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.

Radiomics-Based Prediction of Anti-VEGF Treatment Response in Neovascular Age-Related Macular Degeneration With Pigment Epithelial Detachment

“…The tools discussed in this study and others are easily generalizable beyond PED and other retinal fluid compartments and could be applied to other retinal disease processes, healthy eyes with comorbid risk factors, and other types of ocular imaging. 14 – 19 Expanded use of radiomics for prediction holds promise for improving care for an even broader patient population.…”

“…diabetic macular edema, myopia maculopathy, and age-related macular degeneration), 14 – 16 and imaging modalities (e.g., optical coherence tomography [OCT], optical coherence tomography angiography [OCTA], and ultra-wide-field fluorescein angiography [UWFA]). 17 – 19 Radiomic feature extraction is a promising approach to identifying biomarkers for the development of intuitive, efficient, and interpretable prediction algorithms.…”

Racial differences in quantitative optical coherence tomography angiography findings between older non-diabetics with co-morbidities

“…The average intercapillary area of the choriocapillaris is 5-20 μm while the lateral resolution of the OCTA instrument used in this study is comparably limited to 15-20 μm [39,40]. Hence, we may not have adequately distinguished neighboring capillaries, which should prompt analysis of flow deficits or other textural parameters [41] in the choriocapillaris of different races.…”