Multiple-isovalue selection by clustering gray values of the boundary surfaces within volume image
Lisheng Wang, Pheng‐Ann Heng, Tien‐Tsin Wong, Jing Bai · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2002
In medical visualization, multiple isosurfaces are usually extracted from medical volume image and used to represent (approximate) the boundary surfaces of different structures in the image. In this paper, we will discuss the approximating problem of the boundary surface (contained within volume image) by isosurface. It is quite common that a medical volume image can contain multiple interesting structures; we present a novel approach for the selection of multiple isosurfaces to approximate the boundary surfaces of these multiple structures. With this approach, the discrete sampling points of the gray values of the boundary surfaces within volume image are computed first. Then by identifying appropriate clusters from the discrete sampling points and computing the mean of each cluster, we can determine the corresponding isosurfaces for approximating these multiple boundary surfaces.