Computerized Texture Analysis of Optical Coherence Tomography Angiography of Choriocapillaris in Normal Eyes of Young and Healthy Subjects

Abstract

Computerized texture analysis uses higher-order mathematics to identify patterns beyond what the naked eye can recognize. We tested its feasibility in optical coherence tomography angiography imaging of choriocapillaris. Our objective was to determine sets of parameters that provide coherent and consistent output when applied to a homogeneous, healthy group of patients. This observational cross-sectional study involved 19 eyes of 10 young and healthy Caucasian subjects. En-face macular optical coherence tomography angiography of superficial choriocapillaris was obtained by the RTVue-XR Avanti system. Various algorithms were used to extract texture features. The mean and standard deviation were used to assess the distribution and dispersion of data points in each metric among eyes, which included: average gray level, gray level yielding 70% threshold and 30% threshold, balance, skewness, energy, entropy, contrast, edge mean gradient, root-mean-square variation, and first moment of power spectrum, which was compared between images, showing a highly concordant homology between all eyes of participants. We conclude that computerized texture analysis for en-face optical coherence tomography angiography images of choriocapillaris is feasible and provides values that are coherent and tightly distributed around the mean in a homogenous, healthy group of patients. Homology of blob size among subjects may represent a "repeat pattern" in signal density and thus a perfusion in the superficial choriocapillaris of healthy young individuals of the same ethnic background.

Keywords: choriocapillaris; computerized texture analysis; optical coherence tomography angiography.

Figure 1

En-face 3 × 3 mm macular OCTA image of choriocapillaris of a young healthy subject (A). Texture modification using different filters: Edge filter (B), Corner filter (C), Histogram of oriented gradients (D), Blob localization (E), Local binary pattern (F).

Figure 2

Blob size distribution, each color representing one eye of a subject (A). Normalized Fourier transform with 0.2 threshold; each color represents an eye (B).

Figure 3

Gray level histogram analysis consisting of measures of Balance (A) and Skewness (B). Absolute value of gray levels in OCTA images of choriocapillaris in each eye. These set of measures included average gray level (C), gray level with 30% (D) or 70% threshold (E). Spatial relationship among gray levels in OCTA images of choriocapillaris in each eye. Energy (F), entropy (G), and contrast (H) were measured in this category of measures.

Figure 4

Fourier transform analysis of parameters. Root mean square (RMS) variation (A) and First Moment of Power (FMP) spectrum (B) is shown. Edge frequency analysis (C) is depicted.