Image mining in IRIS: Integrated retinal information system

There is an increasing demand for systems that can automatically analyze im ages and extract semantically meaningful information. IRIS, an Integrated R etinal Information system, has been developed to provide medical profession als easy and unified access to the screening, trend and progression of diab etic-related eye diseases in a diabetic patient database. This paper shows how mining techniques can be used to accurately extract features in the ret inal images. In particular, we apply a classification approach to determine the conditions for tortuousity in retinal blood vessels.