Abstract
Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection methodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is proposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by utilizing all image channels, generating more efficient results compared to methods utilizing only one (green) channel. A structure-based level set method employing a modified phase map is introduced to obtain accurate skeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the level sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level contour regularization term which is more appropriate than the ones introduced by other methods for vasculature structures. We conducted the experiments on our own dataset, as well as two publicly available datasets. The results show that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art supervised/unsupervised segmentation techniques.
Highlights
Published ophthalmology studies reveal that there are often significant differences in clinical diagnosis of retinal diseases among medical experts [1]
Eight uniformly distributed angle directions and three image re-sampling scales for the log-Gabor filter are used in the method
Small gaps in the created mask image for STARE dataset are filled using a morphological closing operator whose structure element is a disk of radius 10
Summary
Published ophthalmology studies reveal that there are often significant differences in clinical diagnosis of retinal diseases among medical experts [1]. Some of these approaches involve tedious processes. Due to the structure of the optic disk and macula, segmentation of blood vessels of retinal images is difficult These regions have a more prominent intensity inhomogeneity compared to other parts of retinal images. Pathological images may contain defects and disorders such as drusen, geographic atrophy (GA), and non-uniform intensities. Such disorders make the process of segmentation complicated
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have