Flux-maximizing geometric flows for two-dimensional and three-dimensional blood vessel segmentation.

摘要

The visualization of two-dimensional and three-dimensional vascular structures is of significant interest in image-guided surgery. This assists clinicians in pre-operation planning, real-time operating room decision making, and post-operation monitoring. In order to achieve this goal, vascular networks must first be segmented from intensity data such as CT or MR angiography images. A framework for addressing this problem is the use of geometric flows where a curve (in two dimensions) or a surface (in three dimensions) is evolved under constraints from image forces so that it clings to features of interest in an intensity image. Recent variations on this theme take into account properties of enclosed regions and textures and allow for multiple curves or surfaces to be simultaneously represented. However, it is not clear how to apply these techniques to images of low contrast elongated structures, such as blood vessels. To address this problem we derive the gradient flow which maximizes the rate of increase of flux of an auxiliary vector field through a curve or surface. The calculation leads to a simple and elegant interpretation which is essentially parameter free. We illustrate its advantages with level-set based segmentations of 2D and 3D angiography images of blood vessels.