To assess the impact of histogram adjustments and binarization thresholding selection on quantitative measurements of diabetic macular ischemia using optical coherence tomography angiography (OCTA).
Patients with diabetic retinopathy (DR) who had swept-source OCTA imaging obtained were enrolled. An additional group of 15 healthy control subjects was included for comparison. Previously employed brightness/contrast changes and binarization thresholds were applied to original OCTA images in order to obtain and compare different binarized images. Qualitative and quantitative comparisons were performed.
Thirty patients with DR (30 eyes) were included in the analysis. Fifteen eyes displayed the presence of diabetic macular edema (DME). Qualitative grading revealed that binarized images obtained using a global threshold had better quality compared with local or multistep thresholds. The “median” filter was most frequently graded as the histogram adjustment resulting in binarized images with best quality. In the quantitative analysis, local thresholds tended to generate higher values of measured metrics. Differences in OCTA metrics between global and local thresholds were associated with presence of DME and signal strength index value. In the comparison between healthy and DR eyes, differences in OCTA metrics were significantly affected by binarization threshold selection.
Quantitative OCTA parameters may be significantly influenced by strategies to quantify macular perfusion. Image quality and presence of macular edema can significantly impact OCTA-derived quantitative vascular measurements and differences between global and local binarization thresholds. These findings highlight the importance of consistent strategies to reliably generate quantitative OCTA metrics in DR patients.

Author