一种用于在体积显微CT图像中分割小鼠脾脏和滤泡的三维水平集方法。

A 3D level sets method for segmenting the mouse spleen and follicles in volumetric microCT images.

作者信息

Price Jeffrey R, Aykac Deniz, Wall Jonathan

机构信息

Image Science & Machine Vision Group, Oak Ridge National Laboratory, TN, USA.

出版信息

Conf Proc IEEE Eng Med Biol Soc. 2006;2006:2332-6. doi: 10.1109/IEMBS.2006.260127.

DOI:10.1109/IEMBS.2006.260127

PMID:17945708

Abstract

We present a semi-automatic, 3D approach for segmenting the mouse spleen, and its interior follicles, in volumetric microCT imagery. Based upon previous 2D level sets work, we develop a fully 3D implementation and provide the corresponding finite difference formulas. We incorporate statistical and proximity weighting schemes to improve segmentation performance. We also note an issue with the original algorithm and propose a solution that proves beneficial in our experiments. Experimental results are provided for artificial and real data.

摘要

我们提出了一种半自动的三维方法，用于在体积微计算机断层扫描（microCT）图像中分割小鼠脾脏及其内部滤泡。基于先前的二维水平集工作，我们开发了一个完全三维的实现方法，并提供了相应的有限差分公式。我们纳入了统计和邻近加权方案以提高分割性能。我们还指出了原始算法存在的一个问题，并提出了一种在我们的实验中被证明是有益的解决方案。提供了针对人工数据和真实数据的实验结果。