Efficient estimation of 3-dimensional centerlines of inner carotid arteries and their curvature functions by free knot regression splines

Keywords

Statistical learning
Computational Medicine for the Cardiocirculatory System
Code:
23/2007
Title:
Efficient estimation of 3-dimensional centerlines of inner carotid arteries and their curvature functions by free knot regression splines
Date:
Monday 26th November 2007
Author(s):
Sangalli, Laura M.; Secchi, Piercesare; Vantini, Simone; Veneziani, Alessandro
Download link:
Abstract:
This work stems from the need for accurate estimation of the curvature function of an artery, that emerged within ANEURISK Project, a research program that aims at investigating the role of vascular morphology and hemodynamics on the pathogenesis of cerebral aneurysms. We develop here a regression technique that exploits free knot splines in a novel setting, to estimate 3-dimensional curves, and their derivatives. We thoroughly compare this technique to a classical regression method, local polynomial smoothing, showing that 3-dimensional free knot regression splines yield more accurate and efficient estimates.
This report, or a modified version of it, has been also submitted to, or published on
Sangalli, L.M., et al., Efficient estimation of three-dimensional curves and their derivatives by free-knot regression splines, applied to the analysis of inner..., J. of the Royal Statistical Soc. Ser. C, App. Stat., Vol. 58, No. 3, 285-306 (2009)