Automatic initialization of level set segmentation for application to optic disc margin identification

This paper presents a methodology for automatic initialization of a level-set segmentation algorithm to find the margin of the optic disc in fundus images as an indicator for glaucoma. Accurate segmentation of the optic disc is fundamental to the diagnosis and treatment of glaucoma. Our algorithm improves on previous applications by automatically finding the initialization points for ideal segmentation and more efficient convergence. Our algorithm was evaluated by comparing its output with images manually segmented by glaucoma specialists. Our results produced an average overlap with ground truth of 82%.