Retinal Diseases Research Articles

Implications of Ocular Confounding Factors for Aqueous Humor Proteomic and Metabolomic Analyses in Retinal Diseases.

To assess the impact of ocular confounding factors on aqueous humor (AH) proteomic and metabolomic analyses for retinal disease characterization. This study recruited 138 subjects (eyes): 102 with neovascular age-related macular degeneration (nAMD), 18 with diabetic macular edema (DME), and 18 with cataract (control group). AH samples underwent analysis using Olink Target 96 proteomics and Metabolon's metabolomics platform Data analysis included correlation, differential abundance, and gene-set analysis. In total, 756 proteins and 408 metabolites were quantified in AH. Total AH protein concentration was notably higher in nAMD (3.2-fold) and DME (4.1-fold) compared to controls. Pseudophakic eyes showed higher total AH protein concentrations than phakic eyes (e.g., 1.6-fold in nAMD) and a specific protein signature indicative of matrix remodeling. Unexpectedly, pupil-dilating drugs containing phenylephrine/tropicamide increased several AH proteins, notably interleukin-6 (5.4-fold in nAMD). Correcting for these factors revealed functionally relevant protein correlation clusters and disease-relevant, differentially abundant proteins across the groups. Metabolomics analysis, for which the relevance of confounder adjustment was less apparent, suggested insufficiently controlled diabetes and chronic hyperglycemia in the DME group. AH protein concentration, pseudophakia, and pupil dilation with phenylephrine/tropicamide are important confounding factors for AH protein analyses. When these factors are considered, AH analyses can more clearly reveal disease-relevant factors. Considering AH protein concentration, lens status, and phenylephrine/tropicamide administration as confounders is crucial for accurate interpretation of AH protein data.

Molecular hydrogen promotes retinal vascular regeneration and attenuates neovascularization and neuroglial dysfunction in oxygen-induced retinopathy mice

BackgroundRetinopathy of Prematurity (ROP) is a proliferative retinal vascular disease occurring in the retina of premature infants and is the main cause of childhood blindness. Nowadays anti-VEGF and retinal photocoagulation are mainstream treatments for ROP, but they develop a variety of complications. Hydrogen (H2) is widely considered as a useful neuroprotective and antioxidative therapeutic method for hypoxic-ischemic disease without toxic effects. However, whether H2 provides physiological angiogenesis promotion, neovascularization suppression and glial protection in the progression of ROP is largely unknown.This study aims to investigate the effects of H2 on retinal angiogenesis, neovascularization and neuroglial dysfunction in the retinas of oxygen-induced retinopathy (OIR) mice.MethodsIn this study, mice that were seven days old and either wild-type (WT) or Nrf2-deficient (Nrf2−/−) were exposed to 75% oxygen for 5 days and then returned to normal air conditions. Different stages of hydrogen gas (H2) inhalation were administered. Vascular obliteration, neovascularization, and blood vessel leakage were analyzed and compared. To count the number of neovascularization endothelial nuclei, routine HE staining of retinal sections was conducted. Immunohistochemistry was performed using DyLight 594 labeled GSL I-isolectin B4 (IB4), as well as primary antibodies against proliferating cell nuclear antigen (PCNA), glial fibrillary acidic protein (GFAP), and Iba-1. Western blots were used to measure the expression of NF-E2-related factor 2 (Nrf2), vascular endothelial growth factor (VEGF), Notch1, Dll4, and HIF-1α. Additionally, the expression of target genes such as NQO1, HO-1, Notch1, Hey1, Hey2, and Dll4 was measured. Human umbilical vein endothelial cells (HUVECs) treated with H2 under hypoxia were used as an in vitro model. RT-PCR was used to evaluate the mRNA expression of Nrf2, Notch/Dll4, and the target genes. The expression of reactive oxygen species (ROS) was observed using immunofluorescence staining.ResultsOur results indicate that 3–4% H2 does not disturb retinal physiological angiogenesis, but ameliorates vaso-obliteration and neovascularization in OIR mice. Moreover, H2 prevents the decreased density and reverses the morphologic and functional changes in retinal astrocytes caused by oxygen-induced injury. In addition, H2 inhalation reduces microglial activation, especially in the area of neovascularization in OIR mice. H2 plays a protective role in vascular regeneration by promoting Nrf2 activation and suppressing the Dll4-induced Notch signaling pathway in vivo. Also, H2 promotes the proliferation of HUVECs under hypoxia by negatively regulating the Dll4/Notch pathway and reducing ROS levels through Nrf2 pathway aligning with our findings in vivo.Moreover, the retinal oxygen-sensing mechanisms (HIF-1α/VEGF) are also involved in hydrogen-mediated retinal revascularization and neovascularization suppression.ConclusionsCollectively, our results indicate that H2 could be a promising therapeutic agent for POR treatment and that its beneficial effect in human ROP might involve the activation of the Nrf2-Notch axis as well as HIF-1α/VEGF pathways.Graphical

