A New Seeded Region Growing Technique for Retinal Blood Vessels Extraction

Distribution of retinal blood vessels (rbvs) in retinal images has an important role in the prevention, diagnosis, monitoring andtreatment of diseases, such as diabetes, high blood pressure, or heart disease. therefore, detection of the exact location of rbvs isvery important for ophthalmologists. one of the frequently used techniques for extraction of these vessels is region growing basedsegmentation. in this paper, we propose a new region growing (rg) technique for rbvs extraction, called cellular automata basedsegmentation. rg techniques often require manually seed point selection, that is, human intervention. however, due to the complexstructure of vessels in retinal images, manual tracking of them is very difficult. therefore, to make our proposed technique fullautomatic, we use an automatic seed point selection method. the proposed rg technique was tested on digital retinal imagesfor vessel extraction database for three different initial seed sets and evaluated against the manual segmentation of retinal imagesavailable at this database. three quantitative criteria including accuracy, true positive rate and false positive rate, were considered toevaluate this method. the visual scrutiny of the segmentation results and the quantitative criteria show that, using cellular automatafor extracting the blood vessels is promising. however, the important point at here is that the correct initial seeds have an effectiverole on the final results of segmentation.