A fuzzy logic approach to drusen detection in retinal angiographic images

Drusen are yellow deposits at the level of the retinal pigment and are frequently associated with age-related macular degeneration (ARMD). Drusen often change in size, number and degree of confluence. A quantitative method to measure the development of drusen is needed for controlled studies of the natural history, prognosis, and tertenant of ARMD. A novel method to detect drusen is presented. This method proceeds in two steps: an optimal partition followed by a fuzzy logic approach. The proposed method is used to quantify objectively drusen over time, it constitutes a diagnosis help tool to the long term follow-up of patients