Domain-Shift AI Technology for Vendor-Agnostic Multiple Macular Disease Detection From 3D OCT Scans

Can a deep learning (DL) model be trained to detect multiple macular conditions robustly and analyze unseen 3-dimensional (3D) scans from a new optical coherence tomography (OCT) vendor without requiring labeled data?In this multicenter cohort study, a Residual Neural Network 3D model trained exclusively on Spectralis OCT 3D scans successfully analyzed 3D scans from Cirrus OCT, achieving mean accuracies ranging from 87.81% to 92.93%.This vendor-agnostic DL model for automated analysis of unsegmented 3D scans may enable broad clinical application across diverse eye care settings, streamlining detection and triage.

Corresponding Author: Carol Y. Cheung, PhD, Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, 4/F Hong Kong Eye Hospital, 147K Argyle St, Kowloon, Hong Kong Special Administrative Region, China (carolcheung@cuhk.edu.hk).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.