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.

[Alexey Alexeevich Maklakov (19.09.1872-21.03.1918)]. / Aleksei Alekseevich Maklakov (19.09.1872­21.03.1918).

This article commemorates the 150th anniversary of the birth of prominent early 20th-century Russian ophthalmologist Professor Alexey Alekseevich Maklakov of Moscow University and aims to explore his biography, which remains relatively obscure. His scientific, pedagogical, and public activities have not been subjected to comprehensive analysis until now. The study clarifies key dates in his life through examination of archival documents. The biography is further supplemented with new facts concerning his work at the medical faculty of Moscow University.

Towards Standardizing Ophthalmic Data for Seamless Interoperability in Eye Care.

INTRODUCTION: Seamless interoperability of ophthalmic clinical data is beneficial for improving patient care and advancing research through the integration of data from various sources. Such consolidation increases the amount of data available, leading to more robust statistical analyses, and improving the accuracy and reliability of artificial intelligence models. However, the lack of consistent, harmonized data formats and meanings (syntactic and semantic interoperability) poses a significant challenge in sharing ophthalmic data. METHODS: The Health Level 7 (HL7) Fast Healthcare Interoperability Resources (FHIR), a standard for the exchange of healthcare data, emerges as a promising solution. To facilitate cross-site data exchange in research, the German Medical Informatics Initiative (MII) has developed a core data set (CDS) based on FHIR. RESULTS: This work investigates the suitability of the MII CDS specifications for exchanging ophthalmic clinical data necessary to train and validate a specific machine learning model designed for predicting visual acuity. In interdisciplinary collaborations, we identified and categorized the required ophthalmic clinical data and explored the possibility of its mapping to FHIR using the MII CDS specifications. DISCUSSION: We found that the current FHIR MII CDS specifications do not completely accommodate the ophthalmic clinical data we investigated, indicating that the creation of an extension module is essential.

Thiel cadaver eye as a training model for sub-Tenon's blocks: a feasibility study.

BACKGROUND: Regional anaesthesia education, especially for ocular procedures, necessitates reliable surgical training models. While cadaveric models offer anatomical fidelity, conventional embalming methods may compromise tissue integrity. We aimed to assess the effectiveness of Thiel cadavers for training in sub-Tenon's blocks by evaluating ocular tissues and measuring insertion forces. METHODS: Experimental design, using twenty eyes from ten Thiel cadaver heads. These cadavers were specifically prepared to test the administration of sub-Tenon's blocks. The research was conducted in a controlled laboratory setting appropriate for handling cadaveric materials and conducting precise measurements. Each cadaver eye underwent an initial ultrasound examination, and its axial length was noted. An intravitreal injection of heptastarch solution followed, to re-establish the eye's sphericity. After this volume injection, the axial length and intraocular pressure were measured again. Mock sub-Tenon's blocks were administered in 2 separate quadrants of the eye, with insertion forces measured using a pressure gauge. These were compared to a data set of insertion forces measured in a series of isolated pig's eyes on which STBs had been performed. Main outcome measurements were macroscopic assessment of the ocular tissue layers and the insertion forces required for the sub-Tenon's blocks. In a second set of 10 Thiel cadaver heads, 5 ml of sodium chloride were injected as sub-Tenon's blocks and the emergence of a periocular "T-sign" ascertained and measured by ultrasound. RESULTS: Four of twenty eyes (20%) retained near-natural sphericity, with the remaining requiring volume injection to approximate physiological shape and pressure. The conjunctiva and Tenon's layer were intact, and correct cannula placement was achieved in all cases. In 16 of 20 eyes where T-signs could be measured, the median thickness of the T-sign amounted to 2.72 mm (range 1.34 mm-5.28 mm). The average maximum cannula insertion force was 2.92 Newtons. Insertion forces in intact Thiel cadaver heads were consistently higher than in isolated pig's eyes (3.6 N vs 2.0 N). CONCLUSION: These findings suggest that Thiel cadavers are a promising model for training in sub-Tenon'sblocks, despite the challenge of often desiccated and involuted eyes.

Bibliometric analysis of ophthalmic OCT and OCT angiography research trends over the past 20 years.

