Intra-retinal Layer Segmentation in Optical Coherence Tomography Using an Active Contour Approach

Abstract

Abstract. Optical coherence tomography (OCT) is a non-invasive, depth resolved imaging modality that has become a prominent ophthalmic diagnostic technique. We present an automatic segmentation algorithm to detect intra-retinal layers in OCT images acquired from rodent models of retinal degeneration. We adapt Chan-Vese's energy-minimizing active contours without edges for OCT images, which suffer from low contrast and are highly corrupted by noise. We adopt a multi-phase framework with a circular shape prior in order to model the boundaries of retinal layers and estimate the shape parameters using least squares. We use a contextual scheme to balance the weight of different terms in the energy functional. The results from various synthetic experiments and segmentation results on 20 OCT images from four rats are presented, demonstrating the strength of our method to detect the desired retinal layers with sufficient accuracy and average Dice similarity coefficient of 0.85, specifically 0.94 for the the ganglion cell layer, which is the relevant layer for glaucoma diagnosis.

The Generalized Log-Ratio Transformation: Learning Shape and Adjacency Priors for Simultaneous Thigh Muscle Segmentation

“…When manually segmenting an image, a clinician often must rely on their prior knowledge of anatomy in order to distinguish different structures; automated segmentation methods must somehow encode similar anatomical information to achieve adequate accuracy. For example, Yazdanpanah et al and Garvin et al [1], [2], encoded spatial relationships between retinal layers S. Andrews [3], [4] encoded containment and exclusion constraints in level sets and graph cut segmentation frameworks, respectively, and applied their methods to cardiac, bone, microscopy, and other segmentation tasks.…”

A Review of Algorithms for Segmentation of Retinal Image Data Using Optical Coherence Tomography

“…In 2009, Yazdanpanah et al presented a modified ChanVese's energy-minimizing active contour algorithm in a multi-phase framework to segment SDOCT data from rodent models. This approach incorporated a circular shape prior based on expert anatomical knowledge of the retinal layers, avoiding the need for training www.intechopen.com A Review of Algorithms for Segmentation of Retinal Image Data Using Optical Coherence Tomography 33 (Yazdanpanah, et al, 2009). Although the sensitivity of the algorithm with respect to model parameters and initialization was not tested, the experimental results showed that this approach was able to detect with good accuracy the desired retinal layers in OCT retinal images from rats compared to the ground truth segmentation used in the evaluations performed.…”

Retinal thickness estimation from SD-OCT macular scans

“…The most recent example of region-based deformable model segmentation is that of Yazdanpanah et al [16], where standalone murine SD-OCT B-scans were segmented into 6 retinal layers. As reported in [16], this model can be corrupted by noise and suffers from areas of low contrast, while the segmentation time was not provided. Such model-based approaches, while effective with respect to a single image of an OCT stack, ignore useful spatial information that could be harnessed if an integrated 3D volume analysis was performed.…”