Dataset Information

A New Approach to Segment Both Main and Peripheral Retinal Vessels Based on Gray-Voting and Gaussian Mixture Model.

ABSTRACT: Vessel segmentation in retinal fundus images is a preliminary step to clinical diagnosis for some systemic diseases and some eye diseases. The performances of existing methods for segmenting small vessels which are usually of more importance than the main vessels in a clinical diagnosis are not satisfactory in clinical use. In this paper, we present a method for both main and peripheral vessel segmentation. A local gray-level change enhancement algorithm called gray-voting is used to enhance the small vessels, while a two-dimensional Gabor wavelet is used to extract the main vessels. We fuse the gray-voting results with the 2D-Gabor filter results as pre-processing outcome. A Gaussian mixture model is then used to extract vessel clusters from the pre-processing outcome, while small vessels fragments are obtained using another gray-voting process, which complements the vessel cluster extraction already performed. At the last step, we eliminate the fragments that do not belong to the vessels based on the shape of the fragments. We evaluated the approach with two publicly available DRIVE (Staal et al., 2004) and STARE (Hoover et at., 2000) datasets with manually segmented results. For the STARE dataset, when using the second manually segmented results which include much more small vessels than the first manually segmented results as the "gold standard," this approach achieved an average sensitivity, accuracy and specificity of 65.0%, 92.1% and 97.0%, respectively. The sensitivities of this approach were much higher than those of the other existing methods, with comparable specificities; these results thus demonstrated that this approach was sensitive to detection of small vessels.

SUBMITTER: Dai P

PROVIDER: S-EPMC4457795 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundInflammation has been proposed to be important in the pathogenesis of diabetic retinopathy. An early feature of inflammation is the release of cytokines leading to increased expression of endothelial activation markers such as vascular cellular adhesion molecule-1 (VCAM-1). Here we investigated the impact of diabetes and dyslipidemia on VCAM-1 expression in mouse retinal vessels, as well as the potential role of tumor necrosis factor-? (TNF?).Methodology/principal findingsExpression of VCAM-1 was examined by confocal immunofluorescence microscopy in vessels of wild type (wt), hyperlipidemic (ApoE(-/-)) and TNF? deficient (TNF?(-/-), ApoE(-/-)/TNF?(-/-)) mice. Eight weeks of streptozotocin-induced diabetes resulted in increased VCAM-1 in wt mice, predominantly in small vessels (<10 µm). Diabetic wt mice had higher total retinal TNF?, IL-6 and IL-1? mRNA than controls; as well as higher soluble VCAM-1 (sVCAM-1) in plasma. Lack of TNF? increased higher basal VCAM-1 protein and sVCAM-1, but failed to up-regulate IL-6 and IL-1? mRNA and VCAM-1 protein in response to diabetes. Basal VCAM-1 expression was higher in ApoE(-/-) than in wt mice and both VCAM-1 mRNA and protein levels were further increased by high fat diet. These changes correlated to plasma cholesterol, LDL- and HDL-cholesterol, but not to triglycerides levels. Diabetes, despite further increasing plasma cholesterol in ApoE(-/-) mice, had no effects on VCAM-1 protein expression or on sVCAM-1. However, it increased ICAM-1 mRNA expression in retinal vessels, which correlated to plasma triglycerides.Conclusions/significanceHyperglycemia triggers an inflammatory response in the retina of normolipidemic mice and up-regulation of VCAM-1 in retinal vessels. Hypercholesterolemia effectively promotes VCAM-1 expression without evident stimulation of inflammation. Diabetes-induced endothelial activation in ApoE(-/-) mice seems driven by elevated plasma triglycerides but not by cholesterol. Results also suggest a complex role for TNF? in the regulation of VCAM-1 expression, being protective under basal conditions but pro-inflammatory in response to diabetes.

Dataset Information

A New Approach to Segment Both Main and Peripheral Retinal Vessels Based on Gray-Voting and Gaussian Mixture Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure