Search Results (255)

For retinal degenerative diseases, advanced therapies such as gene therapy and retinal stem cell therapy have emerged as promising treatments, which are often delivered through subretinal injection. However, clinical subretinal injection remains challenging due to the extremely high precision requirements, lack of depth information, and the physiological limitations of manual operation, often leading to complications such as hypotony and globe atrophy. To address these challenges, this study proposes a novel ophthalmic surgical robotic system designed for high-precision subretinal injections. The robotic system incorporate a remote center of motion mechanism for its mechanical structure and employs a master–slave control system to achieve motion scaling. A microscope-integrated optical coherence tomography device is applied to provide real-time microscopic imaging and depth information. The design and performance of the proposed system are validated through simulations and experiments. Precision tests demonstrate that the system achieves an overall positioning accuracy of less than 30 $\mathsf{\mu }$m, with injection positioning accuracy under 20 $\mathsf{\mu }$m. Subretinal injection experiments conducted on artificial eye models further validate the clinical feasibility of the robotic system. Full article

The effective focal length is a critical determinant of optical performance and imaging quality, serving as a fundamental parameter for components ranging from ophthalmic lenses to precision microlens arrays. With the rapid advancement of complex optical systems in microscopy and smart manufacturing, there is an increasing demand for high-precision measurement techniques that can characterize these parameters with low uncertainty. In this paper, a quadri-wave lateral shearing interferometry (QWLSI) measurement system was developed. A novel precision focal length measurement method of optical lenses based on the principle of QWLSI is presented. A theoretical model for solving the focal length of the measured lens from the curvature radius of the wavefront was derived. We also proposed a novel algorithm and subsequently developed a dedicated hardware platform and a corresponding software package for its real-time implementation. Different sets of repeated measurement experiments were carried out for two convex lenses with symmetrical and asymmetrical structures, a large-scale concave lens, and a microlens array, to verify the measurement uncertainty and robustness of the QWLSI measurement system. The expanded uncertainty was also analyzed and determined as 0.31 mm (k = 1.96, normal distribution). The results show that the proposed QWLSI measuring system possesses good performance in measuring the focal lengths of different kinds of lenses and can be widely used in fields such as advanced optics manufacturing. Full article

Background/Objectives: Retinal optical coherence tomography (OCT) is essential for diagnosing ocular diseases, yet developing high-performing multiclass classifiers remains challenging due to limited labeled data and the computational cost of self-supervised pretraining. This study aims to address these limitations by introducing a curriculum-based self-supervised framework to improve representation learning and reduce computational burden for OCT classification. Methods: Two ensemble strategies were developed using progressive masked autoencoder (MAE) pretraining. We refer to this curriculum-based MAE framework as CurriMAE (curriculum-based masked autoencoder). CurriMAE-Soup merges multiple curriculum-aware pretrained checkpoints using weight averaging, producing a single model for fine-tuning and inference. CurriMAE-Greedy selects top-performing fine-tuned models from different pretraining stages and ensembles their predictions. Both approaches rely on one curriculum-guided MAE pretraining run, avoiding repeated training with fixed masking ratios. Experiments were conducted on two publicly available retinal OCT datasets, the Kermany dataset for self-supervised pretraining and the OCTDL dataset for downstream evaluation. The OCTDL dataset comprises seven clinically relevant retinal classes, including normal retina, age-related macular degeneration (AMD), diabetic macular edema (DME), epiretinal membrane (ERM), retinal vein occlusion (RVO), retinal artery occlusion (RAO), and vitreomacular interface disease (VID) and the proposed methods were compared against standard MAE variants and supervised baselines including ResNet-34 and ViT-S. Results: Both CurriMAE methods outperformed standard MAE models and supervised baselines. CurriMAE-Greedy achieved the highest performance with an area under the receiver operating characteristic curve (AUC) of 0.995 and accuracy of 93.32%, while CurriMAE-Soup provided competitive accuracy with substantially lower inference complexity. Compared with MAE models trained at fixed masking ratios, the proposed methods improved accuracy while requiring fewer pretraining runs and reduced model storage for inference. Conclusions: The proposed curriculum-based self-supervised ensemble framework offers an effective and resource-efficient solution for multiclass retinal OCT classification. By integrating progressive masking with snapshot-based model fusion, CurriMAE methods provide high performance with reduced computational cost, supporting their potential for real-world ophthalmic imaging applications where labeled data and computational resources are limited. Full article

