Delineating fluid-filled region boundaries in optical coherence tomography images of the retina

Abstract

We evaluate the ability of a deformable model to yield accurate shape descriptions of fluid-filled regions associated with age-related macular degeneration. Calculation of retinal thickness and volume by the current optical coherence tomography (OCT) system includes fluid-filled regions or lesions along with actual retinal tissue. In order to quantify these lesions independently from the retinal tissue, they must be outlined. A deformable model was applied to OCT images of retinas demonstrating cystoids and subretinal fluid spaces. Several implementation issues were addressed in order to choose appropriate parameters. The use of a nonlinear anisotropic diffusion filter to suppress speckle noise while at the same time preserving the edges of the original image was explored. Once the contours of the lesions were outlined, quantitative analysis of the surface area and volume of the lesions was performed. The deformable model could accurately outline fluid-filled regions within the retina. The detection method tested proved effective in capturing the complexity of fluid-filled regions in OCT images. Deformable models combined with nonlinear anisotropic diffusion filtering show promise in the detection of retinal features of interest for diagnosis in clinical OCT images. Thus, fluid-filled region detection may significantly aid in analysis of treatments and diagnosis.

Geodesic Graph Cut Based Retinal Fluid Segmentation in Optical Coherence Tomography

“…The first attempt was semi-automatic [1], where a deformable model was manually initialized and grown within a SEAD. Later, a fully automated approach was proposed in [2], where they combined a k-nearest neighbor (k-NN) classification and a graph cut segmentation.…”

Automated quantification of lung structures from optical coherence tomography images

“…Anisotropic diffusion has been demonstrated previously in the removal of speckle from retinal OCT scans [30,31]. The present implementation [32] performs diffusion with a 2D kernel that adapts the degree of smoothing, based on the location and direction of intensity gradients in the image.…”

Bio-inspired Ant Algorithms: A review

“…By using the essence of machine learning and AI, DIP can be increased its performance and efficiency. AS are also introducing as a new technique to improve its performance by using basic low level image segmentation via boundary detection methods [32], [33], [34], & [35] and via clustering methods [36] & [37]. Novel approach of boundary detection methods deploy the pheromone aspects of AS , here the ants are considered as pixels within the image and move within the image in a discretised pixel-wise fashion whose aim is to extract and map boundary"s within the image .…”