Capillary-Large Vessel Segmentation on OCTA for Predicting Anti-VEGF Treatment Outcomes in Diabetic Macular Edema

Objective: This study aimed to evaluate the predictability of baseline optical coherence tomography angiography (OCTA) metrics utilizing a specialized capillary-large vessel segmentation analysis framework in patients with diabetic macular edema (DME) undergoing anti-vascular endothelial growth factor (anti-VEGF) therapy. Methods: Forty-two treatment-naïve eyes with DME receiving three monthly loading anti-VEGF injections were included. Superficial capillary plexus (SCP) images from 3 × 3 mm OCTA scans were processed to isolate the capillary network from the large vessels via image processing. Vessel density and skeleton density were extracted for the total, large-vessel, and capillary components. Multiple linear and logistic regression models were used to identify independent predictors of post-treatment best-corrected visual acuity (BCVA) and "good visual outcome" (≥3-line improvement or final BCVA of 20/40 or better). Results: Following three monthly anti-VEGF injections, the mean BCVA significantly improved from 0.57 ± 0.36 to 0.37 ± 0.30 LogMAR (p < 0.0001), and the mean central retinal thickness decreased from 424.3 ± 117.7 μm to 316.9 ± 84.7 μm (p < 0.0001). The proportion of patients who achieved a good visual outcome was 73.8%. Baseline central retinal thickness was associated with baseline BCVA (p = 0.049) but not predictive of post-treatment BCVA (p = 0.38) or good visual outcomes (p = 0.79). Baseline capillary vessel density was identified as a significant independent predictor of post-treatment BCVA (p = 0.024), whereas total and large-vessel metrics were not. Capillary vessel density was also the only significant predictor of good visual outcomes (p = 0.044). Conclusions: Baseline capillary vessel density is a robust predictor of visual prognosis after anti-VEGF therapy in patients with DME, underscoring the importance of capillary network integrity in functional recovery.