Sept. 27, 1999 to Sept. 29, 1999
A.M. Mendonça , Universidade do Porto
A.J. Campilho , Universidade do Porto
J.M. Nunes , Servi?o de Oftalmologia do Hospital Geral de Santo Ant?nio
In this paper a method for automatic detection of Micro-aneurysms in digital angiograms of the eye fundus is described. These lesions of the human retina, a characteristic of the earliest phases of diabetic retinopathy, present themselves in the angiographic images as small, round, hyper-fluorescent objects. The proposed method includes initial pre-processing and enhancement steps, followed by object segmentation. In the final phase, micro-aneurysms are validated using two new criteria based on local intensity, contrast and shape relations. The combination of these local features with global image parameters makes possible a high degree of independence from image intensity characteristics.
A.M. Mendonça, A.J. Campilho, J.M. Nunes, "Automatic Segmentation of Microaneurysms in Retinal Angiograms of Diabetic Patients", ICIAP, 1999, Image Analysis and Processing, International Conference on, Image Analysis and Processing, International Conference on 1999, pp. 728, doi:10.1109/ICIAP.1999.797681