Computational Retinal Microvascular Biomarkers from an OCTA Image in Clinical Investigation.

Area of Science:

• Ophthalmology and Medical Imaging
• Biomedical Engineering
• Computational Biology

Background:

• Retinal structural and functional changes indicate various physiological and pathological conditions.
• Non-invasive retinal imaging allows direct inspection of microvasculature and pathological changes.
• Optical coherence tomography angiography (OCTA) provides high-resolution 3D mapping of retinal microvasculature.

Purpose of the Study:

• To develop a framework for extracting computational retinal microvasculature biomarkers (CRMBs) from OCTA images.
• To improve the identification of the foveal avascular zone (FAZ) and introduce novel vessel dispersion metrics.
• To differentiate superficial and deep retinal vascular plexuses for correlation with pathology.

Main Methods:

• A knowledge-driven, computerized automatic analytical system was developed for CRMB extraction from OCTA images.
• The system enhances FAZ identification and introduces a novel definition of macular vessel dispersion.
• Retinal large vessels and capillaries in superficial and deep plexuses are differentiated.

Main Results:

• The framework successfully extracts CRMBs from OCTA images.
• A cross-sectional study with healthy subjects and retinal vein occlusion (RVO) patients demonstrated the diagnostic value of OCTA CRMBs.
• Strong correlations were found between OCTA CRMBs and retinal function in RVO patients.

Conclusions:

• The developed OCTA CRMBs pipeline offers a comprehensive tool for analyzing retinal microvasculature.
• These biomarkers can provide insights into disease severity, treatment response, and prognosis.
• The system aids in the early detection and management of various retinal, cerebral, and systemic disorders.