Assessment of Retinal Volume in Individuals Without Ocular Disorders Based on Wide-Field Swept-Source OCT

PurposeTo evaluate retinal volume in eyes without retinal disease using wide-field swept-source optical coherence tomography (SS-OCT). DesignObservational, cross-sectional design ParticipantsA total of 332 eyes of 166 healthy participants. MethodsThe eyes were imaged with OCT-S1 (Canon) using a protocol centered on the fovea cube scans (20 × 23 mm) of SS-OCT images. Retinal volume (6-mm circle, 6–20-mm ring) and various parameters were evaluated in a multivariate analysis using a generalized estimating equation model. Each quadrant of the macula except for the fovea (1–6 mm in diameter) and peripheral ring (6–20 mm in diameter) was also evaluated. Main Outcome MeasureRetinal volume ResultsIn the multivariate analysis, older age and longer axial length were associated with smaller macular retinal volume, whereas older age and left eye were associated with smaller peripheral retinal volume. The temporal area was significantly smaller than all other areas in the macula (1–6 mm), whereas the inferior area was significantly smaller than all other areas in the peripheral retina (6–20 mm). ConclusionsIn wide-field SS-OCT images, age and left eye are negatively correlated with peripheral retinal volume. The thinnest part of the retinal quadrant differs between the macular and peripheral retinas.

Global research trends and future directions in diabetic macular edema research: A bibliometric and visualized analysis.

Diabetic Macular Edema (DME) significantly impairs vision in diabetics, with varied patient responses to current treatments like anti-vascular endothelial growth factor (VEGF) therapy underscoring the necessity for continued research into more effective strategies. This study aims to evaluate global research trends and identify emerging frontiers in DME to guide future research and clinical management. A qualitative and quantitative analysis of publications related to diabetic macular edema retrieved from the Web of Science Core Collection (WoSCC) between its inception and September 4, 2023, was conducted. Microsoft Excel, CiteSpace, VOSviewer, Bibliometrix Package, and Tableau were used for the bibliometric analysis and visualization. This encompasses an examination of the overall distribution of annual output, major countries, regions, institutions, authors, core journals, co-cited references, and keyword analyses. Overall, 5624 publications were analyzed, indicating an increasing trend in DME research. The United States was identified as the leading country in DME research, with the highest h-index of 135 and 91,841 citations. Francesco Bandello emerged as the most prolific author with 97 publications. Neil M. Bressler has the highest h-index and highest total citation count of 46 and 9692, respectively. The journals "Retina - the Journal of Retinal and Vitreous Diseases" and "Ophthalmology" were highlighted as the most prominent in this field. "Retina" leads with 354 publications, a citation count of 11,872, and an h-index of 59. Meanwhile, "Ophthalmology" stands out with the highest overall citation count of 31,558 and the highest h-index of 90. The primary research focal points in diabetic macular edema included "prevalence and risk factors," "pathological mechanisms," "imaging modalities," "treatment strategies," and "clinical trials." Emerging research areas encompassed "deep learning and artificial intelligence," "novel treatment modalities," and "biomarkers." Our bibliometric analysis delineates the leading role of the United States in DME research. We identified current research hotspots, including epidemiological studies, pathophysiological mechanisms, imaging advancements, and treatment innovations. Emerging trends, such as the integration of artificial intelligence and novel therapeutic approaches, highlight future directions. These insights underscore the importance of collaborative and interdisciplinary approaches in advancing DME research and clinical management.

