A comparative evaluation of deep learning approaches for ophthalmology.

There is a growing number of publicly available ophthalmic imaging datasets and open-source code for Machine Learning algorithms. This allows ophthalmic researchers and practitioners to independently perform various deep-learning tasks. With the advancement in artificial intelligence (AI) and in the field of imaging, the choice of the most appropriate AI architecture for different tasks will vary greatly. The best-performing AI-dataset combination will depend on the specific problem that needs to be solved and the type of data available. The article discusses different machine learning models and deep learning architectures currently used for various ophthalmic imaging modalities and for different machine learning tasks. It also proposes the most appropriate models based on accuracy and other important factors such as training time, the ability to deploy the model on clinical devices/smartphones, heatmaps that enhance the self-explanatory nature of classification decisions, and the ability to train/adapt on small image datasets to determine if further data collection is worthwhile. The article extensively reviews the existing state-of-the-art AI methods focused on useful machine-learning applications for ophthalmology. It estimates their performance and viability through training and evaluating architectures with different public and private image datasets of different modalities, such as full-color retinal images, OCT images, and 3D OCT scans. The article is expected to benefit the readers by enriching their knowledge of artificial intelligence applied to ophthalmology.

Management of COVID-19 in Ophthalmology.

From its outbreak in early 2020, the new SARS-CoV-2 infection has deeply affected the entire eye care system for several reasons. Since the beginning of the COVID-19 pandemic, ophthalmologists were among the "high-risk category" for contracting the SARS-CoV-2 infection based on the notion that the eye was suspected to be a site of inoculation, infection, and transmission. Clinical ophthalmologists have been required to learn and promptly recognize the ocular manifestations associated with the COVID-19 disease, with its treatments and vaccinations. Restriction measures, lockdown periods, guidelines to prevent SARS-CoV-2 infection transmission, and the use of telemedicine and artificial intelligence modalities have induced profound modifications. These changes, which are most likely to be irreversible, influence routine clinical practice, education, and research, thus giving rise to a "new ophthalmology in the COVID era". This book chapter aims to provide several notions regarding COVID-19 in ophthalmology, including the SARS-CoV-2 virus infection and transmission modalities; the ocular manifestation associated with the COVID-19 disease; the drugs and vaccines used for COVID-19; the precautions adopted in the ophthalmic practice to limit the spread of the virus; the consequences of the pandemic on the ophthalmic patients, clinicians, and the entire eye care system; and, the future of ophthalmology in the era of "COVID new normal".

Artificial intelligence applications in ophthalmic surgery.

PURPOSE OF REVIEW: Technologies in healthcare incorporating artificial intelligence tools are experiencing rapid growth in static-image-based applications such as diagnostic imaging. Given the proliferation of artificial intelligence (AI)-technologies created for video-based imaging, ophthalmic microsurgery is likely to experience significant benefits from the application of emerging technologies to multiple facets of the care of the surgical patient. RECENT FINDINGS: Proof-of-concept research and early phase clinical trials are in progress for AI-based surgical technologies that aim to provide preoperative planning and decision support, intraoperative image enhancement, surgical guidance, surgical decision-making support, tactical assistive technologies, enhanced surgical training and assessment of trainee progress, and semi-autonomous tool control or autonomous elements of surgical procedures. SUMMARY: The proliferation of AI-based technologies in static imaging in clinical ophthalmology, continued refinement of AI tools designed for video-based applications, and development of AI-based digital tools in allied surgical fields suggest that ophthalmic surgery is poised for the integration of AI into our microsurgical paradigm.

Latest developments of generative artificial intelligence and applications in ophthalmology.

The emergence of generative artificial intelligence (AI) has revolutionized various fields. In ophthalmology, generative AI has the potential to enhance efficiency, accuracy, personalization and innovation in clinical practice and medical research, through processing data, streamlining medical documentation, facilitating patient-doctor communication, aiding in clinical decision-making, and simulating clinical trials. This review focuses on the development and integration of generative AI models into clinical workflows and scientific research of ophthalmology. It outlines the need for development of a standard framework for comprehensive assessments, robust evidence, and exploration of the potential of multimodal capabilities and intelligent agents. Additionally, the review addresses the risks in AI model development and application in clinical service and research of ophthalmology, including data privacy, data bias, adaptation friction, over interdependence, and job replacement, based on which we summarized a risk management framework to mitigate these concerns. This review highlights the transformative potential of generative AI in enhancing patient care, improving operational efficiency in the clinical service and research in ophthalmology. It also advocates for a balanced approach to its adoption.

[Challenges and prospects in the application of artificial intelligence for ocular disease screening and diagnosis].

