Vessel Segmentation in Coloured Retinal Fundus Images Based on Multi-scale Analysis

Retinal diseases are already the most common cause of childhood blindness worldwide. Accordingly, it would be extensively beneficial to humans and healthrelatedcommunities if we could automate the procedure of diagnosis thoroughly or at least partially by exploiting capabilities of computer-aided diagnosis (CAD). This paper proposes two segmentation methods, supervised method and an unsupervised one, which shall expertly tackle the problem of vessel segmentation in retinal fundus images. Our unsupervised method exploits the power of multiscale spatial filters to locate and detect different types of vessels in terms of vessel diameter. Furthermore, we proposed novel denoising filter to overcome challenge called FOV’s tangential ring effectively. In our supervised algorithm, we combined the unsupervised method with support-vector machine (SVM) classifier, in which samples’ features are produced using feature-fusion technique. Dataset used in this research is the public DRIVE (Digital Retinal Images for Vessel Extraction) dataset. We have also addressed another challenging problem with solution that is dataset independent, the challenge of generating mask for retinal coloured images. Our supervised method has achieved higher accuracy of 94.48%, and our unsupervised method has achieved an accuracy of 94.28% with response time of 1.65 second providing human operators or automatic systems with fast and reliable results.