CPD: Inherited retinal diseases 1

Optometrist Sarah Arnold presents thought-provoking case studies on the topic of inherited retinal disease, taking into consideration both the clinical signs of significance and to need to communicate in a sensitive and thoughtful manner

Magnetically Controlled Intraocular Delivery of Dexamethasone Using Silica-Coated Magnetic Nanoparticles.

Although the number of patients with eye diseases is increasing, efficient drug delivery to the posterior segment of the eyeball remains challenging. The reasons include the unique anatomy of the eyeball, the blood-aqueous barrier, the blood-retina barrier, and drug elimination via the anterior chamber and uveoscleral routes. Solutions to these obstacles for therapeutic delivery to the posterior segment will increase the efficacy, efficiency, and safety of ophthalmic treatment. Micro/nanorobots are promising tools to deliver therapeutics to the retina under the direction of an external magnetic field. Although many groups have evaluated potential uses of micro/nanorobots in retinal treatment, most experiments have been performed under idealized in vitro laboratory conditions and thus do not fully demonstrate the clinical feasibility of this approach. This study examined the use of magnetic nanoparticles (MNPs) to deliver dexamethasone, a drug widely used in retinal disease treatment. The MNPs allowed sustainable drug release and successful magnetic manipulation inside bovine vitreous humor and the vitreous humor of living rabbits. Therefore, controlled drug distribution via magnetic manipulation of MNPs is a promising strategy for targeted drug delivery to the retina.

Polymer-Based Nanoparticles with Probucol and Lithocholic Acid: A Novel Therapeutic Approach for Oxidative Stress-Induced Retinopathies.

Oxidative stress is pivotal in retinal disease progression, causing dysfunction in various retinal components. An effective antioxidant, such as probucol (PB), is vital to counteract oxidative stress and emerges as a potential candidate for treating retinal degeneration. However, the challenges associated with delivering lipophilic drugs such as PB to the posterior segment of the eye, specifically targeting photoreceptor cells, necessitate innovative solutions. This study uses formulation-based spray dry encapsulation technology to develop polymer-based PB-lithocholic acid (LCA) nanoparticles and assesses their efficacy in the 661W photoreceptor-like cell line. Incorporating LCA enhances nanoparticles' biological efficacy without compromising PB stability. In vitro studies demonstrate that PB-LCA nanoparticles prevent reactive oxygen species (ROS)-induced oxidative stress by improving cellular viability through the nuclear erythroid 2-related factor 2 (Nrf2)/heme oxygenase-1 (HO-1) pathway. These findings propose PB-LCA nanoparticles as a promising therapeutic strategy for oxidative stress-induced retinopathies.

Analysis of Prognostic Factors in Non-Traumatic and Non-Diabetic Retinopathy Patients Undergoing Vitrectomy.

Vitrectomy is one of the crucial therapeutic interventions for non-traumatic and non-diabetic retinal diseases. However, the prognosis of patients undergoing this procedure and the factors affecting prognosis remain to be clarified. The aim of this study was to analyze the prognostic factors of non-traumatic and non-diabetic retinopathy complicated by vitreous hemorrhage. A retrospective study was conducted on 352 patients, including 152 (43.18%) females, who underwent vitrectomy in our hospital from March 2018 to December 2022, divided into Group A (postoperative complications) and Group B (no complications) according to whether complications occurred during postoperative follow-up. General and clinical data of the two groups were collected and compared. Binary logistic regression was used to analyze the main factors affecting prognosis. All patients were followed up for 12 months. A total of 87 patients had postoperative complications, accounting for 24.72% (87/352), and were classified as Group A. A total of 265 patients who had no postoperative complications, accounting for 75.28% (265/352), were classified as Group B. There were significant differences in preoperative visual acuity, time of surgical intervention, preoperative fundus condition, stage of retinopathy, preoperative intraocular pressure and age between the two groups (p < 0.05), and these indices were identified as independent risk factors affecting the prognosis of patients (odds ratio >1). Preoperative visual acuity, time of surgical intervention, preoperative fundus condition, stage of retinopathy, preoperative intraocular pressure and age are all factors affecting the prognosis of patients with non-traumatic and non-diabetic retinopathy while undergoing vitrectomy. Personalized care is required to improve the surgical outcome for these patients.

