A new 3D parametric intensity model for accurate segmentation and quantification of human vessels

Abstract

We introduce an approach for 3D segmentation and quantification of vessels. The approach is based on a new 3D cylindrical parametric intensity model, which is directly fit to the image intensities through an incremental process based on a Kalman filter. The model has been successfully applied to segment vessels from 3D MRA images. Our experiments show that the model yields superior results in estimating the vessel radius compared to approaches based on a Gaussian model. Also, we point out general limitations in estimating the radius of thin vessels. © Springer-Verlag Berlin Heidelberg 2004.