Variance components for PIMD‐2π estimation of the optic nerve head and consequences in clinical measurements of glaucoma

Abstract

Purpose To estimate the sources of variation for Pigment epithelium central limit‐Inner limit of the retina Minimal Distance averaged over 2π (PIMD‐2π), and further to analyse their consequences for clinical measurements of glaucoma. Methods Forty subjects with early to moderate stage glaucoma were included. Three SD‐OCT volumes of the optic nerve head (ONH) were captured at two occasions. Each volume was segmented three times for PIMD‐2π. The magnitude of the sources of variation for PIMD‐2π measurements was estimated with an analysis of variance. Results A 95% confidence interval for mean PIMD‐2π was estimated to 215 ± 12 μm (df = 38). The estimated variance for subjects was 1280 μm2. The within‐subject estimated variance for occasions, volumes and segmentations was 10 μm2, 30 μm2 and 40 μm2, respectively. The within‐subject variances were used to model follow‐up of PIMD‐2π over time. A linear loss rate of 0.05 of baseline PIMD‐2π/year was assumed. A significant PIMD‐2π change could be detected in approximately 16–18 months with evenly spaced visits every 4 or 6 months. Conclusions Due to the small within‐subject estimated variances, a clinically undesirable PIMD‐2π change from baseline can be detected in approximately 18 months. Detection of significant PIMD‐2π loss in a subject requires knowledge of normal age loss and measurement variability.

Automatic estimation of the cross‐sectional area of the waist of the nerve fibre layer at the optic nerve head

“…In our original publications (Sandberg Melin et al, 2019a, 2019b), PIMD was estimated as the spatial distance between OPCL and IRCP. Due to the limitation in the spatial resolution, often, the same IRCP corresponded to consecutive OPCL coordinates.…”

“…Recently, it was found that there is no difference in efficiency between PIMD-2π and PIMA-2π at 0.95 specificity considering averages among subjects (Söderberg et al, 2022). The lack of difference is probably due to substantial variability among individuals (Sandberg Melin et al, 2019b). Within-subject comparison may result in different efficiencies.…”