Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection\nmethodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is\nproposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by\nutilizing all image channels, generating more efficient results compared to methods utilizing only one (green)\nchannel. A structure-based level set method employing a modified phase map is introduced to obtain accurate\nskeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the\nlevel sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level\ncontour regularization term which is more appropriate than the ones introduced by other methods for vasculature\nstructures. We conducted the experiments on our own data set, as well as two publicly available data sets. The results\nshow that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art\nsupervised/unsupervised segmentation techniques.
Loading....