Common Ophthalmic Diseases Research Articles

Artificial intelligence in ophthalmology: the present and the future

The medical industry is undergoing an active digital transformation, including the creation of electronic databases, cloud security systems, mobile health monitoring devices, and telemedicine tools. Artificial intelligence (AI), one of the most important technological achievements of the last decade, is gradually gaining momentum in various areas of practical medicine. The cutting edge of AI, neural networks, offers promising approaches to the improvement of clinical examination quality. The review presents data of studies focusing on the use of AI tools in the diagnosis of the most common ophthalmic diseases: diabetic retinopathy, macular degeneration, retinopathy of prematurity, glaucoma, cataracts, and ophthalmic oncology. We discuss both the advantages of neural networks in the diagnosis and monitoring of eye diseases, and outline the difficulties of their implementation, including ethical and legal conflicts.

Application and progress of artificial intelligence technology in the segmentation of hyperreflective foci in OCT images for ophthalmic disease research.

With the advancement of retinal imaging, hyperreflective foci (HRF) on optical coherence tomography (OCT) images have gained significant attention as potential biological biomarkers for retinal neuroinflammation. However, these biomarkers, represented by HRF, present pose challenges in terms of localization, quantification, and require substantial time and resources. In recent years, the progress and utilization of artificial intelligence (AI) have provided powerful tools for the analysis of biological markers. AI technology enables use machine learning (ML), deep learning (DL) and other technologies to precise characterization of changes in biological biomarkers during disease progression and facilitates quantitative assessments. Based on ophthalmic images, AI has significant implications for early screening, diagnostic grading, treatment efficacy evaluation, treatment recommendations, and prognosis development in common ophthalmic diseases. Moreover, it will help reduce the reliance of the healthcare system on human labor, which has the potential to simplify and expedite clinical trials, enhance the reliability and professionalism of disease management, and improve the prediction of adverse events. This article offers a comprehensive review of the application of AI in combination with HRF on OCT images in ophthalmic diseases including age-related macular degeneration (AMD), diabetic macular edema (DME), retinal vein occlusion (RVO) and other retinal diseases and presents prospects for their utilization.

A deep-learning pipeline for the diagnosis and grading of common blinding ophthalmic diseases based on lesion-focused classification model.

Glaucoma (GLAU), Age-related Macular Degeneration (AMD), Retinal Vein Occlusion (RVO), and Diabetic Retinopathy (DR) are common blinding ophthalmic diseases worldwide. This approach is expected to enhance the early detection and treatment of common blinding ophthalmic diseases, contributing to the reduction of individual and economic burdens associated with these conditions. We propose an effective deep-learning pipeline that combine both segmentation model and classification model for diagnosis and grading of four common blinding ophthalmic diseases and normal retinal fundus. In total, 102,786 fundus images of 75,682 individuals were used for training validation and external validation purposes. We test our model on internal validation data set, the micro Area Under the Receiver Operating Characteristic curve (AUROC) of which reached 0.995. Then, we fine-tuned the diagnosis model to classify each of the four disease into early and late stage, respectively, which achieved AUROCs of 0.597 (GL), 0.877 (AMD), 0.972 (RVO), and 0.961 (DR) respectively. To test the generalization of our model, we conducted two external validation experiments on Neimeng and Guangxi cohort, all of which maintained high accuracy. Our algorithm demonstrates accurate artificial intelligence diagnosis pipeline for common blinding ophthalmic diseases based on Lesion-Focused fundus that overcomes the low-accuracy of the traditional classification method that based on raw retinal images, which has good generalization ability on diverse cases in different regions.

Dysfunkcja gruczołów Meiboma jako przyczyna stanów zapalnych powierzchni oka

Meibomian glands dysfunction is described as one of the most common ophthalmic diseases in the world. Meibomian glands dysfunction is the most common cause of posterior blepharitis. Meibomian glands are the only ones responsible for the production of the tear film lipid layer. There are many diseases which induce Meibomian glands dysfunction, even leading to their disappearance. It is concluded that Meibomian glands dysfunction can both cause and result from dry eye syndrome through a process of events involving inflammation of the ocular surface. Accurate diagnosis becomes a great challenge, and it is of key importance in selecting the optimal form of treatment. This article provides an overview of the current understanding of Meibomian gland dysfunction and its therapeutic outlook.

