OCT Segmentation: Integrating Open Parametric Contour Model of the Retinal Layers and Shape Constraint to the Mumford-Shah Functional

Abstract

In this paper, we propose a novel retinal layer boundary model for segmentation of optical coherence tomography (OCT) images. The retinal layer boundary model consists of 9 open parametric contours representing the 9 retinal layers in OCT images. An intensity-based Mumford-Shah (MS) variational functional is first defined to evolve the retinal layer boundary model to segment the 9 layers simultaneously. By making use of the normals of open parametric contours, we construct equal sized adjacent narrowbands that are divided by each contour. Regional information in each narrowband can thus be integrated into the MS energy functional such that its optimisation is robust against different initialisations. A statistical prior is also imposed on the shape of the segmented parametric contours for the functional. As such, by minimising the MS energy functional the parametric contours can be driven towards the true boundaries of retinal layers, while the similarity of the contours with respect to training OCT shapes is preserved. Experimental results on real OCT images demonstrate that the method is accurate and robust to low quality OCT images with low contrast and high-level speckle noise, and it outperforms the recent geodesic distance based method for segmenting 9 layers of the retina in OCT images.

Benchmarking automated detection of the retinal external limiting membrane in a 3D spectral domain optical coherence tomography image dataset of full thickness macular holes

“…A fully automated graph theory and dynamic programmingbased method was applied to segment three retinal layers from SD-OCT images of an eye with drusen and geographic atrophy (GA) [18]. Another group [20] used a small dataset of OCT images for statistical shape modelling. Specifically, the Mumford-Shah functional method was employed, which allows the development of a parametric illustration of open contours.…”

“…There are two main types of automated image analysis approaches that have been utilized for CAD system development, which includes classical image analysis techniques and machine learning-based image informatics techniques [18,20,64,42,54,51]. Classical image informatics methodologies have several limitations such as threshold methods which struggle with discontinuities and intensity variations across different retinal layers, and they also cannot combine previously obtained information such as retinal layer thicknesses from previous OCT scans.…”