Graph-based guide-wire segmentation through fusion of contrast-enhanced and fluoroscopic images

In this paper, we present a novel method that fuses, through a graph matching, segmentation of the blood vessels in contrast-enhanced images with segmentation of the guide-wires in the fluoroscopic images. This is achieved through a bottom up approach that first extracts local geometric primitives of interest in both images. Fusion between two graphs built with these primitives is performed through spectral matching and allows the definition of an improved criterion of ordering of the wire primitives. Given such criterion, local ordering is used towards reconstruction of multiple curvilinear structures that inherit visual support from both images. An evaluation performed on a broad variety of clinical situations validates the effectiveness of our approach.