Hasil untuk "Ophthalmology"

Mari Masunaga, Reo Shimatani, Kazumi Shinozaki et al.

Dendritic keratitis is a form of eye infection caused by herpes simplex virus (HSV). The virus spreads via direct cell-to-cell infection among corneal epithelial cells. This leads to the formation of dendritic lesions characterized by terminal bulbs at their tips. Under immunosuppression, the condition may progress to geographic keratitis, which is a map-shaped lesion with dendritic tails. The mechanism of this pattern formation remains to be elucidated. In this study, we propose a mathematical model to elucidate the mechanisms of lesion pattern formation in dendritic keratitis. Our model shows that increased production of infection-suppressive cytokines induces dendritic patterns with terminal bulbs, whereas reduced cytokine levels lead to geographic patterns. Furthermore, altering the spatial distribution of cytokine production can reproduce dendritic tails. By including external cytokine secretion, we could reproduce tapered lesions observed in non-HSV keratitis. By clarifying the mechanisms behind terminal bulb formation and reproducing atypical lesion morphologies, our findings enhance the understanding of herpetic keratitis and highlight the utility of mathematical modeling in ophthalmology.

Jinglun Yu, Yaning Wang, Rosalinda Xiong et al.

Training deep learning models for corneal optical coherence tomography (OCT) imaging is limited by the availability of large, well-annotated datasets. We present a configurable Monte Carlo simulation framework that generates synthetic corneal B-scan optical OCT images with pixel-level five-layer segmentation labels derived directly from the simulation geometry. A five-layer corneal model with Gaussian surfaces captures curvature and thickness variability in healthy and keratoconic eyes. Each layer is assigned optical properties from the literature and light transport is simulated using Monte Carlo modeling of light transport in multi-layered tissues (MCML), while incorporating system features such as the confocal PSF and sensitivity roll-off. This approach produces over 10,000 high-resolution (1024x1024) image-label pairs and supports customization of geometry, photon count, noise, and system parameters. The resulting dataset enables systematic training, validation, and benchmarking of AI models under controlled, ground-truth conditions, providing a reproducible and scalable resource to support the development of diagnostic and surgical guidance applications in image-guided ophthalmology.

Gustav Schmidt, Philipp Berens, Sarah Müller

It has been suggested that generative image models such as diffusion models can improve performance on clinically relevant tasks by offering deep learning models supplementary training data. However, most conditional diffusion models treat disease stages as independent classes, ignoring the continuous nature of disease progression. This mismatch is problematic in medical imaging because continuous pathological processes are typically only observed through coarse, discrete but ordered labels as in ophthalmology for diabetic retinopathy (DR). We propose an ordinal latent diffusion model for generating color fundus images that explicitly incorporates the ordered structure of DR severity into the generation process. Instead of categorical conditioning, we used a scalar disease representation, enabling a smooth transition between adjacent stages. We evaluated our approach using visual realism metrics and classification-based clinical consistency analysis on the EyePACS dataset. Compared to a standard conditional diffusion model, our model reduced the Fréchet inception distance for four of the five DR stages and increased the quadratic weighted $κ$ from 0.79 to 0.87. Furthermore, interpolation experiments showed that the model captured a continuous spectrum of disease progression learned from ordered, coarse class labels.