Administration of Bicarbonate Protects Mitochondria, Rescues Retinal Ganglion Cells, and Ameliorates Visual Dysfunction Caused by Oxidative Stress.

Oxidative stress is a key factor causing mitochondrial dysfunction and retinal ganglion cell (RGC) death in glaucomatous neurodegeneration. The cyclic adenosine monophosphate (cAMP)/protein kinase A (PKA) signaling pathway is involved in mitochondrial protection, promoting RGC survival. Soluble adenylyl cyclase (sAC) is a key regulator of the cyclic adenosine monophosphate (cAMP)/protein kinase A (PKA) signaling pathway, which is known to protect mitochondria and promote RGC survival. However, the precise molecular mechanisms connecting the sAC-mediated signaling pathway with mitochondrial protection in RGCs against oxidative stress are not well characterized. Here, we demonstrate that sAC plays a critical role in protecting RGC mitochondria from oxidative stress. Using mouse models of oxidative stress induced by ischemic injury and paraquat administration, we found that administration of bicarbonate, as an activator of sAC, protected RGCs, blocked AMP-activated protein kinase activation, inhibited glial activation, and improved visual function. Moreover, we found that this is the result of preserving mitochondrial dynamics (fusion and fission), promoting mitochondrial bioenergetics and biogenesis, and preventing metabolic stress and apoptotic cell death. Notably, the administration of bicarbonate ameliorated mitochondrial dysfunction in RGCs by enhancing mitochondrial biogenesis, preserving mitochondrial structure, and increasing ATP production in oxidatively stressed RGCs. These findings suggest that activating sAC enhances the mitochondrial structure and function in RGCs to counter oxidative stress, consequently promoting RGC protection. We propose that modulation of the sAC-mediated signaling pathway has therapeutic potential acting on RGC mitochondria for treating glaucoma and other retinal diseases.

Artificial Intelligence to Facilitate Clinical Trial Recruitment in Age-Related Macular Degeneration

ObjectiveRecent developments in artificial intelligence (AI) have positioned it to transform several stages of the clinical trial process. In this study, we explore the role of AI in clinical trial recruitment of individuals with geographic atrophy (GA), an advanced stage of age-related macular degeneration, amidst numerous ongoing clinical trials for this condition. DesignCross-sectional study.Subjects, Participants, and/or Controls: Retrospective dataset from the INSIGHT Health Data Research Hub at Moorfields Eye Hospital in London, United Kingdom, including 306,651 patients (602,826 eyes) with suspected retinal disease who underwent optical coherence tomography (OCT) imaging between 1 January 2008 and 10 April 2023. Methods, Intervention, or TestingA deep learning model was trained on OCT scans to identify patients potentially eligible for GA trials, using AI-generated segmentations of retinal tissue. This method's efficacy was compared against a traditional keyword-based electronic health record (EHR) search. A clinical validation with fundus autofluorescence (FAF) images was performed to calculate the positive predictive value (PPV) of this approach, by comparing AI predictions to expert assessments. Main Outcome MeasuresThe primary outcomes included the PPV of AI in identifying trial-eligible patients, and the secondary outcome was the intraclass correlation between GA areas segmented on FAF by experts and AI-segmented OCT scans. ResultsThe AI system shortlisted a larger number of eligible patients with greater precision (1,139, PPV: 63%; 95% CI: 54–71%) compared to the EHR search (693, PPV: 40%; 95% CI: 39–42%). A combined AI-EHR approach identified 604 eligible patients with a PPV of 86% (95% CI: 79–92%). Intraclass correlation of GA area segmented on FAF versus AI-segmented area on OCT was 0.77 (95% CI: 0.68–0.84) for cases meeting trial criteria. The AI also adjusts to the distinct imaging criteria from several clinical trials, generating tailored shortlists ranging from 438 to 1,817 patients. ConclusionsThis study demonstrates the potential for AI in facilitating automated pre-screening for clinical trials in GA, enabling site feasibility assessments, data-driven protocol design, and cost reduction. Once treatments are available, similar AI systems could also be used to identify individuals who may benefit from treatment.

Lutein Modulates Cellular Functionalities and Regulates NLRP3 Inflammasome in a H2O2-Challenged Three-Dimensional Retinal Pigment Epithelium Model.