Background: Primary intraosseous carcinoma (PIOC) is a rare and aggressive odontogenic malignancy that originates within the jaw bones without initial mucosal involvement. Its atypical and nonspecific symptoms frequently lead to diagnostic delays, especially in maxillary presentations. Methods: A 74-year-old male presented with persistent trigeminal-like neuralgic pain along the ophthalmic branch, initially misdiagnosed as secondary trigeminal neuralgia. MRI revealed a 45 × 46 × 34 mm mass occupying the right maxillary sinus with orbital wall destruction and dural invasion. Following histopathological confirmation of malignancy, a multidisciplinary team performed total maxillectomy with orbital exenteration and dural resection, followed by reconstruction using a temporoparietal flap. Adjuvant radiotherapy was administered. Results: Histopathology revealed invasive odontogenic carcinoma with atypical squamous features, dentinoid deposition, and perineural invasion. Postoperative recovery was uneventful, with complete pain resolution. MRI and PET surveillance over 2.5 years demonstrated no local recurrence. Conclusions: Maxillary PIOC may present exclusively with neuropathic pain, mimicking trigeminal neuralgia and leading to delayed diagnosis. In cases of unexplained facial pain with sinus or skull base involvement, odontogenic malignancies should be considered in the differential diagnosis. Early imaging and multidisciplinary management are key to achieving timely diagnosis, effective treatment, and improved quality of life. Full article

Background/Objectives: Recent advances in large language models (LLMs) have enabled the multimodal interpretation of medical images, but their agreement in ophthalmology issues remains underexplored. This study evaluated the ability of ChatGPT-4o, a multimodal LLM, to classify idiopathic epiretinal membrane (ERM) using optical coherence tomography (OCT) based on the Govetto classification. Methods: This retrospective study included 250 eyes of 250 patients with idiopathic ERM who visited Uonuma Kikan Hospital between June 2015 and April 2025. Horizontal B-scan OCT images were independently classified into four stages by two masked ophthalmologists; cases with disagreement were excluded. ChatGPT-4o was prompted to identify ocular diseases and classify ERM stage. Agreement between ChatGPT-4o and ophthalmologists was evaluated using weighted Cohen’s κ, and logistic regression identified factors associated with disagreement. Results: Among 272 eligible eyes, 250 were analyzed (Stage 1: 87; Stage 2: 76; Stage 3: 63; Stage 4: 24). ChatGPT-4o identified the presence of ERM in 26.4% of cases on the first prompt. The perfect agreement rate for Govetto staging was 46.0%, with a weighted κ of 0.513 (95% CI: 0.420–0.605; p < 0.001), indicating moderate agreement. Disagreement was significantly associated with the presence of ectopic inner foveal layer (EIFL) (OR = 0.528, 95% CI: 0.312–0.893; p = 0.017). Conclusions: ChatGPT-4o showed moderate agreement with ophthalmologists in Govetto classification of idiopathic ERM using OCT images. Although its agreement was limited, the model demonstrated partial ability to recognize retinal structures, providing insight into the current capabilities and limitations of multimodal large language models in ophthalmic image interpretation. Full article

The early differentiation of benign choroidal naevi from malignant melanoma remains one of the most nuanced challenges in ophthalmic oncology, with profound implications for patient survival. Conventional diagnostic pathways rely on multimodal imaging and expert interpretation, but inter-observer variability and the rarity of melanoma limit timely and consistent detection. Recent advances in artificial intelligence (AI) offer a promising adjunct to conventional ophthalmic practice. This review provides a critical comparative synthesis of the studies to-date which have looked at AI’s use in the detection, risk stratification, and longitudinal monitoring of choroidal melanoma. While early results are promising—with some models achieving an accuracy comparable to expert clinicians—significant challenges remain regarding generalisability, dataset bias, interpretability, and real-world deployment. We conclude by outlining practical priorities for future research to ensure that AI becomes a safe, effective, and equitable tool for improving patient outcomes. Full article