Sreelekha P, Sushma Naranappa Salethoor, Shanti K

BackgroundMeibomian Gland Dysfunction (MGD) has become increasingly common in community practice, often presenting as dryness, irritation, and ocular fatigue. Factors such as prolonged screen exposure, environmental irritants, and advancing age contribute to its growing burden in primary health settings. Conventional management usually focuses on symptom relief, leaving a need for safer, sustainable options that can be applied easily in routine care. Ayurvedic eye therapies, known for their gentle yet restorative effects, may offer such an alternative.MethodsA single-arm, open-label clinical study was conducted on 30 patients with clinically diagnosed Meibomian Gland Dysfunction (MGD). The treatment protocol consisted of daily nasal oil instillation (pratimarsha nasya) using Anu oil for 30 days, along with medicated eye drops (aschyotana) prepared from Moringa oleifera leaves and localized warm ocular fomentation (avagundana) using a herbal bolus immersed in a Triphala-based decoction for the first 15 days. Clinical outcomes were assessed using both subjective and objective parameters, including the Ocular Surface Disease Index (OSDI), Tear Film Break-Up Time (TBUT), Schirmer’s Test I, fluorescein staining, and meibomian gland expressibility. Assessments were performed at baseline, immediately after treatment, and during follow-up visits. Data were analyzed using the Friedman test and Wilcoxon Signed-Rank test.ResultsPatients showed marked improvement in all clinical parameters. OSDI, TBUT, and Schirmer’s scores improved significantly (p < 0.001). Fluorescein staining was reduced to nil after treatment and remained stable during follow-ups, while meibomian gland expressibility improved consistently, reflecting better tear film stability and glandular function. No side effects or adverse reactions were reported.ConclusionThis exploratory study suggests that a simple Ayurvedic care regimen may be associated with improvement in symptoms and ocular surface parameters in individuals with Meibomian Gland Dysfunction. Given its non-invasive nature, ease of administration, and suitability for low-resource settings, this approach may have potential relevance as a supportive strategy within primary eye care. However, these findings are preliminary, and further controlled studies are required to confirm effectiveness and define its role in community-level preventive and promotive eye health.Limitations of the studyThis was a single-arm exploratory study with a small sample size and limited follow-up. Consequently, the findings are preliminary and require confirmation in controlled trials.

Nurcan Gürsoy, Ersan Gürsoy

Abstract Correctable refractive errors are a major, preventable cause of visual impairment. Refractive surgery is widely promoted online, yet how Turkish-language YouTube videos frame benefits, risks, recovery, and long-term outcomes—and how this framing differs between patient and physician narrators—remains underexplored. We aimed to qualitatively compare patient- and physician-generated Turkish-language YouTube videos on refractive surgery and to describe audience engagement. We conducted a reflexive thematic analysis (Braun & Clarke) of 64 publicly available videos (29 patient, 35 physician) meeting predefined criteria (Turkish; primarily refractive surgery; ≥1 min; ≥1,000 views; ≥240p). Searches were performed on 15 July 2025 using predefined search strings. Videos were transcribed verbatim and inductively coded in NVivo by two researchers. Between-group differences in engagement metrics were assessed with Mann–Whitney U tests, with a one-video-per-channel sensitivity analysis to address potential clustering. Patient narratives foregrounded lived experience (decision-making, perioperative discomfort, postoperative visual fluctuations, and symptoms such as dry eye and glare/halos) and often raised concerns about commercialization. Physician narratives emphasized candidacy assessment, procedure selection, recovery timelines, and risk mitigation. In the one-video-per-channel sensitivity analysis (patient n = 27; physician n = 23), patient videos received more likes (median 300 [IQR 1,639] vs. 59 [269], p = 0.009) and showed a higher like-to-view ratio (0.013 [0.01] vs. 0.006 [0.01], p < 0.001), whereas view counts were not significantly different (24,000 [98,900] vs. 18,000 [48,500], p = 0.224). Turkish-language YouTube narratives share experiential touchpoints but diverge systematically in how risks, commercialization, and expectations are framed by patients versus physicians. Findings support the need for balanced, accurate, and discoverable patient-facing materials tailored to platform dynamics.

Gustavo Adolpho Bonesso, Carlos Marcelo Gurjão de Godoy, Tammy Hentona Osaki et al.

Blinking is a vital physiological process that protects and maintains the health of the ocular surface. Objective assessment of eyelid movements remains challenging due to the complexity, cost, and limited clinical applicability of existing tools. This study presents the Bapp (Blink Application), a mobile application developed using the Flutter framework and integrated with Google ML Kit for on-device, real-time analysis of eyelid movements, and its clinical validation. The validation was performed using 45 videos from patients, whose blinks were manually annotated by an ophthalmology specialist as the ground truth. The Bapp's performance was evaluated using standard metrics, with results demonstrating 98.4% precision, 96.9% recall, and an overall accuracy of 98.3%. These outcomes confirm the reliability of the Bapp as a portable, accessible, and objective tool for monitoring eyelid movements. The application offers a promising alternative to traditional manual blink counting, supporting continuous ocular health monitoring and postoperative evaluation in clinical environments.

Leonor Fernandes, Tiago Gonçalves, João Matos et al.

