Cooperation of two fuzzy segmentation operators for digital substract angiograms analysts

A computer-based system for the automatic quantification of vascular lesions from 2D renal angiograms should be able to to provide reproducible measurements on visible lesions. This article presents a knowledge based approach for the automatic and reproducible identification of arteries boundaries. The method is based on the cooperation of two fuzzy segmentation operators in order to take into account the natural stepped process of an expert that looks for useful information in the image. The purpose of the first operator is to focus on the region of interest by detecting the bifurcation points between the aorta and the renal arteries. The second operator aims at extracting the artery outlines inside the region of interest. The segmentation process has been applied to real situations and the results obtained are presented.