In recent years, artificial intelligence (AI) technologies have experienced substantial growth across various sectors, with significant strides made particularly in medical AI through advancements such as large models. The application of AI within the field of ophthalmology can enhance the accuracy of eye disease screening and diagnosis. However, the deployment of AI and its large models in ophthalmology still encounters numerous limitations and challenges. This article builds upon the transformative achievements in the medical AI sector and discusses the ongoing challenges faced by AI applications in ophthalmology. It provides forward-looking insights from an ophthalmic perspective regarding the era of large models and anticipates research trends in AI applications in ophthalmology, so as to foster the continuous advancement of AI technologies, thereby significantly promoting eye health.

Tissue Engineering and Ophthalmology.

Tissue engineering (TE) is a field of science that combines biological, engineering, and medical sciences and allows the development of disease models, drug development and gene therapy studies, and even cellular or tissue-based treatments developed by engineering methods. The eye is an organ that is easily accessible and amenable to engineering applications, paving the way for TE in ophthalmology. TE studies are being conducted on a wide range of topics, including the tear film, eyelids, cornea, optic nerve, glaucoma, and retinal diseases. With the rapid scientific advances in the field, it seems that TE is radically modifying the management of ocular disorders.

Nanosuspensions in ophthalmology: Overcoming challenges and enhancing drug delivery for eye diseases.

This review article provides a comprehensive overview of the advancements in using nanosuspensions for controlled drug delivery in ophthalmology. It highlights the significance of ophthalmic drug delivery due to the prevalence of eye diseases and delves into various aspects of this field. The article explores molecular mechanisms, drugs used, and physiological factors affecting drug absorption. It also addresses challenges in treating both anterior and posterior eye segments and investigates the role of mucus in obstructing micro- and nanosuspensions. Nanosuspensions are presented as a promising approach to enhance drug solubility and absorption, covering formulation, stability, properties, and functionalization. The review discusses the pros and cons of using nanosuspensions for ocular drug delivery and covers their structure, preparation, characterization, and applications. Several graphical representations illustrate their role in treating various eye conditions. Specific drug categories like anti-inflammatory drugs, antihistamines, glucocorticoids, and more are discussed in detail, with relevant studies. The article also addresses current challenges and future directions, emphasizing the need for improved nanosuspension stability and exploring potential technologies. Nanosuspensions have shown substantial potential in advancing ophthalmic drug delivery by enhancing solubility and absorption. This article is a valuable resource for researchers, clinicians, and pharmaceutical professionals in this field, offering insights into recent developments, challenges, and future prospects in nanosuspension use for ocular drug delivery.

Implementation of anterior segment ophthalmic telemedicine.

PURPOSE OF REVIEW: The growing push to integrate telemedicine into ophthalmic practices requires physicians to have a thorough understanding of ophthalmic telemedicine's applications, limitations, and recent advances in order to provide well tolerated and appropriate clinical care. This review aims to provide an overview of recent advancements in the use of ophthalmic telemedicine for anterior segment eye examinations. RECENT FINDINGS: Virtual care for anterior segment evaluation relies on appropriate technology, novel workflows, and appropriate clinical case selection. Recent advances, particularly in the wake of the COVID-19 pandemic, have highlighted the utility of home-based assessments for visual acuity, external evaluation, tonometry, and refraction. Additionally, innovative workflows incorporating office-based testing into virtual care, termed 'hybrid telemedicine', enable high-quality ophthalmic testing to inform clinical decision-making. SUMMARY: Novel digital tools and workflows enable high-quality anterior segment evaluation and management for select ophthalmic concerns. This review highlights the clinical tools and workflows necessary to enable anterior segment telehealth.

[Vitreomacular traction: diagnostics, natural course, treatment decision and guideline recommendations]. / Vitreomakuläre Traktion: Diagnostik, natürlicher Verlauf, Therapieentscheidung und Leitlinienempfehlungen.

Vitreomacular traction is a tractive foveolar adhesion of the posterior vitreous limiting membrane, resulting in pathological structural alterations of the vitreomacular interface. This must be differentiated from physiological vitreomacular adhesion, which exhibits a completely preserved foveolar depression. Symptoms depend on the severity of the macular changes and typically include reduced visual acuity, reading problems and metamorphopsia. High-resolution spectral domain optical coherence tomography (SDOCT) imaging enables classification of the sometimes only subtle morphological changes. If pronounced vitreomacular traction is accompanied by epiretinal gliosis and alterations to the outer retina, it is referred to as a vitreomacular traction syndrome. Vitreomacular traction has a high probability of spontaneous resolution within 12 months. Therefore, treatment should only be carried out in cases of undue suffering of the patient and with symptoms during bilateral vision and a lack of spontaneous resolution. In addition to pars plana vitrectomy, alternative treatment options, such as intravitreal injection of ocriplasmin and pneumatic vitreolysis are discussed for vitreomacular traction with an associated macular hole; however, ocriplasmin is no longer available in Germany. The best anatomical results in comparative investigations were achieved by vitrectomy. Pneumatic vitreolysis is controversially discussed due to the increased risk of retinal tears. In one of the current S1 guidelines of the German ophthalmological societies evidence-based recommendations for the diagnostics and treatment of vitreomacular traction are summarized.