Diabetic retinopathy (DR) is a leading cause of vision loss in working-age adults. While screening reduces the risk of blindness, traditional imaging is often costly and inaccessible. Artificial intelligence (AI) algorithms present a scalable diagnostic solution, but concerns regarding fairness and generalization persist. This work evaluates the fairness and performance of image-trained models in DR prediction, as well as the impact of disentanglement as a bias mitigation technique, using the diverse mBRSET fundus dataset. Three models, ConvNeXt V2, DINOv2, and Swin V2, were trained on macula images to predict DR and sensitive attributes (SAs) (e.g., age and gender/sex). Fairness was assessed between subgroups of SAs, and disentanglement was applied to reduce bias. All models achieved high DR prediction performance in diagnosing (up to 94% AUROC) and could reasonably predict age and gender/sex (91% and 77% AUROC, respectively). Fairness assessment suggests disparities, such as a 10% AUROC gap between age groups in DINOv2. Disentangling SAs from DR prediction had varying results, depending on the model selected. Disentanglement improved DINOv2 performance (2% AUROC gain), but led to performance drops in ConvNeXt V2 and Swin V2 (7% and 3%, respectively). These findings highlight the complexity of disentangling fine-grained features in fundus imaging and emphasize the importance of fairness in medical imaging AI to ensure equitable and reliable healthcare solutions.

José Morano, Botond Fazekas, Emese Sükei et al.

Artificial intelligence (AI) has become a fundamental tool for assisting clinicians in analyzing ophthalmic images, such as optical coherence tomography (OCT). However, developing AI models often requires extensive annotation, and existing models tend to underperform on independent, unseen data. Foundation models (FMs), large AI models trained on vast unlabeled datasets, have shown promise in overcoming these challenges. Nonetheless, available FMs for ophthalmology lack extensive validation, especially for segmentation tasks, and focus on a single imaging modality. In this context, we propose MIRAGE, a novel multimodal FM for the analysis of OCT and scanning laser ophthalmoscopy (SLO) images. Additionally, we propose a new evaluation benchmark with OCT/SLO classification and segmentation tasks. The comparison with general and specialized FMs and segmentation methods shows the superiority of MIRAGE in both types of tasks, highlighting its suitability as a basis for the development of robust AI systems for retinal OCT image analysis. Both MIRAGE and the evaluation benchmark are publicly available: https://github.com/j-morano/MIRAGE.

Wiktor Stopyra, Oleksiy Voytsekhivskyy, Andrzej Grzybowski

<b>Purpose:</b> To compare the accuracy of seven artificial intelligence (AI)-based intraocular lens (IOL) power calculation formulas in medium-long Caucasian eyes regarding the root-mean-square absolute error (RMSAE), the median absolute error (MedAE) and the percentage of eyes with a prediction error (PE) within ±0.5 D. <b>Methods:</b> Data on Caucasian patients who underwent uneventful phacoemulsification between May 2018 and September 2023 in MW-Med Eye Center, Krakow, Poland and Kyiv Clinical Ophthalmology Hospital Eye Microsurgery Center, Kyiv, Ukraine were reviewed. Inclusion criteria, i.e., complete biometric and refractive data, were applied. Exclusion criteria were as follows: intraoperative or postoperative complications, previous eye surgery or corneal diseases, postoperative BCVA less than 0.8, and corneal astigmatism greater than 2.0 D. Prior to phacoemulsification, IOL power was computed using SRK/T, Holladay1, Haigis, Holladay 2, and Hoffer Q. The refraction was measured three months after cataract surgery. Post-surgery intraocular lens calculations for Hill-RBF 3.0, Kane, PEARL-DGS, Ladas Super Formula AI (LSF AI), Hoffer QST, Karmona, and Nallasamy were performed. RMSAE, MedAE, and the percentage of eyes with a PE within ±0.25 D, ±0.50 D, ±0.75 D, and ±1.00 were counted. <b>Results:</b> Two hundred fourteen eyes with axial lengths ranging from 24.50 mm to 25.97 mm were tested. The Hill-RBF 3.0 formula yielded the lowest RMSAE (0.368), just before Pearl-DGS (0.374) and Hoffer QST (0.378). The lowest MedAE was achieved by Hill-RBF 3.0 (0.200), the second-lowest by LSF AI (0.210), and the third-lowest by Kane (0.228). The highest percentage of eyes with a PE within ±0.50 D was obtained by Hill-RBF 3.0, LSF AI, and Pearl-DGS (86.45%, 85.51%, and 85.05%, respectively). <b>Conclusions:</b> The Hill-RBF 3.0 formula provided highly accurate outcomes in medium-long eyes. All studied AI-based formulas yielded good results in IOL power calculation.