PURPOSE: Optical coherence tomography (OCT) and OCT angiography (OCTA) are widely used in the diagnosis of ophthalmic diseases. This study aims to provide a comprehensive bibliometric analysis of ophthalmologic OCT and OCT angiography. METHODS: We retrieved publications on ophthalmic OCT and OCTA from 2003 to 2022 from the Web of Science Core Collection and used bibliometric tools to analyze and visualize the distribution, trend, and hotspots. RESULTS: In total, 20,817 articles written by 48,160 authors from 106 countries were selected. The number of publications has significantly increased. In the last two decades, the USA was the most productive country and received the highest citations. The most productive journal was Investigative Ophthalmology and Visual Science and received the highest number of citations. Moorfields Eye Hospital was the most productive institution. Bandello F published the most papers, while Spaide RF was the highest cited author. SPAIDE RF, 2011, AM J Ophthalmology was the most cited document. "OCT", "glaucoma" and "OCTA" were three hotspots in the last two decades. "Vessel density" and "deep learning" would be research hotspots in the future. CONCLUSION: The bibliometric analysis of ophthalmic OCT and OCTA research over the past two decades on keywords, authors, citations, hotspots and trends will provide global researchers with valuable information for future research and cooperation.

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".

Running the enrollment numbers on ophthalmic clinical trials in the United States.

SIGNIFICANCE: This is one of the first reports to summarize the enrollment metrics for ophthalmology trials completed in the United States (US). PURPOSE: This study aimed to describe US ophthalmology clinical trial enrollment metrics to facilitate planning and budgeting of US Food and Drug Administration-regulated ophthalmological drugs trials. METHODS: A GlobalData PLC search was conducted on or before February 27, 2024, to evaluate the clinical trial landscape for completed ophthalmology clinical trials conducted in the US. The primary search contained only the term "ophthalmology," which was restricted to trials that were completed and were conducted within the US. Trials were classified as multicenter when trials included three sites or more, and when the enrollment search resulted in ≥30 multicenter trials for an individual indication, enrollment data were further broken down by Food and Drug Administration trial phase. RESULT: The search yielded 2229 trials, which analyzed 980 different drugs produced by 854 different sponsors. The most common indications evaluated in US trials were macular degeneration, glaucoma, macular edema, allergies, and keratoconjunctivitis. Multicenter trials by indication had an overall median enrollment period range of 4.8 to 35.1 months; number of subjects enrollment, range of 36 to 518 subjects; number of sites utilized, range of 4 to 74 sites; and enrollment rate, range of 0.11 to 4.04 subjects/sites per month. There were 17 indications with ≥30 multicenter trials, which allowed for enrollment metric calculation by trial phase. CONCLUSIONS: This study provides sponsors with an understanding of the number of subjects and sites needed to complete a trial while also setting realistic enrollment timelines. Although this work represents the US market, more work is needed to better understand other countries given that country-specific guidelines and subject beliefs may impact enrollment metrics.

Advancements and emerging trends in ophthalmic anti-VEGF therapy: a bibliometric analysis.

INTRODUCTION: Vascular Endothelial Growth Factor (VEGF) is associated with abnormal fundus neovascularization. Consequently, Anti-VEGF agents are vital for ophthalmic treatment. This paper reviews the application of anti-VEGF agents in ophthalmology over the past two decades with the aim of providing insights for further research. METHODS: A meticulous search strategy was employed in the Web of Science Core Collection literature from 2003 to 2023 to gather relevant literature, which was then analyzed using VOSviewer, CiteSpace, and the R package Bibliometrix. RESULTS: The study included 3,602 publications from 83 countries and 3,445 institutions. The United States and China have emerged as leading contributors in terms of the publication volume. Johns Hopkins University, the University of Sydney, and Genentech Inc were identified as frontrunners in this field. "Retina" had the highest publication volume, whereas "Ophthalmology" had the highest citation frequency. Among the 15,918 scholars, Bressler NM, Holz FG, Glassman AR, and Bandello F led in publication volume, while Brown DM was the most cited author. High-frequency keywords included "Endothelial Growth Factor," "Therapy," "Safety," and "Randomized Clinical Trial." CONCLUSION: Anti-VEGF drugs have shown notable success in treating neovascular eye diseases, especially wet age-related macular degeneration and diabetic macular edema, focusing on clinical efficacy, injection regimens, and safety. Future directions include developing new anti-VEGF drugs, drug delivery systems, non-invasive administration, multi-target drugs, leveraging big data and artificial intelligence, and addressing the current treatment limits. Continuous innovation and method improvement in this field promise more breakthroughs, providing effective, safe, and economical options for eye disease treatment.