AVA-Net: an open-source deep learning network for arterial-venous area segmentation in OCT angiography

Abstract

Differential artery-vein (AV) analysis in optical coherence tomography angiography (OCTA) holds promise for early detection of eye diseases. However, currently available methods for AV analysis are limited for binary processing of retinal vasculature in OCTA, without quantitative information of vascular perfusion intensity. This study is to develop a deep learning network AVA-Net for automated AV area (AVA) segmentation in OCTA, and thus to enable quantitative AV analysis of vascular perfusion intensity. Seven new OCTA features, including arterial area (AA), venous area (VA), AVA ratio (AVAR), total perfusion intensity density (T-PID), arterial PID (A-PID), venous PID (V-PID), and arterial-venous PID ratio (AV-PIDR), have been developed and validated for early detection of diabetic retinopathy (DR). Each of these seven features was evaluated for quantitative comparison of OCTA images from healthy controls, diabetic patients without DR (NoDR), and mild DR. It was observed that the area features, i.e., AA, VA and AVAR, can reveal significant differences between the control and diabetic eyes (NoDR and mild DR), but cannot separate NoDR and mild DR from each other. Vascular perfusion parameters, including T-PID and V-PID, can differentiate mild DR from control and NoDR groups, but cannot separate control and NoDR from each other. In contrast, the AV-PIDR can disclose significant differences among all three groups, i.e., control, NoDR, and mild DR. The AVA-Net validated in this study is available on GitHub for open access.