Guanzhou Di, Chen Lu, Mengting Xue et al.

ObjectivesRetinal pigment epithelium (RPE) cell transplantation holds therapeutic promise for retinal degenerative diseases, but longitudinal monitoring of graft survival and efficacy remains clinically challenging. The aim of this study is to develop a simple and effective method for the therapeutic quantification of RPE cell transplantation and immune rejection in vivo.MethodsA nanoprobe was developed and modified to label donor RPE cells, and used to monitor the position and intensity of the fluorescence signal in vivo. Immunofluorescence staining and single-cell RNA sequencing (scRNA-seq) were used to characterize the cell types showing the fluorescence signal of the nanoprobe and to determine the composition of the immune microenvironment associated with subretinal transplantation.ResultsThe spatial distribution of the fluorescence signal of the nanoprobe corresponded with the site of transplantation, but the signal intensity decreased over time, while the signal distribution extended to the choroid. Additionally, the nanoprobe fluorescence signal was detected in the liver and spleen during long-term monitoring. Conversely, in mice administered the immunosuppressive drug cyclosporine A, the decrease in signal intensity was slower and the expansion of the signal distribution was less pronounced. Immunofluorescence analysis revealed a significant temporal increase in the proportion of macrophages with nanoprobe-labeled cells following transplantation. The stability and cell-penetrating ability of the nanoprobe enables the labeling of immune cell niches in RPE transplantation. Additionally, scRNA-seq analysis of nanoprobe-labeled cells identified MDK and ANXA1 signaling pathway in donor RPE cells as initiators of the immune rejection cascade, which were further amplified by macrophage-mediated pro-inflammatory signaling.ConclusionNear-infrared fluorescent nanoprobes represent a reliable method for in vivo tracing of donor RPE cells and long-term observation of nanoprobe distribution can be used to evaluate the degree of immune rejection. Molecular analysis of nanoprobe-labeled cells facilitates the characterization of the dynamic immune cell rejection niche and the landscape of donor-host interactions in RPE transplantation.

Yu Bin Son, Kye-Hyung Kim, Hee-Young Choi et al.

Sribala Vidyadhari Chinta, Zichong Wang, Avash Palikhe et al.

Artificial intelligence (AI) is rapidly advancing in healthcare, enhancing the efficiency and effectiveness of services across various specialties, including cardiology, ophthalmology, dermatology, emergency medicine, etc. AI applications have significantly improved diagnostic accuracy, treatment personalization, and patient outcome predictions by leveraging technologies such as machine learning, neural networks, and natural language processing. However, these advancements also introduce substantial ethical and fairness challenges, particularly related to biases in data and algorithms. These biases can lead to disparities in healthcare delivery, affecting diagnostic accuracy and treatment outcomes across different demographic groups. This review paper examines the integration of AI in healthcare, highlighting critical challenges related to bias and exploring strategies for mitigation. We emphasize the necessity of diverse datasets, fairness-aware algorithms, and regulatory frameworks to ensure equitable healthcare delivery. The paper concludes with recommendations for future research, advocating for interdisciplinary approaches, transparency in AI decision-making, and the development of innovative and inclusive AI applications.

Thomas Saigre, Christophe Prud'Homme, Marcela Szopos

Heat transfer in the human eyeball, a complex organ, is significantly influenced by various pathophysiological and external parameters. Particularly, heat transfer critically affects fluid behavior within the eye and ocular drug delivery processes. Overcoming the challenges of experimental analysis, this study introduces a comprehensive three-dimensional mathematical and computational model to simulate the heat transfer in a realistic geometry. Our work includes an extensive sensitivity analysis to address uncertainties and delineate the impact of different variables on heat distribution in ocular tissues. To manage the model's complexity, we employed a very fast model reduction technique with certified sharp error bounds, ensuring computational efficiency without compromising accuracy. Our results demonstrate remarkable consistency with experimental observations and align closely with existing numerical findings in the literature. Crucially, our findings underscore the significant role of blood flowand environmental conditions, particularly in the eye's internal tissues. Clinically, this model offers a promising tool for examining the temperature-related effects of various therapeutic interventions on the eye. Such insights are invaluable for optimizing treatment strategies in ophthalmology.

