Repeatability of Microperimetry in Areas of Retinal Pigment Epithelium and Photoreceptor Loss in Geographic Atrophy Supported by Artificial Intelligence–Based Optical Coherence Tomography Biomarker Quantification

Published

2025

Audience

Therapeutic Area

Content Type

AI Generated Summary*

Twenty eyes of 20 patients with geographic atrophy (mean age 77) took two consecutive microperimetry sessions on each of two devices, a mesopic MAIA and a photopic MP3, using a 45-point grid. Each test point was registered to same-day OCT, where deep learning tools mapped RPE loss, photoreceptor integrity loss, drusen, hyperreflective foci and photoreceptor thickness. Overall test-retest coefficients of repeatability were nearly equal (±6.57 dB MAIA, ±6.59 dB MP3). Photoreceptor loss was linked to greater variability on both devices, while RPE loss (±10.99 vs ±5.34 dB without it) and hyperreflective foci were linked to it on MP3 only. Within-device correlation was 0.94, mean between-device 0.83, and fixation stability was unaffected by device, run order or foveal sparing.

*This summary was generated by AI and is published unedited. Oku does not alter these summaries. It may contain errors or omissions and is provided for general informational purposes only. Oku does not guarantee its accuracy, completeness, or reliability. For authoritative information, please refer to the original, peer-reviewed article.

At a glance

Authors
Leonard M. Coulibaly; Klaudia Birner; Azin Zarghami; Markus Gumpinger; Simon Schürer-Waldheim; Philipp Fuchs; Hrvoje Bogunović; Ursula M. Schmidt-Erfurth; Gregor S. Reiter
Publication
American Journal of Ophthalmology
Keywords
Microperimetry; Geographic Atrophy; Repeatability; Optical Coherence Tomography; Retinal Pigment Epithelium; Photoreceptor Cells; Deep Learning; Biomarker
Year
2025
View primary source

This is the evidence

See where we take it next

Join the Network