Differential artery-vein analysis improves the OCTA classification of diabetic retinopathy

Abstract

This study investigates the impact of differential artery-vein (AV) analysis in optical coherence tomography angiography (OCTA) on machine learning classification of diabetic retinopathy (DR). Leveraging deep learning for arterial-venous area (AVA) segmentation, six quantitative features, including perfusion intensity density (PID), blood vessel density (BVD), vessel area flux (VAF), blood vessel caliber (BVC), blood vessel tortuosity (BVT), and vessel perimeter index (VPI) features, were derived from OCTA images before and after AV differentiation. A support vector machine (SVM) classifier was utilized to assess both binary and multiclass classifications of control, diabetic patients without DR (NoDR), mild DR, moderate DR, and severe DR groups. Initially, one-region features, i.e., quantitative features extracted from the entire OCTA, were evaluated for DR classification. Differential AV analysis improved classification accuracies from 78.86% to 87.63% and from 79.62% to 85.66% for binary and multiclass classifications, respectively. Additionally, three-region features derived from the entire image, parafovea, and perifovea, were incorporated for DR classification. Differential AV analysis further enhanced classification accuracies from 84.43% to 93.33% and from 83.40% to 89.25% for binary and multiclass classifications, respectively. These findings highlight the potential of differential AV analysis in augmenting disease diagnosis and treatment assessment using OCTA.

Fig. 1.

Illustrating the feature extraction from an OCTA image. (A) OCTA image. (B) AVA map. (C) Fovea, parafovea, and perifovea in OCTA-AV map. (D) OCTA-AV map excluding fovea and OCTA layer indicator area. (E) Binarized OCTA-AV map including large blood vessels and small capillaries. (F) Hessian-based Frangi vesselness filter in OCTA-AV map. (G) Skeletonized blood vessel map in OCTA-AV map. (H) Vessel perimeter map in OCTA-AV map.

Fig. 2.

ROC curves for multiclass classification using data (A) from one region before AV analysis. (B) from one region after AV analysis. (C) from three regions before AV analysis. (D) from three regions after AV analysis.