. X-linked retinoschisis is highly phenotypically variable, but with relative foveal and BCVA preservation until late adulthood, allowing more accurate prognostication. The slowly (often minimally) progressive disease course may pose a challenge in identification of early end points for therapeutic trials aimed at altering the kinetics of degeneration.

Purpose. To illustrate a data-driven deep learning approach to predicting the gene responsible for the inherited retinal disorder (IRD) in macular dystrophy caused by ABCA4 and RP1L1 gene aberration in comparison with retinitis pigmentosa caused by EYS gene aberration and normal subjects. Methods. Seventy-five subjects with IRD or no ocular diseases have been ascertained from the database of Japan Eye Genetics Consortium; 10 ABCA4 retinopathy, 20 RP1L1 retinopathy, 28 EYS retinopathy, and 17 normal patients/subjects. Horizontal/vertical cross-sectional scans of optical coherence tomography (SD-OCT) at the central fovea were cropped/adjusted to a resolution of 400 pixels/inch with a size of 750 × 500 pix² for learning. Subjects were randomly split following a 3 : 1 ratio into training and test sets. The commercially available learning tool, Medic mind was applied to this four-class classification program. The classification accuracy, sensitivity, and specificity were calculated during the learning process. This process was repeated four times with random assignment to training and test sets to control for selection bias. For each training/testing process, the classification accuracy was calculated per gene category. Results. A total of 178 images from 75 subjects were included in this study. The mean training accuracy was 98.5%, ranging from 90.6 to 100.0. The mean overall test accuracy was 90.9% (82.0–97.6). The mean test accuracy per gene category was 100% for ABCA4, 78.0% for RP1L1, 89.8% for EYS, and 93.4% for Normal. Test accuracy of RP1L1 and EYS was not high relative to the training accuracy which suggests overfitting. Conclusion. This study highlighted a novel application of deep neural networks in the prediction of the causative gene in IRD retinopathies from SD-OCT, with a high prediction accuracy. It is anticipated that deep neural networks will be integrated into general screening to support clinical/genetic diagnosis, as well as enrich the clinical education.

Rare eye diseases such as inherited retinal diseases (IRDs) are challenging to diagnose genetically. IRDs are typically monogenic disorders and represent a leading cause of blindness in children and working-age adults worldwide. A growing number are now being targeted in clinical trials, with approved treatments increasingly available. However, access requires a genetic diagnosis to be established sufficiently early. Critically, the timely identification of a genetic cause remains challenging. We demonstrate that a deep learning algorithm, Eye2Gene, trained on a large multimodal imaging dataset of individuals with IRDs (n = 2,451) and externally validated on data provided by five different clinical centres, provides better-than-expert-level top-five accuracy of 83.9% for supporting genetic diagnosis for the 63 most common genetic causes. We demonstrate that Eye2Gene’s next-generation phenotyping can increase diagnostic yield by improving screening for IRDs, phenotype-driven variant prioritization and automatic similarity matching in phenotypic space to identify new genes. Eye2Gene is accessible online (app.eye2gene.com) for research purposes.

Background/Aims: To investigate the utility of a data-driven deep learning approach in patients with inherited retinal disorder (IRD) and to predict the causative genes based on fundus photography and fundus autofluorescence (FAF) imaging.Methods: Clinical and genetic data from 1302 subjects from 729 genetically confirmed families with IRD registered with the Japan Eye Genetics Consortium were reviewed. Three categories of genetic diagnosis were selected, based on the high prevalence of their causative genes: Stargardt disease (ABCA4), retinitis pigmentosa (EYS) and occult macular dystrophy (RP1L1). Fundus photographs and FAF images were cropped in a standardised manner with a macro algorithm. Images for training/testing were selected using a randomised, fourfold cross-validation method. The application program interface was established to reach the learning accuracy of concordance (target: >80%) between the genetic diagnosis and the machine diagnosis (ABCA4, EYS, RP1L1 and normal).Results: A total of 417 images from 156 Japanese subjects were examined, including 115 genetically confirmed patients caused by the three prevalent causative genes and 41 normal subjects. The mean overall test accuracy for fundus photographs and FAF images was 88.2% and 81.3%, respectively. The mean overall sensitivity/specificity values for fundus photographs and FAF images were 88.3%/97.4% and 81.8%/95.5%, respectively.Conclusion: A novel application of deep neural networks in the prediction of the causative IRD genes from fundus photographs and FAF, with a high prediction accuracy of over 80%, was highlighted. These achievements will extensively promote the quality of medical care by facilitating early diagnosis, especially by non-specialists, access to care, reducing the cost of referrals, and preventing unnecessary clinical and genetic testing.