Thresholding strategies to measure vessel density by optical coherence tomography angiography

Abstract

ObjectiveA variety of binarization strategies have been used to measure vessel density by optical coherence tomography angiography (OCT-A), but it is uncertain if they produce similar results. The purpose of the study was to evaluate the impact of different thresholding methods and contrast and brightness adjustment on OCT-A vessel density metrics. DesignObservational, cross-sectional case series. ParticipantsConsecutive healthy volunteers. MethodsHealthy volunteers underwent fovea-centred 3 mm × 3 mm OCT-A scans using PlexElite 9000. Images of the superficial vascular plexus were generated using the instrument’s automated segmentation. Images were thresholded with 5 different threshold tools in ImageJ (Default, Huang, IsoDat, Mean, and Otsu), and the threshold grey level value defined by each method was recorded. Brightness and contrast were also increased or decreased by 50% compared with the default. Binarization was performed using the threshold values from each method, and vessel densities were computed and compared. Main outcome measuresSuperficial plexus vessel density was measured and compared using different adjust threshold tools and changing brightness and contrast. ResultsTwenty eyes of 20 healthy participants were included. Different threshold strategies produced measurements with different mean values (p < 0.0001). Pairwise comparisons revealed differences between all groups (p < 0.0001) except between the IsoData and Otsu thresholding approaches (p > 0.270). Increasing or decreasing the brightness or to 50% of the mean value also yielded statistically significant differences (p < 0.0001). ConclusionsThe method of thresholding and adjustments in contrast and brightness can significantly impact retinal vessel density measurements. These findings highlight the importance of using consistent thresholding strategies for clinical studies.