Fast center-line extraction for quantification of vessels in confocal microscopy images

In this paper we present a novel method for the 3D centerline extraction of elongated objects such as vessels. This method unites the basic ideas in distance transform-based, thinning, and path planning methods to extract thin and connected centerlines. This fast approach needs no user interaction or any prior knowledge of the object shape. Centerline extraction is the first and most important step towards the quantification of vascular images which is beneficial for research, diagnosis, surgery planning, and therapy. The results confirm the superiority of our proposed method when applied to the complex branching structures of vessels in the confocal microscopy images of a rat brain.