Automatic localization and segmentation of optic disc in fundus image using morphology and level set

Abstract

Optic disc (OD) localization and segmentation are important in developing systems for automated diagnosis of various serious ophthalmic pathologies. This paper presents a new, fast and robust methodology for fully automatic localization and segmentation of the optic disc in fundus images. This methodology locates the OD with a morphological approach based on the combination of vessel convergence and intensity. The boundary of the OD is extracted by using distance regularized narrowband level set evolution (DRLSE). This algorithm has been validated on three public databases. The location procedure has a high success rate of 99.52% in the cases averagely and the segmentation method improves the sensitivity and specificity to 99.92% and 96.49% respectively. The results confirm the superiority of the proposed method over the conventional ways.