视网膜眼底病变图像血管提取方法.pdfVIP

Abstract The retinal fundus image is an important basis for diagnosing of eye disease.Automatic retinal image processing and analyzing system based on computer has an important application value in auxiliary medical diagnosis. Retinal vasculature is an important anatomical structure in retinal fundus image, which spread over whole retinal image as well as tree network structure. Vessel extracting plays an important role in diagnosis of disease such as glaucoma, cataract, diabetics, hypertension, and arteriosclerosis, which often cause micro-vessel change. On the one side, many fundus image analysis and identification algorithms need the information of vascular structure in advance. On the other side, as a relatively stable physiological characteristic structure，vessel has important role in diagnosis system. For example, its distribution characteristics and feature information are favorable for the assessment of retinal disease, it benefit for the localization of other anatomical structure such as optic disc, fovea, and also for lesion detection and multi-source or multi-modal retinal image registration and integration. A lot of research work of vessel extraction has proceeded in all over the world and has made great progress. Although vessel extraction result is good in normal retinal images, it is difficult to extract vascular network structure in disease images accurately, due to the edge of the optic disc, exudates or other lesions has a similar characteristics as vessel and the interference of dark gap between nearly multiply bright areas. This paper focus an in-depth study of vessel extraction in retinopathy image. (1) Due to vascular- like characteristics existed in disease images and