Cross-camera Performance of Deep Learning Algorithms to Diagnose Common Ophthalmic Diseases: A Comparative Study Highlighting Feasibility to Portable Fundus Camera Use

Purpose To compare the inter-camera performance and consistency of various deep learning (DL) diagnostic algorithms applied to fundus images taken from desktop Topcon and portable Optain cameras. Methods Participants over 18 years of age were enrolled between November 2021 and April 2022. Pair-wise fundus photographs from each patient were collected in a single visit; once by Topcon (used as the reference camera) and once by a portable Optain camera (the new target camera). These were analyzed by three previously validated DL models for the detection of diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucomatous optic neuropathy (GON). Ophthalmologists manually analyzed all fundus photos for the presence of DR and these were referred to as the ground truth. Sensitivity, specificity, the area under the curve (AUC) and agreement between cameras (estimated by Cohen’s weighted kappa, K) were the primary outcomes of this study. Results A total of 504 patients were recruited. After excluding 12 photographs with matching errors and 59 photographs with low quality, 906 pairs of Topcon-Optain fundus photos were available for algorithm assessment. Topcon and Optain cameras had excellent consistency (Κ=0.80) when applied to the referable DR algorithm, while AMD had moderate consistency (Κ=0.41) and GON had poor consistency (Κ=0.32). For the DR model, Topcon and Optain achieved a sensitivity of 97.70% and 97.67% and a specificity of 97.92% and 97.93%, respectively. There was no significant difference between the two camera models (McNemar’s test: x2=0.08, p = .78). Conclusion Topcon and Optain cameras had excellent consistency for detecting referable DR, albeit performances for detecting AMD and GON models were unsatisfactory. This study highlights the methods of using pair-wise images to evaluate DL models between reference and new fundus cameras.

Bidirectional associations between hyperopia, myopia, astigmatism, and strabismus, and attention-deficit/hyperactivity disorder in children: a national population-based cohort study.

The present study analyzed the reciprocal relationships between four common pediatric ophthalmic diseases (i.e., hyperopia, myopia, astigmatism, and strabismus) and attention-deficit/hyperactivity disorder (ADHD) in children. This study enrolled 86,028 children with ADHD and 1,798,673 children without ADHD in the Taiwan Maternal and Child Health Database who were born at any time from 2004 to 2017. Cox proportional hazards regression models were used to estimate the bidirectional relationships of the four ophthalmic diseases with ADHD in children after adjusting for age, sex, and gestational age at birth. Survival curves for time-to-event variables were estimated using the Kaplan-Meier method, and the log-rank test was used to compare the curves. The results indicated that ADHD significantly predicted the occurrence of hyperopia, myopia, astigmatism, and strabismus. Furthermore, hyperopia, myopia, astigmatism, and strabismus significantly predicted the occurrence of ADHD. The time between enrollment and ADHD diagnosis was shorter for patients with ophthalmic diseases than for the control group, and the time between enrollment and ophthalmic disease diagnosis was also shorter for ADHD patients than for the control group. Sex differences were found in the associations between ADHD and ophthalmic diseases. Clinicians should monitor children with ADHD for hyperopia, myopia, astigmatism, and strabismus to ensure appropriate treatment, and vice versa.

Knowledge and Awareness of the Public toward Pediatric Eye Health and Diseases in Aseer region, Saudi Arabia: A Cross-Sectional Population Study

Pediatric ophthalmic conditions are a common and a serious public health problem, as they can not only impact the child’s ability to learn, have a normal social life, and get a better quality of life, but they can also lead to complete blindness or visual impairment. Early intervention is necessary for childhood eye diseases since they can result in ongoing issues. The underlying causes of blindness in children differ significantly from region to region, depending on some factors, including socioeconomic development and access to primary healthcare services and facilities. However, it is estimated that there are over 19 million people globally with visual impairments and that there are roughly 1.4 million cases of blindness. As a result, the purpose of this study is to assess the parents’ and caregivers’ awareness in Aseer, Saudi Arabia, about various common pediatric ophthalmic diseases, including strabismus, amblyopia, refractive errors, and congenital glaucoma. By identifying the gap in knowledge and awareness, this could help create targeted educational and awareness programs geared toward the parents and the public of Aseer, Saudi Arabia, which could help prevent or reduce the prevalence of pediatric ophthalmic conditions, and boost the children’s eye health. Key words: knowledge, awareness, paediatric eye health, eye diseases, Aseer, Saudi Arabia

Changes in mean and variance of ophthalmic disease incidences during COVID-19 pandemic in Korea