[OPHTHALMOLOGY - ON THE TIP OF THE SPEAR].

INTRODUCTION: Ophthalmology is a broad branch of medicine, which includes an extensive range of sub-specialties on one hand, and interfaces with other fields of medicine on the other. This issue contains papers from different sub-specialties of ophthalmology, that together cover several of the most important issues in this field. These papers present the topics in a manner compatible with the wide readership of the journal, and touch upon the most current updates and innovations. The original articles in this issue deal with treatments for the prevention of myopia progression in children, treatment of complicated cases of retinal detachment in children, ocular manifestations of vascular abnormalities in patients with coronavirus, and a series of patients with corneal damage due to ultraviolet-C (UVC) lamps intended to clear the air of this virus. The review papers describe glaucoma and the current change in its treatment paradigm, which focuses on earlier intervention, ocular manifestations of systemic autoimmune diseases, and the possibilities for artificial corneal implantation. We hope that this special issue will be of interest and clinical value to its readers.

Converting LEA to Pelli-Robson contrast sensitivity score in neuro-ophthalmology patients.

PURPOSE: The Pelli-Robson and LEA contrast sensitivity charts are commonly used in clinical settings to measure contrast sensitivity. Although the Pelli-Robson chart is considered the gold standard, it is limited by its bulky size. The LEA chart, on the contrary, offers a more practical and portable option that is still reliable. This has led to questions about whether we can predict Pelli-Robson scores based on LEA scores. This study developed a conversion method to help transition from the LEA chart to the Pelli-Robson chart and validate the conversion score. METHODS: In this retrospective study, we analyzed the relationship between LEA and the Pelli-Robson contrast sensitivity test. Our study examined a total of 120 eyes. We developed a conversion table through the equipercentile equating method. Subsequently, we assessed the reliability and accuracy of this algorithm for converting LEA results into Pelli-Robson contrast sensitivity scores. RESULTS: The study used a conversion table to convert LEA scores to Pelli-Robson scores. The conversion table achieved a reliability of 0.91 based on intraclass correlation, and the algorithm had an accuracy of 81.6% within a 1-point difference from the raw score. CONCLUSIONS: This study reported a reliable and comparable conversion algorithm for transforming LEA scores into converted estimated Pelli-Robson scores, thereby improving the usefulness of existing data in both clinical and research contexts.

"Spaceflight-to-Eye Clinic": Terrestrial advances in ophthalmic healthcare delivery from space-based innovations.

The phrase "Bench-to-Bedside" is a well-known phrase in medicine, highlighting scientific discoveries that directly translate to impacting patient care. Key examples of translational research include identification of key molecular targets in diseases and development of diagnostic laboratory tests for earlier disease detection. Bridging these scientific advances to the bedside/clinic has played a meaningful impact in numerous patient lives. The spaceflight environment poses a unique opportunity to also make this impact; the nature of harsh extraterrestrial conditions and medically austere and remote environments push for cutting-edge technology innovation. Many of these novel technologies built for the spaceflight environment also have numerous benefits for human health on Earth. In this manuscript, we focus on "Spaceflight-to-Eye Clinic" and discuss technologies built for the spaceflight environment that eventually helped to optimize ophthalmic health on Earth (e.g., LADAR for satellite docking now utilized in eye-tracking technology for LASIK). We also discuss current technology research for spaceflight associated neuro-ocular syndrome (SANS) that may also be applied to terrestrial ophthalmic health. Ultimately, various advances made to enable to the future of space exploration have also advanced the ophthalmic health of individuals on Earth.

Patient information videos via QR codes: An innovative and sustainable approach in ophthalmology.