Md. Touhidul Islam, Md. Abtahi Majeed Chowdhury, Mahmudul Hasan et al.

Ophthalmic diseases represent a significant global health issue, necessitating the use of advanced precise diagnostic tools. Optical Coherence Tomography (OCT) imagery which offers high-resolution cross-sectional images of the retina has become a pivotal imaging modality in ophthalmology. Traditionally physicians have manually detected various diseases and biomarkers from such diagnostic imagery. In recent times, deep learning techniques have been extensively used for medical diagnostic tasks enabling fast and precise diagnosis. This paper presents a novel approach for ophthalmic biomarker detection using an ensemble of Convolutional Neural Network (CNN) and Vision Transformer. While CNNs are good for feature extraction within the local context of the image, transformers are known for their ability to extract features from the global context of the image. Using an ensemble of both techniques allows us to harness the best of both worlds. Our method has been implemented on the OLIVES dataset to detect 6 major biomarkers from the OCT images and shows significant improvement of the macro averaged F1 score on the dataset.

Hong‐Bin Lin, Pu Hong, Meng‐Yu Yin et al.

Background Cardiac damage induced by ischemic stroke, such as arrhythmia, cardiac dysfunction, and even cardiac arrest, is referred to as cerebral‐cardiac syndrome (CCS). Cardiac macrophages are reported to be closely associated with stroke‐induced cardiac damage. However, the role of macrophage subsets in CCS is still unclear due to their heterogeneity. Sympathetic nerves play a significant role in regulating macrophages in cardiovascular disease. However, the role of macrophage subsets and sympathetic nerves in CCS is still unclear. Methods and Results In this study, a middle cerebral artery occlusion mouse model was used to simulate ischemic stroke. ECG and echocardiography were used to assess cardiac function. We used Cx3cr1GFPCcr2RFP mice and NLRP3‐deficient mice in combination with Smart‐seq2 RNA sequencing to confirm the role of macrophage subsets in CCS. We demonstrated that ischemic stroke‐induced cardiac damage is characterized by severe cardiac dysfunction and robust infiltration of monocyte‐derived macrophages into the heart. Subsequently, we identified that cardiac monocyte‐derived macrophages displayed a proinflammatory profile. We also observed that cardiac dysfunction was rescued in ischemic stroke mice by blocking macrophage infiltration using a CCR2 antagonist and NLRP3‐deficient mice. In addition, a cardiac sympathetic nerve retrograde tracer and a sympathectomy method were used to explore the relationship between sympathetic nerves and cardiac macrophages. We found that cardiac sympathetic nerves are significantly activated after ischemic stroke, which contributes to the infiltration of monocyte‐derived macrophages and subsequent cardiac dysfunction. Conclusions Our findings suggest a potential pathogenesis of CCS involving the cardiac sympathetic nerve–monocyte‐derived macrophage axis.

M. Chiang, A. Sommer, W. Rich et al.

PURPOSE To describe the characteristics of the patient population included in the 2016 IRIS® Registry (Intelligent Research in Sight) database for analytic aims. DESIGN Description of a clinical data registry. PARTICIPANTS The 2016 IRIS Registry database consists of 17 363 018 unique patients from 7200 United States-based ophthalmologists in the United States. METHODS Electronic health record (EHR) data were extracted from the participating practices and placed into a clinical database. The approach can be used across dozens of EHR systems. MAIN OUTCOME MEASURES Demographic characteristics. RESULTS The 2016 IRIS Registry database includes data about patient demographics, top-coded disease conditions, and visit rates. CONCLUSIONS The IRIS Registry is a unique, large, real-world data set that is available for analytics to provide perspectives and to learn about current ophthalmic care and treatment outcomes. The IRIS Registry can be used to answer questions about practice patterns, use, disease prevalence, clinical outcomes, and the comparative effectiveness of different treatments. Limitations of the data are the same limitations associated with EHR data in terms of documentation errors or missing data and the lack of images. Currently, open access to the database is not available, but there are opportunities for researchers to submit proposals for analyses, for example through a Research to Prevent Blindness and American Academy of Ophthalmology Award for IRIS Registry Research.

