In this paper a procedure is described for deformable boundary detection of medical tools, called stents, in angiographic images. A stent is a surgical stainless steel coil which is placed in the artery in order to improve blood circulation, in regions where a stenosis has appeared. Assuming initially a set of 3-D models of stents and using perspective projection of various deformations of the 3-D model of the stent, a large set of synthetic 2D images of stents is constructed. These synthetic images are then used as a training set for deriving a multivariate Gaussian density estimate based on eigenspace decomposition and formulating a Maximum-Likelihood estimation framework in order to reach an initial rough estimate for automatic object recognition. The silhouette of the detected stent is then refined by using a 2D active contour (snake) algorithm integrated with a novel iterative initialization technique which takes into consideration the geometry of the stent. The algorithm is experimentally evaluated using real angiographic images containing stents.