Excessive hydrogen peroxide (H2O2) generated during retinal cell metabolic activity could lead to oxidative degeneration of retinal pigment epithelium (RPE) tissue, a specific pathological process implicated in various retinal diseases resulting in blindness, which can be mitigated by taking dietary antioxidants to prevent inflammation and impaired cellular dysfunction. This study tested the hypothesis that damages induced by oxidative stresses can be mitigated by lutein in a H2O2-challenged model, which was based on an ARPE-19 cell monolayer cultured on three-dimensional (3D)-printed fibrous scaffolds. Pretreating these models with lutein (0.5 μM) for 24 h can significantly lower the oxidative stress and maintain phagocytosis and barrier function. Moreover, lutein can modulate the NLRP3 inflammasome, leading to a ∼40% decrease in the pro-inflammatory cytokine (IL-1β and IL-18) levels. Collectively, this study suggests that the 3D RPE model is an effective tool to examine the capability of lutein to modulate cellular functionalities and regulate NLRP3 inflammation.

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.

Insulin resistance in the retina: possible implications for certain ocular diseases.

Insulin resistance (IR) is becoming a worldwide medical and public health challenge as an increasing prevalence of obesity and metabolic disorders. Accumulated evidence has demonstrated a strong relationship between IR and a higher incidence of several dramatically vision-threatening retinal diseases, including diabetic retinopathy, age-related macular degeneration, and glaucoma. In this review, we provide a schematic overview of the associations between IR and certain ocular diseases and further explore the possible mechanisms. Although the exact causes explaining these associations have not been fully elucidated, underlying mechanisms of oxidative stress, chronic low-grade inflammation, endothelial dysfunction and vasoconstriction, and neurodegenerative impairments may be involved. Given that IR is a modifiable risk factor, it may be important to identify patients at a high IR level with prompt treatment, which may decrease the risk of developing certain ocular diseases. Additionally, improving IR through the activation of insulin signaling pathways could become a potential therapeutic target.

Naringenin-loaded poly(3-hydroxybutyrate-co-3-hydroxyvalerate)-based devices have an anti-inflammatory activity on microglia

Retinal degenerative diseases, such as retinitis pigmentosa, represent a significant fraction of the burden of blindness. This kind of diseases involves the activation of microglial cells which causes neuroinflammation. Flavonoids, such as naringenin (Nar), are able to modulate the pro-inflammatory behavior of the microglia cells but their low bioavailability often hinders this activity. In this context, the aim of this research activity was the development of implantable drug delivery systems through Nar encapsulation into a polymeric matrix, as a valuable way to increase its bioavailability. For this purpose, a blend between microbial poly(3-hydroxybutyrate-co-3-hydroxyvaerate) (PHBV) and poly(d,l-lactide-co-glycolide (PLGA) was processed by means of two different fabrication techniques, i.e., melt-spinning and wet-spinning, to fabricate rods designed for ocular implantation. The two developed kinds of rod had different morphology and thermal properties, as demonstrated by scanning electron microscopy, thermogravimetric analysis, and differential scanning calorimetry. In addition, an increase in Nar concentration in the starting polymeric mixture (1–5 wt% respect to device weight) determined a higher drug encapsulation efficiency, with a resulting drug loading increasing from 0.5 to 3.5 % and from 0.4 to 4.4 % for melt- and wet-spun rods, respectively. A significant effect of processing technique and drug loading on the resulting release kinetics was also observed, with the devices loaded with a higher percentage of Nar reaching a 100 % cumulative drug release after 38 and 73 days in the case of wet- and melt-spun rods, respectively. In addition, the wet-spun rods showed a first order drug release kinetics while the melt-spun rods a zero order one. The bioactivity of the wet-spun rods was tested on lipopolysaccharide-activated BV2 as well as primary murine microglia cells, thus demonstrating the ability of the released flavonoid to favor cell maturation from a pro-inflammatory to an anti-inflammatory phenotype.

