Progression dynamics of early versus later-stage atrophic lesions in non-neovascular AMD using quantitative OCT biomarker segmentation.

PURPOSE: To investigate the progression of geographic atrophy (GA) secondary to non-neovascular age-related macular degeneration (AMD) in early and later stage lesions using AI-based precision tools.

DESIGN: Retrospective analysis of an observational cohort study.

SUBJECTS: Seventy-four eyes of forty-nine patients with at least one complete retinal pigment epithelial and outer retinal atrophy (cRORA) lesion secondary to AMD were included. Patients were divided between recently developed cRORA and lesions with advanced disease status.

METHODS: Patients were prospectively imaged by spectral domain optical coherence tomography (SD-OCT) volume scans. The study period encompassed 18 months with scheduled visits every 6 months. Growth rates of recently to cRORA converted lesions were compared with lesions in an advanced disease status using mixed effect models.

MAIN OUTCOME MEASURES: The progression of retinal pigment epithelial loss (RPEL) was considered the primary endpoint. Secondary endpoints consisted of external limiting membrane disruption (ELMD) and ellipsoid zone loss (EZL). These pathognomonic imaging biomarkers were quantified using validated deep learning algorithms. Further the EZ/RPE-Loss ratio was analysed in both study cohorts.

RESULTS: Mean [95%CI] square root progression of recently converted lesions was 79.676[-77.140 - 236.493], 68.219[-101.210 - 237.648) and 84.825[-124.816 - 294.467] mm/half year for RPEL, ELML and EZL respectively. Mean square root progression of advanced lesions was 131.737[-22.574 - 286.047], 129.964[-36.666 - 296.594] and 116.837[-90.556 - 324.301] mm/half year for RPEL, ELML and EZL respectively. RPEL (p=0.038) and ELMD (p=0.026) progression showed significant differences between the two study cohorts. Further recent converters had significantly (p<0.001) higher EZ/RPE-Loss ratios in all time points compared to patients in an advanced disease status (1.716 [1.135 - 2.296] versus 1.153 [0.576 - 1.729]).

CONCLUSION: Early cRORA lesions have a slower growth rate in comparison to atrophic lesions in advanced disease stages. Differences in growth dynamics may play a crucial role in understanding the pathophysiology of non-neovascular AMD and for the interpretation of clinical trials in GA. Individual disease monitoring using AI-based quantification paves the way towards optimized GA management.