Evaluation of Automated Segmentation Algorithms for Optic Nerve Head Structures in Optical Coherence Tomography Images

Abstract

PURPOSE. To compare the identification of optic nerve head (ONH) structures in optical coherence tomography images by observers and automated algorithms.METHODS. ONH images in 24 radial scan sets by optical coherence tomography were obtained in 51 eyes of 29 glaucoma patients and suspects. Masked intraobserver and interobserver comparisons were made of marked endpoints of Bruch's membrane opening (BMO) and the anterior lamina cribrosa (LC). BMO and LC positional markings were compared between observer and automated algorithm. Repeated analysis on 20 eyes by the algorithm was compared. Regional ONH data were derived from the algorithms. RESULTS.Intraobserver difference in BMO width was not significantly different from zero (P ‡ 0.32) and the difference in LC position was less than 1% different (P ¼ 0.04). Interobserver were slightly larger than intraobserver differences, but interobserver BMO width difference was 0.36% (P ¼ 0.63). Mean interobserver difference in LC position was 14.74 lm (P ¼ 0.004), 3% of the typical anterior lamina depth (ALD). Between observer and algorithm, BMO width differed by 1.85% (P ¼ 0.23) and mean LC position was not significantly different (3.77 lm, P ¼ 0.77). Repeat algorithmic analysis had a mean difference in BMO area of 0.38% (P ¼ 0.47) and mean ALD difference of 0.54 6 0.72%. Regional ALD had greater variability in the horizontal ONH regions. Some individual outlier images were not validly marked by either observers or algorithm.CONCLUSIONS. Automated identification of ONH structures is comparable to observer markings for BMO and anterior LC position, making BMO a practical reference plane for algorithmic analysis.

Characterizing the Collagen Network Structure and Pressure-Induced Strains of the Human Lamina Cribrosa

“…In vivo measurements of the pore area fraction and beam width are becoming more accessible with the developments of adaptive optics scanning laser ophthalmoscopy,29 swept-source OCT,28 and adaptive optics spectral-domain OCT 55–57. These advanced imaging methods permit high-quality visualization of the LC structure, including beam thickness and pore geometry and depth variations of these features 58…”

Detecting Retinal Nerve Fibre Layer Segmentation Errors on Spectral Domain-Optical Coherence Tomography with a Deep Learning Algorithm

“…Additionally, SDOCT has inherent characteristics that can impair correct image segmentation 20–23 . First, SDOCT tomograms suffer from intrinsic speckle noise, which degrades the image quality and complicates image analysis 24 .…”