Exploring the impact of Choroideremia on women with phenotypic and/or genotypic evidence of disease: insights from a global survey

ABSTRACT Introduction Choroideremia (CHM) is an X-linked inherited retinal disease mostly affecting males. However, women with phenotypic and/or genotypic evidence of CHM may develop degenerative visual disability with advancing age. Our objective was to determine the visual impacts of phenotypic and/or genotypic evidence of CHM in women and its associated psychosocial burden and influence on activities of daily living (ADLs). Methods We conducted an international cross-sectional survey from April to December 2022 using an e-questionnaire distributed through not-for-profit stakeholder organizations and social media plat-forms. Results With a total of 55 respondents (n = 55), most women with phenotypic and/or genotypic evidence of CHM (76%) reported a change in their visual acuity. When assessing its impact on ADLs, Pearson’s correlation coefficient showed a negative correlation between driving (p = 0.046) and mobility capabil-ities (0.046) with the respondent’s age. More than half of women reported being afraid, anxious, and stressed, with women below the age of 50 years old reporting a significantly higher level of distress and hopelessness (p = 0.003), anxiety (p = 0.00007), issues with relaxing (p = 0.025), and negative personal thoughts (p = 0.042). Conclusion Overall, this survey outlines both physical and psychological burden of being a woman with phenotypic and/or genotypic evidence of CHM. Given the limited clinical research in females affected by CHM, this patient-centered survey is a crucial advocacy tool for these individuals.

Синаптичні процеси гангліозних клітин сітківки ока ссавців

To date, mammalian retinal ganglion cells have been studied quite well, and their diversity, development, and connections have been clarified. Fifty subtypes of these cells have already been identified, each of which optimally encodes unique visual capabilities and projects visual information to various targets in the brain, where it is decoded. Some types of ganglion cells express the photopigment melanopsin (Opn4), which makes them directly sensitive to light. In this review, we discuss the diversity of ganglion cells, their characteristics and differences, and describe the structure of retinal neurons and the synaptic processes that occur in them. Since the quality of human life is seriously affected by retinal diseases that can lead to vision loss, scientists are paying close attention to the causes of visual clarity and quality and the role of retinal ganglion cells in this process, conducting multidirectional research using new methods and different objects for study.

Enhancing retinal disease diagnosis through AI: Evaluating performance, ethical considerations, and clinical implementation

BackgroundThe research problem addresses the need for accurate and efficient detection of retina diseases using artificial intelligence (AI) technologies. The specific aim is to evaluate the performance, ethical considerations, and clinical implementation of AI-driven retina disease detection systems. MethodsThis study is a systematic review. Data sources assessed included various electronic databases searched up to July 31, 2023. The prespecified criteria for study inclusion were studies involving AI algorithms for retina disease detection, including those focused on diabetic retinopathy, age-related macular degeneration, and glaucoma. Participant eligibility criteria encompassed human subjects of all ages, and the interventions assessed were AI-based diagnostic tools compared to traditional diagnostic methods. Only randomized controlled trials and observational studies set in clinical environments were included, covering a time span from the inception of AI technology. FindingsThe search identified 145 studies, of which 61 met the inclusion criteria and were eligible for analysis. The narrative summary of findings indicated that AI algorithms generally demonstrated high accuracy, sensitivity, and specificity in detecting retinal diseases. Deep learning algorithms showed a sensitivity of 90 % and specificity of 98 % for diabetic retinopathy detection. However, several studies highlighted concerns about algorithmic bias, data privacy, and the need for diverse and representative datasets to ensure generalizability across different populations. InterpretationThe AI-driven retina disease detection systems have significant potential to improve diagnostic accuracy and efficiency in clinical practice. Ethical considerations regarding patient privacy, the risk of algorithmic bias, and the challenges of integrating AI into existing healthcare workflows must be addressed. The study underscores the importance of ongoing validation, ethical scrutiny, and interdisciplinary collaboration to harness the benefits of AI while mitigating its risks, ensuring responsible and equitable implementation in clinical settings.

Multi-label classification of retinal diseases based on fundus images using Resnet and Transformer.

