Segmentation of Optic Disc from Fundus Images

This paper presents a novel method for segmentation of the Optic Disc (OD) in retinal images. Optic disc (OD) segmentation is an essential step for automated detection of various serious ophthalmic pathologies related to diabetic retinopathy. Therefore, exudates detection is our major purpose, but we must extract the OD prior to the process because it appears with similar color, intensity and contrast to other characteristics of the retinal image. The retinal image consists of blood vessels that emerge from the OD. 

The proposed methodology includes localization of OD center, followed by elimination of vascular structure using vessel-ness filter. Finally, an active contour model was applied to boundary OD segmentation. The results are compared with a ground truth image from the ophthalmologist. The source retinal image for performing this work is obtained from the publicly available DRIVE and MESSIDOR database. This method offers a successful segmentation of OD which may help in diagnosis of various retinal abnormalities.