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

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.