This paper presents a Particle Filter (PF) framework that stochastically detects and labels vessel bifurca- tions. The PF has previously been utilised in the segmentation of vascular structures, however has not demonstrated a consistent ability to detect and track bifurcations without the aid of user intervention. By incorporating a number of techniques into a specially designed vascular PF, including Markov Chain Monte Carlo (MCMC) rejuvenation and a spatially adaptive likelihood, we show that the simultaneous extraction of vessel centrelines, bifurcations and a hierarchical vascular representation is possible. This algorithm is shown to perform well on both synthetic and clinical data.
CITATION STYLE
Allen, K., Yau, C., & Noble, A. (2008). A Recursive, Stochastic Vessel Segmentation Framework that Robustly Handles Bifurcations. Wiaumanacuk, 1(i), 2–6. Retrieved from http://www2.wiau.man.ac.uk/caws/Conferences/46/proceedings/papers/KAllenMIUAFinal.pdf
Mendeley helps you to discover research relevant for your work.