This study undertook to determine the changes in the numbers of outpatient visits for various ophthalmic diseases during the COVID-19 pandemic compared with before. The monthly outpatient visits for 14 common ophthalmic diseases were enumerated based on the ICD-10 codes in Korean National Health Insurance Service data. The differences in the mean outpatient visits and disease variance ‘before’ and ‘during COVID-19’ were calculated. Subsequently, subgroup analyses according to age and sex were performed. The number of outpatient visits for conjunctivitis, scleritis & episcleritis, keratitis, cataract, diabetic retinopathy, and traumatic ophthalmic disease were lower during than before COVID-19 (all P < 0.001). The lower numbers of outpatient visits for ophthalmic disorders during COVID-19 were consistent across the age and sex subgroups. All ophthalmic diseases other than endophthalmitis showed no change of variation ‘during’ relative to ‘before’ COVID-19. In conclusion, during the COVID-19 pandemic, the ophthalmic outpatient visits decreased for infectious and inflammatory diseases, screening diseases, and traumatic diseases. However, COVID-19 is not considered to have had a significant effect on variation.

Class-Aware Attention Network for infectious keratitis diagnosis using corneal photographs

Infectious keratitis is one of the common ophthalmic diseases and also one of the main blinding eye diseases in China, hence rapid and accurate diagnosis and treatment for infectious keratitis are urgent to prevent the progression of the disease and limit the degree of corneal injury. Unfortunately, the traditional manual diagnosis accuracy is usually unsatisfactory due to the indistinguishable visual features. In this paper, we propose a novel end-to-end fully convolutional network, named Class-Aware Attention Network (CAA-Net), for automatically diagnosing infectious keratitis (normal, viral keratitis, fungal keratitis, and bacterial keratitis) using corneal photographs. In CAA-Net, a class-aware classification module is first trained to learn class-related discriminative features using separate branches for each class. Then, the learned class-aware discriminative features are fed into the main branch and fused with other feature maps using two attention strategies to assist the final multi-class classification performance. For the experiments, we have built a new corneal photograph dataset with 1886 images from 519 patients and conducted comprehensive experiments to verify the effectiveness of our proposed method. The code is available at https://github.com/SWF-hao/CAA-Net_Pytorch.

Acupuncture for dry eye disease after recovery from COVID-19: A protocol for systematic review and meta-analysis.

Dry eye disease (DED) is a condition occurring worldwide. Studies have found that coronavirus disease 2019 (COVID-19) patients may have persistent dry eye symptoms for weeks and months after recovery, and the prevalence of dry eye is higher in COVID-19 patients than in people without COVID-19 infection. As one of the common ophthalmic diseases, the clinical application of acupuncture in the treatment of DED is not widely used nowadays. According to the retrieval strategies, randomized controlled trials (RCT) on the acupuncture for DED after recovery from COVID-19 were obtained from Embase, The Cochrane Library, Web of Science, Chinese National Knowledge Infrastructure database, Chinese Biomedical Database, Chinese Science and Technology Periodical database, The WanFang database. Studies were screened based on inclusion and exclusion criteria, and the Cochrane risk bias assessment tool was used to evaluate the quality of the studies. The meta-analysis was performed using Review Manager (RevMan 5.3) and STATA 14.2 software. Ultimately, the evidentiary grade for the results will be evaluated. The study will provide a high-quality and convincing assessment of the efficacy and safety of acupuncture for DED after recovery from COVID-19 and will be published in peer-reviewed journals. Our findings will provide references for future clinical decision and guidance development.

Associations of cardiovascular diseases and type 2 diabetes with ophthalmic diseases in a population sample over 55 years old

Aim. To study associations of cardiovascular diseases and type 2 diabetes (T2D) with ophthalmic diseases in a population sample of men and women from middle to old age (Novosibirsk).Material and methods. The population cohort was initially studied in 2003-2005 (n=9360, 45-69 years old, Novosibirsk, the Health, Alcohol and Psychosocial factors in Eastern Europe (HAPIEE) project). At the second survey (2015-2017) in a random subsample (n=1011), the following ophthalmic diseases were identified: hypertensive retinopathy (HR), diabetic retinopathy (DR), cataract, glaucoma, age-related macular degeneration (AMD), optic disc abnormalities, etc.Results. The prevalence of HR signs in persons with and without hypertension (HTN) was 81 and 46%, respectively (p&lt;0,001). This association persisted regardless of other factors (odds ratio, 2,27 (95% confidence interval: 1,78-4,17). The prevalence of AMD, cataract and DR increased in HTN, but associations were largely explained by metabolic factors in multivariate models. People with T2D more often than without T2D had signs of DR (9,3 vs 0,4%, p&lt;0,001), AMD (22 vs 17%, p=0,042) and glaucoma (14 vs 7%, p=0,001). Associations of T2D with DR and glaucoma persisted regardless of other factors. Individuals with carotid atherosclerosis (CA) were 1,6 times more likely to have HR than those without CA when adjusted for sex, age, and smoking (p=0,013).Conclusion. In the surveyed population sample of mainly elderly people, a number of associations between cardiometabolic and common ophthalmic diseases were revealed. The identified comorbidities may have important therapeutic and prophylactic applications in an aging population.

