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

Jinming Duan,Ryan Wen Liu,Li Bai,Frank Proudlock,Irene Gottlob,Weicheng Xie,Christopher Tench

doi:10.1007/978-3-030-04747-4_17

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.

Highlights

Optical coherence tomography (OCT) image segmentation to detect retinal layer boundaries is a fundamental procedure for diagnosing and monitoring the progression of retinal and optical nerve diseases
In this paper we propose a shape-based variational Mumford-Shah (MS) functional for segmentation of up to 9 retinal layer boundaries in optical coherence tomography (OCT) images, using only a small training set
– We introduce a new piecewise constant variational MS functional to evolve a pre-defined retinal layer boundary model for OCT image segmentation

Summary

Introduction

Optical coherence tomography (OCT) image segmentation to detect retinal layer boundaries is a fundamental procedure for diagnosing and monitoring the progression of retinal and optical nerve diseases. There exist rich literature on approaches for automatic and semi-automatic OCT image segmentation. Deep neural networks are becoming increasingly popular for OCT segmentation, demonstrating excellent performance [7,8]. These deep learning methods usually require the networks to be sufficiently deep to learn all appearance and shape variations of the retinal layers from annotated training sets. Large annotated training sets are difficult to obtain. Existing OCT segmentation algorithms tend to segment individual retinal layers separately. This form of analysis often fails when there is uncertainty in the image, especially some retinal layers are often difficult to see or missing in OCT images

Methods

Results

Conclusion