Skip to main content

This is a preprint.

It has not yet been peer reviewed by a journal.

The National Library of Medicine is running a pilot to include preprints that result from research funded by NIH in PMC and PubMed.

medRxiv logoLink to medRxiv
[Preprint]. 2024 Sep 12:2024.09.11.24312817. [Version 1] doi: 10.1101/2024.09.11.24312817

Deep Learning-Based Detection of Reticular Pseudodrusen in Age-Related Macular Degeneration on Optical Coherence Tomography

Himeesh Kumar, Yelena Bagdasarova, Scott Song, Doron G Hickey, Amy C Cohn, Mali Okada, Robert P Finger, Jan H Terheyden, Ruth E Hogg, Pierre-Henry Gabrielle, Louis Arnould, Maxime Jannaud, Xavier Hadoux, Peter van Wijngaarden, Carla J Abbott, Lauren AB Hodgson, Roy Schwartz, Adnan Tufail, Emily Y Chew, Cecilia S Lee, Erica L Fletcher, Melanie Bahlo, Brendan RE Ansell, Alice Pébay, Robyn H Guymer, Aaron Y Lee, Zhichao Wu
PMCID: PMC11419239  PMID: 39314940

ABSTRACT

Reticular pseudodrusen (RPD) signify a critical phenotype driving vision loss in age-related macular degeneration (AMD). Their detection is paramount in the clinical management of those with AMD, yet they remain challenging to reliably identify. We thus developed a deep learning (DL) model to segment RPD from 9,800 optical coherence tomography B-scans, and this model produced RPD segmentations that had higher agreement with four retinal specialists (Dice similarity coefficient [DSC]=0·76 [95% confidence interval [CI] 0·71–0·81]) than the agreement amongst the specialists (DSC=0·68, 95% CI=0·63–0·73; p <0·001). In five external test datasets consisting of 1,017 eyes from 812 individuals, the DL model detected RPD with a similar level of performance as two retinal specialists (area-under-the-curve of 0·94 [95% CI=0·92–0·97], 0·95 [95% CI=0·92–0·97] and 0·96 [95% CI=0·94–0·98] respectively; p ≥0·32). This DL model enables the automatic detection and quantification of RPD with expert-level performance, which we have made publicly available.

Full Text Availability

The license terms selected by the author(s) for this preprint version do not permit archiving in PMC. The full text is available from the preprint server.


Articles from medRxiv are provided here courtesy of Cold Spring Harbor Laboratory Preprints

RESOURCES