Retinal disorders are a major cause of irreversible vision loss, which can be mitigated through accurate and early diagnosis. Conventionally, fundus images are used as the gold diagnosis standard in detecting retinal diseases. In recent years, more and more researchers have employed deep learning methods for diagnosing ophthalmic diseases using fundus photography datasets. Among the studies, most of them focus on diagnosing a single disease in fundus images, making it still challenging for the diagnosis of multiple diseases. In this paper, we propose a framework that combines ResNet and Transformer for multi-label classification of retinal disease. This model employs ResNet to extract image features, utilizes Transformer to capture global information, and enhances the relationships between categories through learnable label embedding. On the publicly available Ocular Disease Intelligent Recognition (ODIR-5k) dataset, the proposed method achieves a mean average precision of 92.86%, an area under the curve (AUC) of 97.27%, and a recall of 90.62%, which outperforms other state-of-the-art approaches for the multi-label classification. The proposed method represents a significant advancement in the field of retinal disease diagnosis, offering a more accurate, efficient, and comprehensive model for the detection of multiple retinal conditions.

The Effect of Perinatal High‐Dose Erythropoietin on Retinal Structural and Vascular Characteristics in Children Born Preterm

To study the long-term effects of perinatal high-dose recombinant human erythropoietin (rhEPO) on macular structural and vascular development in preterm children. Randomized, double-blind clinical trial follow-up plus cohort study. Setting: Department of Ophthalmology, University Hospital Zurich, Zurich, Switzerland. extremely or very preterm born children aged 7-15 years from an ongoing neuropediatric study (EpoKids). These had been previously randomized to receive either high-dose rhEPO or placebo perinatally. participation in the EpoKids Study, written informed consent (IC). previous ocular trauma or surgery; retinal or developmental disease unrelated to prematurity. Term-born children of comparable age were enrolled as a healthy control (HC) group. term birth, IC. any ocular or visual abnormality, high refractive error. Examiners were blinded regarding intervention status until completion of all analyses. (Participants/guardians remain blinded). Spectral-domain OCT scans (Heidelberg Spectralis system) and OCTA imaging (Zeiss PlexElite 9000) were obtained. Ophthalmological and orthoptic examinations excluded ocular comorbidities. OCT (central retinal thickness, CRT; total macular volume, TMV), superficial plexus OCTA (foveal avascular zone, FAZ; vessel density, VD; vessel length density, VLD) parameters and foveal hypoplasia grade according to published criteria. Macular vessel density parameters (VD and VLD) were significantly lower (p =0.015, CI-95: 0.01 to 0.06 and p=0.015, CI-95: 0.74 to 3.64) in the EPO group (n= 52) when compared to placebo (n=35). No other significant differences were observed between the EPO and placebo group. When comparing the intervention subgroups to HC we found six significant differences in OCT and OCTA parameters (FAZ, VD, VLD and CRT comparing HC and EPO group; FAZ and CRT when comparing HC and placebo group). Early high-dose rhEPO in infants born extremely or very preterm affects macular vessel density parameters compared to placebo. Premature birth (regardless of intervention status) affects retinal structure and vascular development. Our findings on macular vascular development do not contraindicate the administration of early high-dose EPO in preterm infants. For further understanding of the role of EPO on macular development and its clinical significance, future studies are needed.

RDLR: A Robust Deep Learning-Based Image Registration Method for Pediatric Retinal Images.

Retinal diseases stand as a primary cause of childhood blindness. Analyzing the progression of these diseases requires close attention to lesion morphology and spatial information. Standard image registration methods fail to accurately reconstruct pediatric fundus images containing significant distortion and blurring. To address this challenge, we proposed a robust deep learning-based image registration method (RDLR). The method consisted of two modules: registration module (RM) and panoramic view module (PVM). RM effectively integrated global and local feature information and learned prior information related to the orientation of images. PVM was capable of reconstructing spatial information in panoramic images. Furthermore, as the registration model was trained on over 280,000 pediatric fundus images, we introduced a registration annotation automatic generation process coupled with a quality control module to ensure the reliability of training data. We compared the performance of RDLR to the other methods, including conventional registration pipeline (CRP), voxel morph (WM), generalizable image matcher (GIM), and self-supervised techniques (SS). RDLR achieved significantly higher registration accuracy (average Dice score of 0.948) than the other methods (ranging from 0.491 to 0.802). The resulting panoramic retinal maps reconstructed by RDLR also demonstrated substantially higher fidelity (average Dice score of 0.960) compared to the other methods (ranging from 0.720 to 0.783). Overall, the proposed method addressed key challenges in pediatric retinal imaging, providing an effective solution to enhance disease diagnosis. Our source code is available at https://github.com/wuwusky/RobustDeepLeraningRegistration .