Multiple Sclerosis (MS) is a chronic autoimmune demyelinating disease of the central nervous system (CNS) characterized by inflammation, demyelination, and axonal damage. Early recognition and treatment are important for preventing or minimizing the long-term effects of the disease. Current gold standard modalities of diagnosis (e.g., CSF and MRI) are invasive and expensive in nature, warranting alternative methods of detection and screening. Oculomics, the interdisciplinary combination of ophthalmology, genetics, and bioinformatics to study the molecular basis of eye diseases, has seen rapid development through various technologies that detect structural, functional, and visual changes in the eye. Ophthalmic biomarkers (e.g., tear composition, retinal nerve fibre layer thickness, saccadic eye movements) are emerging as promising tools for evaluating MS progression. The eye's structural and embryological similarity to the brain makes it a potentially suitable assessment of neurological and microvascular changes in CNS. In the advent of more powerful machine learning algorithms, oculomics screening modalities such as optical coherence tomography (OCT), eye tracking, and protein analysis become more effective tools aiding in MS diagnosis. Artificial intelligence can analyse larger and more diverse data sets to potentially discover new parameters of pathology for efficiently diagnosing MS before symptom onset. While there is no known cure for MS, the integration of oculomics with current modalities of diagnosis creates a promising future for developing more sensitive, non-invasive, and cost-effective approaches to MS detection and diagnosis.
The ability to make on-field, split-second decisions is critical for National Football League (NFL) game officials. Multiple principles in visual function are critical for accuracy and precision of these play calls, including foveation time and unobstructed line of sight, static visual acuity, dynamic visual acuity, vestibulo-ocular reflex, and sufficient visual field. Prior research has shown that a standardized curriculum in these neuro-ophthalmic principles have demonstrated validity and self-rated improvements in understanding, confidence, and likelihood of future utilization by NFL game officials to maximize visual performance during officiating. Virtual reality technology may also be able to help optimize understandings of specific neuro-ophthalmic principles and simulate real-life gameplay. Personal communication between authors and NFL officials and leadership have indicated that there is high interest in 3D virtual on-field training for NFL officiating. In this manuscript, we review the current and past research in this space regarding a neuro-ophthalmic curriculum for NFL officials. We then provide an overview our current visualization engineering process in taking real-life NFL gameplay 2D data and creating 3D environments for virtual reality gameplay training for football officials to practice plays that highlight neuro-ophthalmic principles. We then review in-depth the physiology behind these principles and discuss strategies to implement these principles into virtual reality for football officiating.
Generative AI has revolutionized medicine over the past several years. A generative adversarial network (GAN) is a deep learning framework that has become a powerful technique in medicine, particularly in ophthalmology and image analysis. In this paper we review the current ophthalmic literature involving GANs, and highlight key contributions in the field. We briefly touch on ChatGPT, another application of generative AI, and its potential in ophthalmology. We also explore the potential uses for GANs in ocular imaging, with a specific emphasis on 3 primary domains: image enhancement, disease identification, and generating of synthetic data. PubMed, Ovid MEDLINE, Google Scholar were searched from inception to October 30, 2022 to identify applications of GAN in ophthalmology. A total of 40 papers were included in this review. We cover various applications of GANs in ophthalmic-related imaging including optical coherence tomography, orbital magnetic resonance imaging, fundus photography, and ultrasound; however, we also highlight several challenges, that resulted in the generation of inaccurate and atypical results during certain iterations. Finally, we examine future directions and considerations for generative AI in ophthalmology.
Open AI's Sora represents a ground-breaking innovation in AI that can generate lifelike and imaginative visual scenes based on text prompts. However, Sora has also produced some new concerns surrounding artificial video generation in medicine. While Sora is highly promising to enhance patient education, facilitate remote consultations and simulate surgical procedures, AI-generated videos also bring technical, legal, and ethical challenges. In this paper, we explore the clinical and ethical implications of Sora's AI-generated videos in the field of medicine.
Neuralink is a neurotechnology company founded by Elon Musk in 2016, which has been quietly developing revolutionary technology allowing for ultra-high precision bidirectional communication between external devices and the brain. In this paper, we explore the multifaceted ethical considerations surrounding neural interfaces, analyzing potential societal impacts, risks, and call for a need for responsible innovation. Despite the technological, medical, medicolegal, and ethical challenges ahead, neural interface technology remains extremely promising and has the potential to create a new era of medicine.
