Segmentation of VesselLike Patterns Using Mathematical Morphology and Curvature Evaluation.pdfVIP

1010 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 10, NO.7, JULY 2001 Segmentation of Vessel-Like Patterns Using Mathematical Morphology and Curvature Evaluation Frédéric Zana and Jean-Claude Klein Abstract— This paper presents an algorithm based on mathe- fundus images, the detection of the vascular tree seems a nat- matical morphology and curvature evaluation for the detection of ural approach to the registration problem. Vessels are the only vessel-like patterns in a noisy environment. Such patterns are very features that are common to every image of the retina. This is common in medical images. Vessel detection is interesting for the computation of parameters related to blood flow. Its tree-like ge- particularly true for angiographic images, since the signal comes ometry makes it a usable feature for registration between images from a dye injection. that can be of a different nature. In order to define vessel-like pat- In this paper, we present an algorithm that combines Mor- terns, segmentation will be performed with respect to a precise phological filters and cross-curvature evaluation to segment model. We define a vessel as a bright pattern, piece-wise connected, vessel-like patterns. Its application to images from retinal and locally linear. Mathematical Morphology is very well adapted to this description, however other patterns fit such a morpholog- angiographies has been briefly presented in [9]. We study ical description. In order to differentiate vessels from analogous the behavior of this algorithm on a wider set of angiographic background patterns, a cross-curvature evaluation is performed. images an