Detection and segmentation of drusen deposits on human retina: potential in the diagnosis of age-related macular degeneration

Abstract

Assessment of the risk for the development of age-related macular degeneration requires reliable detection and quantitative mapping of retinal abnormalities (drusen) that are considered precursors of the disease. In this study, a novel segmentation algorithm is presented for the automatic detection and mapping of drusen images acquired with a digital fundus camera. A modified adaptive histogram equalization, the multilevel histogram equalization scheme for enhancing local intensity structures, was used. For the detection of drusen in retinal images, a novel segmentation technique, histogram-based adaptive local thresholding, was developed. This technique extracts the useful information from an image without being affected by the presence of other structures. Application of this technique showed that drusen have slightly different characteristics from the background. The performance of the algorithm is established through statistical analysis of the results. This analysis indicates that the proposed drusen detector gives reliable detection accuracy in both drusen position and size—Hans E. Grossniklaus