Elevated Retinal Neovascularization on Widefield Optical Coherence Tomography Angiography Predicts Complications in...

Area of Science:

• Ophthalmology
• Medical Imaging
• Diabetic Retinopathy Research

Background:

• Proliferative diabetic retinopathy (PDR) poses a significant risk of vision loss due to complications like vitreous hemorrhage (VH) and tractional retinal detachment (TRD).
• Accurate prediction of these vision-threatening events is crucial for timely intervention in high-risk PDR patients.

Purpose of the Study:

• To evaluate the predictive capability of retinal neovascularization (RNV) metrics obtained via single-shot widefield swept-source OCT angiography (SS-OCTA) for subsequent complications in high-risk PDR eyes.
• To assess the correlation between specific RNV characteristics and the development of VH or TRD.

Main Methods:

• A prospective case series involving eyes diagnosed with high-risk PDR.
• Single-shot widefield SS-OCTA imaging was performed, and a deep learning algorithm quantified RNV membrane and vascular areas, classifying lesions as attached or elevated relative to the internal limiting membrane (ILM).
• Baseline OCTA metrics were analyzed to identify predictors of new or recurrent VH and TRD over a minimum 6-month follow-up period.

Main Results:

• Of 18 eyes followed for a median of 291 days, 44.4% developed complications (7 VH, 1 TRD).
• Eyes with complications exhibited significantly larger total RNV membrane area (25.72 mm² vs 1.33 mm²) and vascular area (9.72 mm² vs 0.76 mm²).
• Elevated RNV membrane area (5.13 mm² vs 0.10 mm²) and vascular area (2.69 mm² vs 0.05 mm²) were significantly larger in eyes with complications; total RNV membrane area showed high predictive performance (AUC=0.888).

Conclusions:

• Widefield SS-OCTA is a valuable tool for assessing RNV burden and its spatial relationship with the ILM in high-risk PDR.
• Elevated baseline RNV metrics, reflecting both size and anatomical features, effectively predict subsequent VH and TRD.
• These SS-OCTA-derived imaging biomarkers can potentially enhance the current clinical staging and risk stratification of PDR.