An optimized segmentation and quantification approach in microvascular imaging for OCTA-based fibrovascular regression monitoring

Abstract Background: Quantification of neovascularization changes in fibrovascular membrane (FVM) acquired from optical coherence tomography angiography (OCTA) imaging is extremely important for diagnosis and treatment monitoring of proliferative diabetic retinopathy (PDR). However, few vessel extraction methods have been reported for quantifying the neovascular changes on fibrovascular membrane (FVM) in proliferative diabetic retinopathy PDR based on OCTA imaging. Results: The proposed method has achieved better performance compared with existing algorithms on accuracy and can be used for PRD treatment monitoring. In the study of PDR treatment monitoring, the data show that from the beginning (0 day) to 5th day of treatment, the total length of neovascularization on FVM in this area has been significantly shortened by an 77.8% reduction, indicating significant effects from the treatment applied. Besides, the average width of the neovascularization on FVM at the 7th day after treatment has been increased by 158%, which indicates that most of the narrow neovascularization has been reduced. Conclusion: The result and analysis have confirmed that the proposed optimization process with improved VCA method is both effective and feasible to segment and quantify the neovascularization on FVM with less noise and artifacts, thus can be readily applied to monitor the fibrovascular regression within the treatment period.