Medical Schools’ Ophthalmology Course: An Appraisal by Ophthalmology Residents

ObjectiveTo investigate the perception and satisfaction of ophthalmology residents with the currently provided ophthalmology curricula to medical students.MethodsA cross-sectional survey involving first to fourth year ophthalmology residents (N = 106) from all regions of Saudi Arabia was conducted between December 2018 and February 2019. An online questionnaire explored opinions about the ophthalmology course regarding three dimensions. Firstly, adequacy in covering essential parts of the specialty; secondly, improvements required; and thirdly, effectiveness. A score (0–21) was calculated, indicating the overall suitability of the ophthalmology course. In addition, factors of good overall suitability (score ≥10) were analyzed.ResultsRegarding adequacy, respondents opined that the ophthalmology course did not reasonably cover the basic part (35.8%), clinical part (61.3%), common disease (26.4%), and emergencies (39.6%). Concerning improvements required, more than 80% of the participants expressed that the course required to be improved for all its features, including duration (80.2%), objectives (85.8%), content (82.1%), organization (83.0%), and supervision (81.1%). As to effectiveness, half of them deemed the course unhelpful in familiarizing general practitioners with common ophthalmic diseases and emergencies. Overall, the ophthalmology course was generally deemed suitable (score ≥10) for only 27.4% of the participants, with no differences across gender, level, or region.ConclusionOphthalmology residents perceived multiple deficits in the current Saudi ophthalmology teaching course. Significant improvements in ophthalmologic curricula are required, besides coping with unprecedented technological advancement in the ophthalmological field.

M2LC-Net: A multi-modal multi-disease long-tailed classification network for real clinical scenes

Leveraging deep learning-based techniques to classify diseases has attracted extensive research interest in recent years. Nevertheless, most of the current studies only consider single-modal medical images, and the number of ophthalmic diseases that can be classified is relatively small. Moreover, imbalanced data distribution of different ophthalmic diseases is not taken into consideration, which limits the application of deep learning techniques in realistic clinical scenes. In this paper, we propose a Multimodal Multi-disease Long-tailed Classification Network (M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> LC-Net) in response to the challenges mentioned above. M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> LC-Net leverages ResNet18-CBAM to extract features from fundus images and Optical Coherence Tomography (OCT) images, respectively, and conduct feature fusion to classify 11 common ophthalmic diseases. Moreover, Class Activation Mapping (CAM) is employed to visualize each mode to improve interpretability of M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> LC-Net. We conduct comprehensive experiments on realistic dataset collected from a Grade III Level A ophthalmology hospital in China, including 34,396 images of 11 disease labels. Experimental results demonstrate effectiveness of our proposed model M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> LC-Net. Compared with the state-of-the-art, various performance metrics have been improved significantly. Specifically, Cohen's kappa coefficient κ has been improved by 3.21%, which is a remarkable improvement.

Retinal Diseases and Parkinson Disease: A Population-Based Study.