Diabetic retinopathy (DR) and diabetic macular edema (DME) remain major causes of vision loss among working-age adults. Artificial intelligence (AI), particularly deep learning, has gained attention in ophthalmic imaging, offering opportunities to improve both diagnostic accuracy and efficiency. This review examined applications of AI in DR and DME published between 2010 and 2025. A narrative search of PubMed and Google Scholar identified English-language, peer-reviewed studies, with additional screening of reference lists. Eligible articles evaluated AI algorithms for detection, classification, prognosis, or treatment monitoring, with study selection guided by PRISMA 2020. Of 300 records screened, 60 met the inclusion criteria. Most reported strong diagnostic performance, with sensitivities up to 96% and specificities up to 98% for detecting referable DR on fundus photographs. Algorithms trained on optical coherence tomography (OCT) data showed high accuracy for identifying DME, with area under the receiver operating characteristic curve (AUC) values frequently exceeding 0.90. Several models also predicted anti-vascular endothelial growth factor (anti-VEGF) treatment response and recurrence of fluid with encouraging results. Autonomous AI tools have gained regulatory approval and have been implemented in clinical practice, though performance can vary depending on image quality, device differences, and patient populations. Overall, AI demonstrates strong potential to improve screening, diagnostic consistency, and personalized care, but broader validation and system-level integration remain necessary. Full article

Objectives: To assess retinal microvascular changes in patients with Grade II and III obesity before and after bariatric surgery using Optical Coherence Tomography Angiography (OCTA), and to compare these metrics with age- and sex-matched healthy controls. Methods: Prospective, consecutive, longitudinal cohort study with a 12-month follow-up. Grade II and III obese patients scheduled for bariatric surgery underwent comprehensive ophthalmic examinations, including OCTA imaging, prior to the surgery and postoperatively at 1 month, 6 months, and 12 months post-surgery. Results: A total of 43 eyes from 43 patients with obesity (one eye per patient) were included at baseline. At 12 months post-surgery, there was a significant increase in vessel density (VD) (16.70 vs. 17.68; p < 0.01) and perfusion density (PD) (0.406 vs. 0.433; p < 0.01), reaching values comparable to those of the control group (17.73 and 0.434, respectively). Significant reductions were also observed in body mass index (BMI) (43.74 vs. 29.53; p < 0.01), body weight (122.44 kg vs. 81.90 kg; p < 0.01), and intraocular pressure (IOP) (15.72 mmHg vs. 14.16 mmHg; p < 0.01). Conclusions: This study demonstrates a compelling association between obesity and retinal microvascular impairment, highlighting the efficacy of bariatric surgery not only in achieving substantial weight loss but also in improving the retinal perfusion of these patients, achieving metrics at 12 months comparable to age- and sex-matched healthy controls at baseline. These findings raise the hypothesis of the potential utility of OCTA as a monitoring tool for tracking the microvascular status in patients with obesity undergoing bariatric surgery in a longitudinal manner. Full article

Introduction: Inherited retinal dystrophies (IRDs) are genetically determined conditions leading to progressive vision loss. Developments in gene therapy are creating new treatment options for IRD, but require precise imaging diagnosis and monitoring. According to recent studies, artificial intelligence, especially deep neural networks, could become an important tool for analyzing imaging data. Material and Methods: A systematic literature review was conducted in accordance with PRISMA guidelines, using PubMed, Scopus, and Web of Science databases to identify publications from 2015 to 2025 on the application of artificial intelligence in diagnosing inherited retinal dystrophies and monitoring the effects of gene therapy. The included articles passed a two-stage selection process and met the methodological quality criteria. Results: Among all the included studies it can be noticed that the use of artificial intelligence in diagnostics and therapy of IRDs is rather effective. The most common method was deep learning with its subtype convolutional neural networks (CNNs). However, there is still a place for improvement due to various limitations occurring in the studies. Conclusions: The review points to the growing potential of AI models in optimizing the diagnostic and therapeutic pathway in IRDs, while noting current limitations such as low data availability, the need for clinical validation, and the interpretability of the models. AI may play a key role in personalized ophthalmic medicine in the near future, supporting both clinical decisions and interventional study design. Full article

