Automated segmentation of macular layers in OCT images and quantitative evaluation of performances

Abstract

Optical coherence tomography (OCT) allows high-resolution and noninvasive imaging of the structure of the retina in humans. This technique revolutionized the diagnosis of retinal diseases in routine clinical practice. Nevertheless, quantitative analysis of OCT scans is yet limited to retinal thickness measurements. We propose a novel automated method for the segmentation of eight retinal layers in these images. Our approach is based on global segmentation algorithms, such as active contours and Markov random fields. Moreover, a Kalman filter is designed in order to model the approximate parallelism between the photoreceptor segments and detect them. The performance of the algorithm was tested on a set of retinal images acquired in-vivo from healthy subjects. Results have been compared with manual segmentations performed by five different experts, and intra and interphysician variability has been evaluated as well. These comparisons have been carried out directly via the computation of the root mean squared error between the segmented interfaces, region-oriented analysis, and retrospectively on the thickness measures derived from the segmentations. This study was performed on a large database including more than seven hundred images acquired from more than one hundred healthy subjects. OCT image enhancement, by performing image equalization [9], applying directional filters [9] or coherence-enhanced diffusion filtering [10]; A-scans (columns) alignment with regard to a reference retina layer, determined by cross correlation of adjacent columns [6] or with regard to an already detected interface [9,11]. The filtered OCT images are then passed to the interface detection process. This second step is generally based on the search for peak Contents lists available at ScienceDirect

An anomaly detection approach for the identification of DME patients using spectral domain optical coherence tomography images

“…Then, a graph-cut method is applied to get the final segmentation using the probabilities of an initial segmentation based on texture classification as constraints. Although methods based on a prior segmentation of retinal layers have reported good detection accuracy, this first step is still difficult and subject to errors [12,13]. More-over, as mentioned by Lee et al, retinal thickness measurement differences produced by different algorithms are important and it is not always possible to compare retinal thicknesses among eyes in which thickness measurements have been obtained by different systems [14].…”

Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search

“…in [46], active contours is combined with Markov random fields to create a global layer segmentation method. Other methods also combine the CNN model with additional techniques (e.g.…”

Automated retinal layers segmentation in SD-OCT images using dual-gradient and spatial correlation smoothness constraint

“…However, active contour methods are time-consuming and have limited accuracy, making clinical application difficult. Machine learning and pattern recognition [30][31][32][33][34][35] have also been used for OCT image segmentation. In practice, these methods can work well if training set contains various examples of retinal images.…”