IntroductionPatients with Parkinson disease (PD) tend to have ophthalmic symptoms. Retinal diseases are associated with central nervous system diseases, especially neurodegenerative diseases. Here, we investigated the association of retinal diseases with PD, especially the temporal relationship before and after PD diagnosis.MethodsData were obtained from the National Health Insurance Research Database of Taiwan. In total, 21,845 patients with newly diagnosed PD were matched with four controls each on the basis of propensity score. This study was bidirectional. A case–control study evaluated the adjusted odds ratio (aOR) of retinal disease before PD diagnosis by using conditional logistic regression. Furthermore, a cohort study evaluated the adjusted subdistribution hazard ratio (aSHR) for new-onset retinal and optic nerve diseases after PD diagnosis by using competing risk analysis. The association between PD with optic nerve diseases and glaucoma (another common ophthalmic diseases with the consequence of retinal dysfunction) were also analyzed as reference.ResultsIn the case–control study, PD was found to be significantly comorbid with recent and remote retinal disease [recent: ≤ 5 years, aOR: 1.12, 95% confidence interval (CI): 1.03–1.23; remote: > 5 years, aOR: 1.18, 95% CI: 1.04–1.34]. No similar association was identified between optic nerve disease or glaucoma with PD. In the cohort study, patients with PD were found to have a low risk of retinal disease in short-term (≤ 5 years, aSHR: 0.81, 95% CI: 0.71–0.93) and long-term (> 5 years, aSHR: 0.82, 95% CI: 0.72–0.93) follow-up.ConclusionThe study findings demonstrated that patients with prediagnostic PD were at greater risk of retinal disease than non-PD participants, but the risk reversed afterward. Thus, retinal disease may be a premotor manifestation of PD, and there may be some possible effect of dopamine supplements on retina.

Mitophagy: An Emerging Target in Ocular Pathology.

Mitochondrial function is essential for the viability of aerobic eukaryotic cells, as mitochondria provide energy through the generation of adenosine triphosphate (ATP), regulate cellular metabolism, provide redox balancing, participate in immune signaling, and can initiate apoptosis. Mitochondria are dynamic organelles that participate in a cyclical and ongoing process of regeneration and autophagy (clearance), termed mitophagy specifically for mitochondrial (macro)autophagy. An imbalance in mitochondrial function toward mitochondrial dysfunction can be catastrophic for cells and has been characterized in several common ophthalmic diseases. In this article, we review mitochondrial homeostasis in detail, focusing on the balance of mitochondrial dynamics including the processes of fission and fusion, and provide a description of the mechanisms involved in mitophagy. Furthermore, this article reviews investigations of ocular diseases with impaired mitophagy, including Fuchs endothelial corneal dystrophy, primary open-angle glaucoma, diabetic retinopathy, and age-related macular degeneration, as well as several primary mitochondrial diseases with ocular phenotypes that display impaired mitophagy, including mitochondrial encephalopathy lactic acidosis stroke, Leber hereditary optic neuropathy, and chronic progressive external ophthalmoplegia. The results of various studies using cell culture, animal, and human tissue models are presented and reflect a growing awareness of mitophagy impairment as an important feature of ophthalmic disease pathology. As this review indicates, it is imperative that mitophagy be investigated as a targetable mechanism in developing therapies for ocular diseases characterized by oxidative stress and mitochondrial dysfunction.

Teleophthalmology: an essential tool in the era of the novel coronavirus 2019.

The aim of this article is to assess the current state of teleophthalmology given the sudden surge in telemedicine demand in response to the novel coronavirus 2019 (COVID-19). Recommendations and policies from government and national health organizations, combined with social distancing, have led to exponential increases in telemedicine use. Teleophthalmology can be integrated into ophthalmic care delivery. In the emergency room, teleophthalmology can be utilized to triage patients and diagnose common ophthalmic eye diseases. Ophthalmology practices can utilize real-time medicine to conduct many parts of an in-person exam. In cases where more complex diagnostic tools are warranted, a model incorporating telemedicine and focused in-person visits may still be beneficial. Innovative technologies emerging in the market allow for increased remote monitoring, screening, and management of adult and pediatric patients for common eye diseases. COVID-19 created a demand for healthcare delivery that limits in-person examination and potential viral exposure. Teleophthalmology allows ophthalmologists to continue caring for patients while keeping physicians and patients safe. Although challenges still exist, the pandemic has accelerated the adoption of teleophthalmology. As a result, teleophthalmology will play an integral role in providing high-quality efficient care in the near future.

Research progress of extracellular high mobility group box 1 in common ophthalmic diseases

Research progress of extracellular high mobility group box 1 in common ophthalmic diseases

