BLOOD VESSEL ENHANCEMENT AND SEGMENTATION USING WAVELET TRANSFORM

Abstract

Diagnostic Imaging is an important addition to clinical examination in the case of patient with common illness. It provides effective and non-invasive mapping of anatomy and physiology of human being. A large number of diseases influence human body tissue in such a manner as to produce abnormalities which are detectable from the image. The different imaging technologies provide exceptional views of an internal anatomy and functionality of organs and the trained radiologist quantify and investigate the image. However, the manual. analysis of image is a time consuming process and also susceptible to human error. Retinal image processing is greatly required in diagnosing and treatment of many diseases affecting the retina and the choroid. Diabetic retinopathy is one of the complications of diabetes mellitus affecting the retina and the choroid. In this condition, a network of small blood vessels, called choroid neovascularization (CNV), arises in the choroid and taking a portion of the blood supplying the retina. As the amount of blood supplying the retina is decreased, the sight may be degraded and in the severe cases, blindness may occur. The eye is a window to the retinal vascular system which is uniquely accessible for the study. Vascular pattern is normally not visible in retinal images. Retinal blood vessel enhancement and segmentation is an essential step for the diagnosis of various eye diseases. An automated tool for blood vessel enhancement and segmentation is useful to eye specialists for purpose of patient screening and clinical study. In this dissertation work, we have used a method for enhancing, and segmenting blood vessels in images of retina. We used 2-D Gabor wavelet and Morphological algorithm for enhancement of the blood vessels in the retinal image and we compared the enhancement results obtained by both the methods. Segmentation of enhanced blood vessels is achieved using canny edge detection algorithm followed by morphological dilation operation. This whole process is tested on publicly available STARE and Drive database of retinal images. iii