Search

Purpose: Both retinal changes and age-related macular degeneration (AMD) have been shown to be associated with Alzheimer's disease and related dementias (ADRD). In AMD, the outer retina is impacted significantly and early, but little is known about its association with cognition or changes in brain morphometry. This study investigates the relationship between retinal and brain morphometry in older adults with early and intermediate age-related macular degeneration (AMD)., Design: Cross-sectional study., Methods: Adults ≥ 70 years with normal, early, and intermediate AMD were recruited from Callahan Eye Hospital Clinics at the University of Alabama at Birmingham. Participants underwent cognitive testing, optical coherence tomography (OCT), and magnetic resonance imaging (MRI). Associations of retinal layer thickness with brain volume and thickness of specific brain regions were evaluated utilizing multivariable linear regression. The relevance of retinal thickness variables in brain volumetrics was quantified using least absolute shrinkage and selection operator (LASSO) regression models. Correlations between demographic variables, cognitive scores, and brain morphometry were evaluated., Results: Participants with thinner outer retina had significantly smaller hippocampus (β = 0.019, p = 0.022), lower occipital cortex regions of interest (occipital ROIs) thickness (β = 5.68, p = 0.020), and lower cortical thickness in ADRD-related brain regions (β = 7.72, p = 0.006). People with thinner total retina had significantly lower occipital ROIs (β = 3.19, p = 0.009) and ADRD-related brain region (β = 3.94, p = 0.005) thickness. Outer retinal thickness in the outer Early Treatment of Diabetic Retinopathy Study (ETDRS) ring was the most frequently reported retinal variable associated with brain morphometry on LASSO regression. Total gray matter volume showed positive correlations with education (Pearson's r = 0.30, p = 0.022)., Conclusion: In older adults with normal retinal aging and early and intermediate AMD, thinner outer retina had specific associations with brain regions primarily involved in vision and cognition, such as lower hippocampal volume and lower thickness of the occipital ROIs and brain regions known to show early structural changes in dementia., Competing Interests: Declaration of competing interest C.O.: Johnson & Johnson Vision; L.G.: BioEQ, Formycon; CAC: consults for Genentech/ Hoffman LaRoche, Apellis, Astellas, Boehringer Ingelheim, Character Biosciences, Osanni, Annexon, Mobius, and Ripple (outside this project)., (Copyright © 2024. Published by Elsevier Inc.)

Purpose: To apply methods for quantifying uncertainty of deep learning segmentation of geographic atrophy (GA)., Design: Retrospective analysis of OCT images and model comparison., Participants: One hundred twenty-six eyes from 87 participants with GA in the SWAGGER cohort of the Nonexudative Age-Related Macular Degeneration Imaged with Swept-Source OCT (SS-OCT) study., Methods: The manual segmentations of GA lesions were conducted on structural subretinal pigment epithelium en face images from the SS-OCT images. Models were developed for 2 approximate Bayesian deep learning techniques, Monte Carlo dropout and ensemble, to assess the uncertainty of GA semantic segmentation and compared to a traditional deep learning model., Main Outcome Measures: Model performance (Dice score) was compared. Uncertainty was calculated using the formula for Shannon Entropy., Results: The output of both Bayesian technique models showed a greater number of pixels with high entropy than the standard model. Dice scores for the Monte Carlo dropout method (0.90, 95% confidence interval 0.87-0.93) and the ensemble method (0.88, 95% confidence interval 0.85-0.91) were significantly higher ( P  < 0.001) than for the traditional model (0.82, 95% confidence interval 0.78-0.86)., Conclusions: Quantifying the uncertainty in a prediction of GA may improve trustworthiness of the models and aid clinicians in decision-making. The Bayesian deep learning techniques generated pixel-wise estimates of model uncertainty for segmentation, while also improving model performance compared with traditionally trained deep learning models., Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article., (© 2024 by the American Academy of Ophthalmology.)

Data is the cornerstone of using AI models, because their performance directly depends on the diversity, quantity, and quality of the data used for training. Using AI presents unique potential, particularly in medical applications that involve rich data such as ophthalmology, encompassing a variety of imaging methods, medical records, and eye-tracking data. However, sharing medical data comes with challenges because of regulatory issues and privacy concerns. This review explores traditional and nontraditional data sharing methods in medicine, focusing on previous works in ophthalmology. Traditional methods involve direct data transfer, whereas newer approaches prioritize security and privacy by sharing derived datasets, creating secure research environments, or using model-to-data strategies. We examine each method's mechanisms, variations, recent applications in ophthalmology, and their respective advantages and disadvantages. By empowering medical researchers with insights into data sharing methods and considerations, this review aims to assist informed decision-making while upholding ethical standards and patient privacy in medical AI development.