Quantification of choroidal neovascularization vessel length using optical coherence tomography angiography

Area of Science:

• Ophthalmology
• Medical Imaging
• Computational Biology

Background:

• Quantifying choroidal neovascularization (CNV) is crucial for diagnosing and monitoring eye diseases.
• Optical coherence tomography angiography (OCTA) provides detailed visualization of retinal vasculature.
• Accurate and efficient quantification methods for CNV are needed.

Purpose of the Study:

• To develop and validate an automated algorithm for quantifying the vessel skeleton of CNV from OCTA images.
• To measure CNV extent by calculating vessel length.

Main Methods:

• Automated segmentation of CNV using saliency-based detection and thresholding.
• Refinement of vessel edges with a level set method.
• Identification of vessel centerlines via a skeleton algorithm.

Main Results:

• The algorithm successfully quantified CNV vessel length on en face OCTA angiograms.
• Comparisons between automated and manual delineations demonstrated good agreement.
• The method provides a reliable tool for objective CNV assessment.

Conclusions:

• The developed automated algorithm offers an efficient and accurate method for quantifying CNV vessel length.
• This tool has potential clinical applications in the diagnosis and management of diseases involving CNV.
• Automated quantification can improve the consistency and objectivity of CNV assessment.