Detection of non-perfused zones in retinal images

Abstract

An automatic analysis of angiographic retinal images is discussed. A detection method based on textural differences between perfused and nonperfused regions is described. The image is tessellated into a large number of primary regions using the positions of major vessels. For each region the degree of nonperfusion is estimated by measuring textural properties using mathematical morphology. The image is represented as a region adjacency graph. Adjacent regions are subsequently merged using information on the degree of perfusion. Comparison with manual grading is presented. It is shown that the algorithm for tessellating the image into regions conforms well to the manual delineation of nonperfused regions. The only parameter in the algorithm selects what size of vessels are used for region detection. The features used for grading the images are sensitive enough to detect nonperfused regions.<>