Prevelance of diabetes mellitus in common ophthalmic disorders

Aim: To study the prevalence of diabetes mellitus in common ophthalmic diseases such as glaucoma, cataract and retinopathy. Materials and Methods: This cross sectional, observational study. The study was conducted in a tertiary eye care hospital. Patients with diseases of glaucoma, cataract and retinopathy in this study. Thorough eye examination was carried out in outward patient department at Tertiary eye care hospital. Examination was carried out in ophthalmology department with slit lamp examination, distant direct opthalmoscopy, fundus examination with the help of direct opthalmoscope, indirect opthalmoscope and slit lamp with 90D tonometry with help of applanation tonometer. First anterior segment examination was done with the help of slit lamp, and applanation tonometer after thorough examination of anterior segment, posterior segment was thoroughly examined. Pupils of patients were dilated with the help of Tropicamide 0.5% with Phenylepherine. After full dilatation of pupil fundus examination was done after 30 mins. The patients were evaluated for diabetic retinopathy and findings such as microaneurysm, dot and blot hemorrhages, venous dilatation, intraretinal microvascular aneurysm, neovascularisation at the disk, neovascularisation elsewhere, hard exudates, macular edema were noted. Results: Are during this study a total of 856 patients were included in the study. There were 42% male patients and 54% female patients. Out of 856 patients 75% were affected with cataract, 70% with retinopathy, and 58% with glaucoma. Prevalence of diabetes mellitus in glaucoma is 18.50%. Ocular disorders without diabetes mellitus in patients with cataract is 54.6, in retinopathy is 3.05% and in glaucoma is 11.56%. Conclusion: we then came to the conclusion that one of the most potential risk factor for eye diseaqses is diabetes mellitus. There were most strong association of diabetes mellitus in cataract and glaucoma. Keywords: Diabetes mellitus, Diabetic retinopathy, Dia

Assessment of Deep Generative Models for High-Resolution Synthetic Retinal Image Generation of Age-Related Macular Degeneration

Deep learning (DL) used for discriminative tasks in ophthalmology, such as diagnosing diabetic retinopathy or age-related macular degeneration (AMD), requires large image data sets graded by human experts to train deep convolutional neural networks (DCNNs). In contrast, generative DL techniques could synthesize large new data sets of artificial retina images with different stages of AMD. Such images could enhance existing data sets of common and rare ophthalmic diseases without concern for personally identifying information to assist medical education of students, residents, and retinal specialists, as well as for training new DL diagnostic models for which extensive data sets from large clinical trials of expertly graded images may not exist. To develop DL techniques for synthesizing high-resolution realistic fundus images serving as proxy data sets for use by retinal specialists and DL machines. Generative adversarial networks were trained on 133 821 color fundus images from 4613 study participants from the Age-Related Eye Disease Study (AREDS), generating synthetic fundus images with and without AMD. We compared retinal specialists' ability to diagnose AMD on both real and synthetic images, asking them to assess image gradability and testing their ability to discern real from synthetic images. The performance of AMD diagnostic DCNNs (referable vs not referable AMD) trained on either all-real vs all-synthetic data sets was compared. Accuracy of 2 retinal specialists (T.Y.A.L. and K.D.P.) for diagnosing and distinguishing AMD on real vs synthetic images and diagnostic performance (area under the curve) of DL algorithms trained on synthetic vs real images. The diagnostic accuracy of 2 retinal specialists on real vs synthetic images was similar. The accuracy of diagnosis as referable vs nonreferable AMD compared with certified human graders for retinal specialist 1 was 84.54% (error margin, 4.06%) on real images vs 84.12% (error margin, 4.16%) on synthetic images and for retinal specialist 2 was 89.47% (error margin, 3.45%) on real images vs 89.19% (error margin, 3.54%) on synthetic images. Retinal specialists could not distinguish real from synthetic images, with an accuracy of 59.50% (error margin, 3.93%) for retinal specialist 1 and 53.67% (error margin, 3.99%) for retinal specialist 2. The DCNNs trained on real data showed an area under the curve of 0.9706 (error margin, 0.0029), and those trained on synthetic data showed an area under the curve of 0.9235 (error margin, 0.0045). Deep learning-synthesized images appeared to be realistic to retinal specialists, and DCNNs achieved diagnostic performance on synthetic data close to that for real images, suggesting that DL generative techniques hold promise for training humans and machines.

Epigenetics and common ophthalmic diseases

The study of ocular diseases and epigenetic dysregulation is an emerging area of research. The knowledge from the epigenetic mechanisms of DNA methylation, histone modifications, chromatin remodeling, and non-coding RNAs regarding the pathogenesis of ocular diseases will be helpful for improved treatment modalities for our patients. In particular, we focus upon the how epigenetic regulatory mechanisms impact five common ocular diseases: age related macular degeneration, age-related cataract, pterygium, retinoblastoma, and uveal melanoma. Hence, the foundation of this research paves the way for future specific therapeutic targets to treat and prevent vision loss.