Ke Zou, Tian Lin, Xuedong Yuan et al.

Multimodality eye disease screening is crucial in ophthalmology as it integrates information from diverse sources to complement their respective performances. However, the existing methods are weak in assessing the reliability of each unimodality, and directly fusing an unreliable modality may cause screening errors. To address this issue, we introduce a novel multimodality evidential fusion pipeline for eye disease screening, EyeMoSt, which provides a measure of confidence for unimodality and elegantly integrates the multimodality information from a multi-distribution fusion perspective. Specifically, our model estimates both local uncertainty for unimodality and global uncertainty for the fusion modality to produce reliable classification results. More importantly, the proposed mixture of Student's $t$ distributions adaptively integrates different modalities to endow the model with heavy-tailed properties, increasing robustness and reliability. Our experimental findings on both public and in-house datasets show that our model is more reliable than current methods. Additionally, EyeMost has the potential ability to serve as a data quality discriminator, enabling reliable decision-making for multimodality eye disease screening.

Jiacheng Wang, Hao Li, Dewei Hu et al.

High-resolution Optical Coherence Tomography (OCT) images are crucial for ophthalmology studies but are limited by their relatively narrow field of view (FoV). Image mosaicking is a technique for aligning multiple overlapping images to obtain a larger FoV. Current mosaicking pipelines often struggle with substantial noise and considerable displacement between the input sub-fields. In this paper, we propose a versatile pipeline for stitching multi-view OCT/OCTA \textit{en face} projection images. Our method combines the strengths of learning-based feature matching and robust pixel-based registration to align multiple images effectively. Furthermore, we advance the application of a trained foundational model, Segment Anything Model (SAM), to validate mosaicking results in an unsupervised manner. The efficacy of our pipeline is validated using an in-house dataset and a large public dataset, where our method shows superior performance in terms of both accuracy and computational efficiency. We also made our evaluation tool for image mosaicking and the corresponding pipeline publicly available at \url{https://github.com/MedICL-VU/OCT-mosaicking}.

Keith Harrigian, Tina Tang, Anthony Gonzales et al.

Diabetic eye disease is a major cause of blindness worldwide. The ability to monitor relevant clinical trajectories and detect lapses in care is critical to managing the disease and preventing blindness. Alas, much of the information necessary to support these goals is found only in the free text of the electronic medical record. To fill this information gap, we introduce a system for extracting evidence from clinical text of 19 clinical concepts related to diabetic eye disease and inferring relevant attributes for each. In developing this ophthalmology phenotyping system, we are also afforded a unique opportunity to evaluate the effectiveness of clinical language models at adapting to new clinical domains. Across multiple training paradigms, we find that BERT language models pretrained on out-of-distribution clinical data offer no significant improvement over BERT language models pretrained on non-clinical data for our domain. Our study tempers recent claims that language models pretrained on clinical data are necessary for clinical NLP tasks and highlights the importance of not treating clinical language data as a single homogeneous domain.

Xueshen Li, Zhenxing Dong, Hongshan Liu et al.

Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment in fields such as cardiology and ophthalmology. Such applications can be further facilitated by deep learning-based super-resolution technology, which improves the capability of resolving morphological structures. However, existing deep learning-based method only focuses on spatial distribution and disregard frequency fidelity in image reconstruction, leading to a frequency bias. To overcome this limitation, we propose a frequency-aware super-resolution framework that integrates three critical frequency-based modules (i.e., frequency transformation, frequency skip connection, and frequency alignment) and frequency-based loss function into a conditional generative adversarial network (cGAN). We conducted a large-scale quantitative study from an existing coronary OCT dataset to demonstrate the superiority of our proposed framework over existing deep learning frameworks. In addition, we confirmed the generalizability of our framework by applying it to fish corneal images and rat retinal images, demonstrating its capability to super-resolve morphological details in eye imaging.