%0 Journal Article
%T Extraction of Blood Vessels in Retinal Images Using Four Different Techniques
%A Asloob Ahmad Mudassar
%A Saira Butt
%J Journal of Medical Engineering
%D 2013
%I Hindawi Publishing Corporation
%R 10.1155/2013/408120
%X A variety of blood vessel extraction (BVE) techniques exist in the literature, but they do not always lead to acceptable solutions especially in the presence of anomalies where the reported work is limited. Four techniques are presented for BVE: (1) BVE using Image Line Cross-Sections (ILCS), (2) BVE using Edge Enhancement and Edge Detection (EEED), (3) BVE using Modified Matched Filtering (MMF), and (4) BVE using Continuation Algorithm (CA). These four techniques have been designed especially for abnormal retinal images containing low vessel contrasts, drusen, exudates, and other artifacts. The four techniques were applied to 30 abnormal retinal images, and the success rate was found to be (95 to 99%) for CA, (88每91%) for EEED, (80每85%) for MMF, and (74每78%) for ILCS. Application of these four techniques to 105 normal retinal images gave improved results: (99-100%) for CA, (96每98%) for EEED, (94-95%) for MMF, and (88每93%) for ILCS. Investigations revealed that the four techniques in the order of increasing performance could be arranged as ILCS, MMF, EEED, and CA. Here we demonstrate these four techniques for abnormal retinal images only. ILCS, EEED, and CA are novel additions whereas MMF is an improved and modified version of an existing matched filtering technique. CA is a promising technique. 1. Introduction Accurate and automatic assessment of retinal images has been considered as a powerful tool for the diagnosis of retinal disorders such as diabetic retinopathy, hypertension, and arteriosclerosis. Blood vessels have varying contrast due to which the darker vessels (thick vessels) can be extracted easily using standard techniques mentioned in the literature while it is difficult to extract the vessels having poor contrast (thin vessels). Segmentation of blood vessels in retinal images is a field of interest for scientists since last two decades [1每4]. Various kinds of eye abnormalities are indicated by changes in vessel tree structure [5, 6]. A true vessel tree structure should contain information about precise thickness of blood vessels in the retinal images. Optic disc and fovea can be located by tracking the vessel tree [7]. Central retinal artery occlusion produces dilated tortuous veins, age related macular degeneration and diabetes can generate new blood vessels (neovascularization), and the study of retinopathy of prematurity in premature infants is not possible without the knowledge of vessel tree structure. Progression of such eye diseases can only be tracked by noticing the changes in the vessel tree structure with the passage of time.
%U http://www.hindawi.com/journals/jme/2013/408120/