Maddah Mahnaz, Zöllei Lilla, Grimson W Eric L, Westin Carl-Fredrik, Wells William M
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
Proc IEEE Int Symp Biomed Imaging. 2008;4543943:105-108. doi: 10.1109/ISBI.2008.4540943.
We propose a Bayesian approach to incorporate anatomical information in the clustering of fiber trajectories. An expectation-maximization (EM) algorithm is used to cluster the trajectories, in which an atlas serves as the prior on the labels. The atlas guides the clustering algorithm and makes the resulting bundles anatomically meaningful. In addition, it provides the seed points for the tractography and initial settings of the EM algorithm. The proposed approach provides a robust and automated tool for tract-oriented analysis both in a single subject and over a population.
我们提出一种贝叶斯方法,将解剖学信息纳入纤维轨迹聚类中。使用期望最大化(EM)算法对轨迹进行聚类,其中图谱用作标签的先验。图谱指导聚类算法,使得到的纤维束在解剖学上具有意义。此外,它为纤维束成像提供种子点和EM算法的初始设置。所提出的方法为单个体和群体的基于纤维束的分析提供了一种强大且自动化的工具。