Image analysis of fundus photographs. The detection and measurement of exudates associated with diabetic retinopathy

Abstract

A computer-based image analysis system was used to detect and measure exudates in fundus photographs. A fundus transparency was imaged, digitized, and stored in image memory. The stored image was then processed by several operators, to reduce shade variations in the image background and enhance the contrast between this background and the exudates. Exudates were separated from the background on the basis of their brightness or "gray level" and were then copied in to a binary image. For comparative purposes, the binary image was superimposed on the original unprocessed image. Exudate areas were measured using the binary image, which was also transferred to a printer to provide a permanent record or "exudate map." The system was able to discriminate between standard photographs used to grade hard exudates in the Early Treatment for Diabetic Retinopathy Study (ETDRS). It was also used to monitor the response of a subject to laser treatment.