Automated OCT-Tailored and Same-Visit Biomarker-Targeted Microperimetry in Geographic Atrophy

AI Generated Summary*

Proof-of-concept work generating individualized mesopic microperimetry grids for geographic atrophy from deep learning OCT segmentation within one visit. Loss of the ellipsoid zone (EZ) and of the retinal pigment epithelium (RPE) was mapped automatically, and a rule-based algorithm placed 40 stimuli, preferentially where the EZ was absent. Of 64 enrolled eyes (44 patients, mean age 79.1 years), 61 were analysed. Mean sensitivity was 18.2 dB over intact retina, 13.3 dB over EZ loss and 7.4 dB over RPE loss (all pairwise p<0.001). Larger EZ loss area predicted lower eye-level sensitivity (-0.038 dB/mm²). Planned and delivered stimulus positions differed by a median 38.8 μm, 98.5% of points fell within their assigned zone, and testing averaged about six minutes.

*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.