Evaluation of Automatically Quantified Foveal Avascular Zone Metrics for Diagnosis of Diabetic Retinopathy Using Optical Coherence Tomography Angiography

Abstract

PurposeTo describe an automated algorithm to quantify the foveal avascular zone (FAZ), using optical coherence tomography angiography (OCTA), and to compare its performance for diagnosis of diabetic retinopathy (DR) and association with best-corrected visual acuity (BCVA) to that of extrafoveal avascular area (EAA).MethodsWe obtained 3 × 3-mm macular OCTA scans in diabetic patients with various levels of DR and healthy controls. An algorithm based on a generalized gradient vector flow (GGVF) snake model detected the FAZ, and metrics assessing FAZ size and irregularity were calculated. We compared the automated FAZ segmentation to manual delineation and tested the within-visit repeatability of FAZ metrics. The correlations of two conventional FAZ metrics, two novel FAZ metrics, and EAA with DR severity and BCVA, as determined by Early Treatment Diabetic Retinopathy Study (ETDRS) charts, were assessed.ResultsSixty-six eyes from 66 diabetic patients and 19 control eyes from 19 healthy participants were included. The agreement between manual and automated FAZ delineation had a Jaccard index > 0.82, and the repeatability of automated FAZ detection was excellent in eyes at all levels of DR severity. FAZ metrics that incorporated both FAZ size and shape irregularity had the strongest correlation with clinical DR grade and BCVA. Of all the tested OCTA metrics, EAA had the greatest sensitivity in differentiating diabetic eyes without clinical evidence of retinopathy, mild to moderate nonproliferative DR (NPDR), and severe NPDR to proliferative DR from healthy controls.ConclusionsThe GGVF snake algorithm tested in this study can accurately and reliably detect the FAZ, using OCTA data at all DR severity grades, and may be used to obtain clinically useful information from OCTA data regarding macular ischemia in patients with diabetes. While FAZ metrics can provide clinically useful information regarding macular ischemia, and possibly visual acuity potential, EAA measurements may be a better biomarker for DR.

Automatic quantification of superficial foveal avascular zone in optical coherence tomography angiography implemented with deep learning

“…Table 2 Segmentation performance of the proposed method in each parameter group Parameter group Dice similarity coefficient (mean ± SD) Sensitivity (mean ± SD) Specificity (mean ± SD) R G1 0.977 ± 0.001 0.972 ± 0.017 0.999 ± 0.001 0.998 (p = 0.000 < 0.5) G2 0.975 ± 0.011 0.967 ± 0.022 0.999 ± 0.001 0.997 (p = 0.000 < 0.5) G3 0.977 ± 0.001 0.972 ± 0.017 0.999 ± 0.001 0.998 (p = 0.000 < 0.5) G4 0.976 ± 0.010 0.972 ± 0.018 0.999 ± 0.001 0.998 (p = 0.000 < 0.5) G5 0.976 ± 0.010 0.972 ± 0.018 0.999 ± 0.001 0.998 (p = 0.000 < 0.5) G6 0.976 ± 0.010 0.973 ± 0.018 0.999 ± 0.001 0.997 (p = 0.000 < 0.5) G7 0.977 ± 0.009 0.974 ± 0.016 0.999 ± 0.001 0.998 (p = 0.000 < 0.5) G8 0.975 ± 0.011 0.971 ± 0.020 0.999 ± 0.001 0.998 (p = 0.000 < 0.5) G9 0.972 ± 0.013 0.975 ± 0.018 0.999 ± 0.001 0.996 (p = 0.000 < 0.5) Table 3 Comparison of the segmentation performance between our proposed method and similar studies Study Dice similarity coefficient R Lu et al . [12] 0.808 0.792 (p = 0.000 < 0.5)…”

“…Specifically, Lu et al [12] extracted an sFAZ by applying a region-growing approach, in which the image center point was manually selected as a seed. The final sFAZ segmentation result was obtained by applying morphological operators and an active contour model.…”

Macular Vessel Density Measured With Optical Coherence Tomography Angiography and Its Associations in a Large Population-Based Study

“…[11][12][13][14] Studies also showed the clinical applicability of OCTA for diagnosis and management of glaucoma, and retinal and choroidal diseases. 5,[15][16][17][18][19][20] However, these were hospital-based studies with relatively few subjects and potential selection bias. A population-based, rather than a hospital-based, investigation has the advantage of being free of potential selection bias induced by referring doctors.…”

Glaucomatous vertical vessel density asymmetry of the temporal raphe detected with optical coherence tomography angiography

“…Therefore, further studies with a larger scan area are needed. Third, several studies have already shown that systemic diseases, including diabetes, contribute to a macular VD decrease and an increase in the foveal avascular zone area [44][45][46] . However, an ADRVD was not detected in any of the examined patients with diabetes.…”