Background/Purpose: Ophthalmic triage is challenging for non-specialists due to limited training and rising global eye disease burden. This study evaluates a multimodal framework integrating clinical text and ophthalmic imaging with large language models (LLMs). Textual consistency filtering and chain-of-thought (CoT) reasoning were incorporated to improve diagnostic accuracy. Methods: A dataset of 56 ophthalmology cases from a Singapore restructured hospital was pre-processed with acronym expansion, sentence reconstruction, and textual consistency filtering. To address dataset size limitations, 100 synthetic cases were generated via one-shot GPT-4 prompting, validated by semantic checks and ophthalmologist review. Three diagnostic approaches were tested: Text-Only, Image-Assisted, and Image with CoT. Diagnostic performance was quantified using a novel SNOMED-CT-based dissimilarity score, defined as the shortest path distance between predicted and reference diagnoses in the ontology, which was used to quantify semantic alignment. Results: The synthetic dataset included anterior segment (n = 40), posterior segment (n = 35), and extraocular (n = 25) cases. The text-only approach yielded a mean dissimilarity of 6.353 (95% CI: 4.668, 8.038). Incorporation of image assistance reduced this to 5.234 (95% CI: 3.930, 6.540), while CoT prompting provided further gains when imaging cues were ambiguous. Conclusions: The multimodal pipeline showed potential in improving diagnostic alignment in ophthalmology triage. Image inputs enhanced accuracy, and CoT reasoning reduced errors from ambiguous features, supporting its feasibility as a pilot framework for ophthalmology triage. Full article

Background: The use of preservative agents in eye drop solutions may worsen symptoms of ocular surface disease, which is a highly prevalent syndrome worldwide. Preservatives are often used in pharmacotherapy of glaucoma, another disease concerning tens of millions of people around the globe. These numbers are predicted by the World Health Organization and are predicted to increase with time due to constant aging of populations. Methods: PubMed and Scopus databases were searched for articles investigating the topic of ocular surface disease in relation with glaucoma pharmacotherapy, according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The aim of this review is to summarize the effect of various solvents used in drug formulations and ways to quantify their impact on the ocular surface. Discussion and Conclusions: Topical ophthalmic preservative-free formulations are better tolerated and less burdensome for all patients. They should be considered especially for glaucoma patients, who are expected to take medications for years, up to decades or a lifetime in many cases. Due to the chronicity of dry eye disease and the lack of reliable ways for lacrimal and meibomian gland renewal, primary prophylaxis is of uttermost importance. Unfortunately, despite the development of many measuring devices, the standardization of diagnostic methods poses a challenge due to high variability of results which are influenced by a myriad of factors—local, internal, and external. Full article

Optical coherence tomography (OCT) is a non-invasive imaging tool that is currently used in the evaluation and management of neuro-ophthalmic disorders. The detailed ability to visualize the optic nerve head, peripapillary retinal nerve fiber layer, and the macula, including the ganglion cell layer, allows for both qualitative and quantitative analysis of optic nerve diseases. This review covers the technical aspects of OCT and related imaging techniques in neuro-ophthalmology and discusses its use in common optic nerve head diseases such as optic disc drusen, optic disc coloboma, and elevated intracranial pressure. It also explores emerging OCT angiography applications in these disorders. Full article