BACKGROUND: Applications for artificial intelligence (AI) in ophthalmology are continually evolving. Fundoscopy is one of the oldest ocular imaging techniques but remains a mainstay in posterior segment imaging due to its prevalence, ease of use, and ongoing technological advancement. AI has been leveraged for fundoscopy to accomplish core tasks including segmentation, classification, and prediction. MAIN BODY: In this article we provide a review of AI in fundoscopy applied to representative chorioretinal pathologies, including diabetic retinopathy and age-related macular degeneration, among others. We conclude with a discussion of future directions and current limitations. SHORT CONCLUSION: As AI evolves, it will become increasingly essential for the modern ophthalmologist to understand its applications and limitations to improve patient outcomes and continue to innovate.
BACKGROUND: To determine whether a neuro-ophthalmic curriculum would improve National Football League (NFL) game officials' self-rated knowledge and interest in neuro-ophthalmic principles to improve precision and accuracy of NFL play-calling. METHODS: The formalized and structured neuro-ophthalmic principles (NOP) curriculum was introduced to 121 NFL game officials, 17 replay officials, and 4 officiating staff who attended the NFL Official Training Camp in Irving, Texas, on September 8 and 9, 2023. Before and after the lecture and videos were introduced, participants completed an optional hard-copy feedback form pertaining to self-reported NOP knowledge, likelihood of using said terms, and interest in future content of NOP applicable NFL officiating. Paired 2-tailed t tests were used for statistical analysis to directly compare the self-reported knowledge before and after the neuro-ophthalmic curriculum introduction. RESULTS: One hundred forty-two participants completed the prelecture and postlecture feedback forms self-reported knowledge after the NOP curriculum was given to the NFL officiating staff. All (142/142) participants completed a survey. There was a statistically significant improvement in the mean ratings of the prelecture vs. postlecture understanding of the specific neuro-ophthalmic terms pertinent to NFL game officials (2.6 [95% CI, 2.3-3.0] vs. 7.9 [95% CI, 7.6-8.2], P < 0.001) and 2.7 [95% CI, 2.3-3.0] vs. 7.7 [95% CI, 7.4-8.0]), respectively. There was a statistically significant greater likelihood of using said terms prelecture vs. postlecture (2.9 [95% CI, 2.4-3.4] vs. 7.5 [95% CI, 7.2-7.9], P < 0.001). CONCLUSIONS: This study found a statistically significant improvement in neuro-ophthalmic knowledge and a greater likelihood of using NOP terms following the NOP curriculum. NFL game officials, replay officials, and staff are interested in expanding their knowledge in the vision science of neuro-ophthalmic concepts and applications involved in play-calling. We hope that our pilot data will lead to a model of education that will improve the precision and accuracy of NFL play-calls by officials on game days.
Purpose: To provide an automated system for synthesizing fluorescein angiography (FA) images from color fundus photographs for averting risks associated with fluorescein dye and extend its future application to spaceflight associated neuro-ocular syndrome (SANS) detection in spaceflight where resources are limited. Design: Development and validation of a novel conditional generative adversarial network (GAN) trained on limited amount of FA and color fundus images with diabetic retinopathy and control cases. Participants: Color fundus and FA paired images for unique patients were collected from a publicly available study. Methods: FA4SANS-GAN was trained to generate FA images from color fundus photographs using 2 multiscale generators coupled with 2 patch-GAN discriminators. Eight hundred fifty color fundus and FA images were utilized for training by augmenting images from 17 unique patients. The model was evaluated on 56 fluorescein images collected from 14 unique patients. In addition, it was compared with 3 other GAN architectures trained on the same data set. Furthermore, we test the robustness of the models against acquisition noise and retaining structural information when introduced to artificially created biological markers. Main Outcome Measures: For GAN synthesis, metric Fréchet Inception Distance (FID) and Kernel Inception Distance (KID). Also, two 1-sided tests (TOST) based on Welch's t test for measuring statistical significance. Results: On test FA images, mean FID for FA4SANS-GAN was 39.8 (standard deviation, 9.9), which is better than GANgio model's mean of 43.2 (standard deviation, 13.7), Pix2PixHD's mean of 57.3 (standard deviation, 11.5) and Pix2Pix's mean of 67.5 (standard deviation, 11.7). Similarly for KID, FA4SANS-GAN achieved mean of 0.00278 (standard deviation, 0.00167) which is better than other 3 model's mean KID of 0.00303 (standard deviation, 0.00216), 0.00609 (standard deviation, 0.00238), 0.00784 (standard deviation, 0.00218). For TOST measurement, FA4SANS-GAN was proven to be statistically significant versus GANgio (P = 0.006); versus Pix2PixHD (P < 0.00001); and versus Pix2Pix (P < 0.00001). Conclusions: Our study has shown FA4SANS-GAN to be statistically significant for 2 GAN synthesis metrics. Moreover, it is robust against acquisition noise, and can retain clear biological markers compared with the other 3 GAN architectures. This deployment of this model can be crucial in the International Space Station for detecting SANS. Financial Disclosures: The authors have no proprietary or commercial interest in any materials discussed in this article.