BACKGROUND: We explore an innovative approach by transforming patient information leaflet (PILs) into Quick Response (QR) code linked patient information videos (PIVs) in ophthalmology. Our objectives are to assess the subjective utility of a PIV on glaucoma and analyse the use of QR codes as a delivery method. METHODS: A prospective study was conducted in Ninewells Hospital, NHS Tayside. A glaucoma PIV was created and linked to a QR code provided to 130 glaucoma patients. Pre- and post-video questionnaires evaluated the patients' perception of using a QR code and subjective improvement in their understanding of glaucoma. RESULTS: Out of 102 responses collected, 55% of patients had no prior experience with QR codes. However, 81% of patients were able to watch the PIV. The average view duration of the video was 3:26, with 82.5% view retention. Statistically significant improvement in glaucoma knowledge was observed across all six areas questioned (p < 0.001) using a 5-point Likert scale. Overall, 70% of patients preferred PIVs over PILs, and 77% acknowledged that PIVs could be a sustainable alternative. CONCLUSION: QR codes for delivering PIVs were well-received, with patients finding them easy to use. Our PIV on glaucoma effectively enhanced patients' understanding of the condition.

The Current State of Artificial Intelligence in Neuro-Ophthalmology. A Review

This article presents a summary of recent advances in the development and use of complex systems using artificial intelligence (AI) in neuro-ophthalmology. The aim of the following article is to present the principles of AI and algorithms that are currently being used or are still in the stage of evaluation or validation within the neuro-ophthalmology environment. For the purpose of this text, a literature search was conducted using specific keywords in available scientific databases, cumulatively up to April 2023. The AI systems developed across neuro-ophthalmology mostly achieve high sensitivity, specificity and accuracy. Individual AI systems and algorithms are subsequently selected, simply described and compared in the article. The results of the individual studies differ significantly, depending on the chosen methodology, the set goals, the size of the test, evaluated set, and the evaluated parameters. It has been demonstrated that the evaluation of various diseases will be greatly speeded up with the help of AI and make the diagnosis more efficient in the future, thus showing a high potential to be a useful tool in clinical practice even with a significant increase in the number of patients.

Diagnostic decisions of specialist optometrists exposed to ambiguous deep-learning outputs.

Artificial intelligence (AI) has great potential in ophthalmology. We investigated how ambiguous outputs from an AI diagnostic support system (AI-DSS) affected diagnostic responses from optometrists when assessing cases of suspected retinal disease. Thirty optometrists (15 more experienced, 15 less) assessed 30 clinical cases. For ten, participants saw an optical coherence tomography (OCT) scan, basic clinical information and retinal photography ('no AI'). For another ten, they were also given AI-generated OCT-based probabilistic diagnoses ('AI diagnosis'); and for ten, both AI-diagnosis and AI-generated OCT segmentations ('AI diagnosis + segmentation') were provided. Cases were matched across the three types of presentation and were selected to include 40% ambiguous and 20% incorrect AI outputs. Optometrist diagnostic agreement with the predefined reference standard was lowest for 'AI diagnosis + segmentation' (204/300, 68%) compared to 'AI diagnosis' (224/300, 75% p = 0.010), and 'no Al' (242/300, 81%, p = < 0.001). Agreement with AI diagnosis consistent with the reference standard decreased (174/210 vs 199/210, p = 0.003), but participants trusted the AI more (p = 0.029) with segmentations. Practitioner experience did not affect diagnostic responses (p = 0.24). More experienced participants were more confident (p = 0.012) and trusted the AI less (p = 0.038). Our findings also highlight issues around reference standard definition.

Ophthalmology Optical Coherence Tomography Databases for Artificial Intelligence Algorithm: A Review.

BACKGROUND: Imaging plays a pivotal role in eye assessment. With the introduction of advanced machine learning and artificial intelligence (AI), the focus has shifted to imaging datasets in ophthalmology. While disparities and health inequalities hidden within data are well-documented, the ophthalmology field faces specific challenges to the creation and maintenance of datasets. Optical Coherence Tomography (OCT) is useful for the diagnosis and monitoring of retinal pathologies, making it valuable for AI applications. This review aims to identify and compare the landscape of publicly available optical coherence tomography databases for AI applications. METHODS: We conducted a literature review on OCT and AI articles with publicly accessible datasets, using PubMed, Scopus, and Web of Science databases. The review retrieved 183 articles, and after full-text analysis, 50 articles were included. From the included articles were identified 8 publicly available OCT datasets, focusing on patient demographics and clinical details for thorough assessment and comparison. RESULTS: The resulting datasets encompass 154,313 images collected from Spectralis, Cirrus HD, Topcon 3D, and Bioptigen devices. These datasets included normal exams, age-related macular degeneration, and diabetic maculopathy, among others. Comprehensive demographic information is available in one dataset and the USA is the most represented population. DISCUSSION: Current publicly available OCT databases for AI applications exhibit limitations, stemming from their non-representative nature and the lack of comprehensive demographic information. Limited datasets hamper research and equitable AI development. To promote equitable AI algorithmic development in ophthalmology, there is a need for the creation and dissemination of more representative datasets.