Study Demonstrates Efficacy of AI in Enabling Home OCT Monitoring
Notal Vision announced the publication of pivotal study results evaluating the performance of its artificial intelligence (AI) algorithm designed to estimate key biomarkers in wet age-related macular degeneration (AMD) using a home-based optical coherence tomography (OCT) system[1].
The study, published in Ophthalmology Science, has been instrumental in securing the first FDA clearance for an AI algorithm applied to OCT images, according to Notal Vision.
The cross-sectional study involved 336 wet AMD patients from six US retina clinics. Participants presented a diverse array of co-existing pathological features, creating complex scenarios for AI-driven segmentation of wet AMD-associated biomarkers. Each patient captured four images on two home OCT devices independently, without technician assistance, and underwent imaging on an in-office OCT device for comparison.
The AI algorithm focused on identifying hypo-reflective spaces (HRS) within the images, including both subretinal and intraretinal spaces. It quantified total retinal hypo-reflective space (TRO) volumes. Expert graders then assessed both home and in-office OCT images to evaluate the AI’s accuracy in detecting HRS.
The study evaluated two primary outcomes:
Repeatability of the AI algorithm in estimating TRO volumes from home OCT images
Agreement between AI-driven segmentation of HRS and expert grader assessments
Results demonstrated that the AI algorithm exhibited strong repeatability and high concordance with expert graders. Notably, the repeatability of TRO estimates from successive home OCT images analyzed by the AI algorithm surpassed that of in-office imaging devices assessed by human experts. Furthermore, the agreement between AI and human graders in segmenting HRS was comparable to the inter-grader agreement among experts.
“This is one of the most significant studies related to artificial intelligence and retinal disease management, as it led to the clearance of the first-ever AI for OCT,” Eric Schneider, MD, of Tennessee Retina, senior author of the study, stated in a Notal Vision news release. “It should give retina specialists a great deal of confidence in adopting this patient monitoring program.”
Kester Nahen, PhD, CEO of Notal Vision, added: “We are excited to see the publication of the pivotal study results that led to the first FDA clearance of an AI algorithm for processing OCT images. The positive results enable SCANLY Home OCT, the first marketing-authorized home imaging device in eye care, to provide physicians with actionable insights into disease activity and treatment response between patients’ office visits.”
The findings will be presented at the Bascom Palmer Eye Institute Angiogenesis meeting by Anat Loewenstein, MD, professor and director of the Department of Ophthalmology at Tel Aviv Medical Center in Israel.
Reference:
1. Schneider EW et al. Pivotal Trial Toward Effectiveness of Self-administered OCT in Neovascular Age-related Macular Degeneration. Report 2—Artificial Intelligence Analytics. Ophthalmology Science, Volume 5, Issue 2, April 2025. doi: 10.1016/j.xops.2024.100662.