Marked point process for vascular tree extraction on angiogram

This paper presents a two-step algorithm to perform automatic extraction of vessel tree on angiogram. Firstly, the approximate vessel centerline is modeled as marked point process with each point denoting a line segment. A Double Area prior model is proposed to incorporate the geometrical and topological constraints of segments through potentials on the interaction and the type of segments. Data likelihood allows for the vesselness of the points which the segment covers, which is computed through the Hessian matrix of the image convolved with 2-D Gaussian filter at multiple scales. Optimization is realized by simulated annealing scheme using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm. Secondly, the extracted approximate vessel centerline, containing global geometry shape as well as location information of vessel, is used as important guide to explore the accurate vessel edges by combination with local gradient information of angiogram. This is implemented by morphological homotopy modification and watershed transform on the original gradient image. Experimental results of clinical digitized coronary angiogram are reported.