Artificial intelligence-based assessment of imaging biomarkers in epiretinal membrane surgery

Purpose This study investigated the applicability of a validated AI-algorithm for analyzing different retinal biomarkers in eyes affected by epiretinal membranes (ERMs) before and after surgery. Methods A retrospective study included 40 patients surgically treated for ERMs removal between November 2022 and January 2024. Pars plana vitrectomy with ERM/ILM peeling was performed by a single experienced surgeon. A validated AI algorithm was used to analyze OCT scans, focusing on intraretinal fluid (IRF) and subretinal fluid (SRF) volumes, external limiting membrane (ELM) and ellipsoid zone (EZ) interruption percentages and hyper-reflective foci (HRF) counts. Results Postoperative best corrected visual acuity (BCVA) significantly improved ( p < 0.01), and central macular thickness (CMT) decreased from 483.61 ± 96.32 to 386.82 ± 94.86 µm ( p = 0.001). IRF volume reduced from 0.283 ± 0.39 mm 3 to 0.142 ± 0.27 mm 3 ( p = 0.036) particularly in the central 1 mm-circle. SRF, HRF and EZ/ELM interruption percentages exhibited no significant differences ( p > 0.05). Significant correlations ( p < 0.05) were found between preoperative BCVA and postoperative BCVA ( r = 0.45); CMT reduction and postoperative BCVA ( r = 0.42), preoperative IRF and Visual Recovery ( r = −0.48), ELM and EZ interruption and visual recovery ( r = −0.43 and r = −0.47 respectively). Multivariate analysis demonstrated that fluid distribution, especially in the central subfield, correlated with BCVA recovery (R2 = 0.38; p < 0.05; Pillai's Trace = 0.79). Conclusion The study highlights AI's potential in quantifying OCT biomarkers in ERMs surgery. The findings suggest that improved BCVA is associated with reduced CMT, IRF, and redistribution of IRF towards the periphery. EZ and ELM integrities remain crucial prognostic factors, emphasizing the importance of the preoperative analysis.