Background: Retinal dystrophies are often challenging to diagnose. At early stages, they may resemble benign retinal pigment epithelium alterations and drusen present in otherwise healthy individuals. With the increased incidence of autoimmunity-related disorders and new treatments for retinal dystrophies on the horizon, thorough investigations and making the correct diagnosis in time are particularly important for these patients. Case report: A 44-year-old myopic female was admitted to the Ophthalmology Department with a 3-week history of painless blurred vision in her right eye. Fundoscopic examination revealed the presence of optic disc edema in this eye with pigmentary and atrophic changes in the macular regions of both eyes. She had no prior ophthalmic history nor systemic comorbidities known at the time. Marked hyperglycemia and renal angiomyolipoma were discovered subsequently. Ultimately, a diagnosis of Maternally Inherited Diabetes and Deafness was made. Discussion and Conclusion: Maternally Inherited Diabetes and Deafness is a rare mitochondrial disorder that should be considered in the differential diagnosis of retinal dystrophies, particularly due to multi-organ syndromes they can occur with, requiring collaborative medical care of several specialists. Integrating the findings and comparing them with other online sources facilitates clinical differential and treatment selection, eventually promoting faster accurate diagnosis of patients. It is especially important because of a long waiting time for results of genetic testing, while ophthalmic pathology can be the first sign of the disease. Full article

Epiretinal membrane (ERM) is a common retinal pathology associated with progressive visual impairment, requiring timely and accurate assessment. Recent advances in artificial intelligence (AI) have enabled automated approaches for ERM detection, segmentation, and postoperative best corrected visual acuity (BCVA) prediction, offering promising avenues to enhance clinical efficiency and diagnostic precision. We conducted a comprehensive literature search across MEDLINE (via PubMed), Scopus, CENTRAL, ClinicalTrials.gov, and Google Scholar from the inception to 31 December 2023. A total of 42 studies were included in the systematic review, with 16 eligible for meta-analysis. Risk of bias and reporting quality were assessed using the QUADAS-2 and CLAIM tools. Meta-analysis of 16 studies (533,674 images) showed that deep learning (DL) models achieved high diagnostic accuracy (AUC = 0.97), with pooled sensitivity and specificity of 0.93 and 0.97, respectively. Optical coherence tomography (OCT)-based models outperformed fundus-based ones, and although performance remained high under external validation, the positive predictive value (PPV) declined—highlighting the importance of testing model generalizability. To the best of our knowledge, this is the first systematic review and meta-analysis to critically evaluate the role of AI in the detection, segmentation, and postoperative BCVA prediction of ERM across various ophthalmic imaging modalities. Our findings provide a clear overview of current evidence supporting the continued development and clinical adoption of AI tools for ERM diagnosis and management. Full article

Diabetic retinopathy (DR), an eye disease that is a threatening cause of irreversible blindness, always challenging to detect and diagnose on time. There are many ophthalmic invasive procedures which exist in medical science for the diagnosis of oculi (eyes). These all require highly skilled medical practitioners with operational knowledge of diagnosing sensitive organs like the retina and its tiny vessels. Due to the dearth of retinal specialists, the eye’s organs’ sensitivity, and the complexity of retinal therapy, invasive procedures are time-consuming, costly, and have slow progress. The fundus images are the visual information of the rear part of the retina. The progression of lesions around the retinal tissue’s surface causes the electric signals to not able to reach at the visual cortex, thus causing blurry vision or vision loss experienced by patients. The older methods using retinal fundus images for diagnosing lesions and symptoms of DR take time, causing delays in treatment and hence reducing the chance of success. Therefore, for early diagnosis, using fundus or retinal images can save the required effort and time of both doctors and patients. Artificial intelligence (AI) techniques have the capability to learn the tissue structures of the eye’s anatomy and to provide an analysis of the disease through the retinal fundus images. This process consists of operations, first apply the image preprocessing techniques followed by segmentation and filtering, then classify the disease using the artificial intelligence-based model. The proposed model trained over a dataset of DR images, for the prediction of accurate results, followed by deciding if the diagnosis by the model is correctly classified or not using the Explainable AI (XAI) algorithm. The rapid growth and better outcome of machine learning and deep learning algorithms are reasons to adopt, enhance the early diagnosis and treatments of patients. Full article