期望最大化框架下具有非平稳组织类别分布的解剖学引导分割
ANATOMICAL GUIDED SEGMENTATION WITH NON-STATIONARY TISSUE CLASS DISTRIBUTIONS IN AN EXPECTATION-MAXIMIZATION FRAMEWORK.
作者信息
Pohl Kilian M, Bouix Sylvain, Kikinis Ron, Grimson W Eric L
机构信息
Artificial Intelligence Laboratory, MIT, Cambridge MA, USA.
Surgical Planning Laboratory, Harvard Medical School, Boston, MA, USA.
出版信息
Proc IEEE Int Symp Biomed Imaging. 2004 Apr;2004:81-84. doi: 10.1109/ISBI.2004.1398479. Epub 2005 Mar 7.
High quality segmentation of brain MR images is a challenging task. To deal with this problem many automatic segmentation methods rely on atlas information of anatomical structures. We further investigate this line of research by introducing hierarchical representations of anatomical structures in an Expectation-Maximization framework. This new approach enables us to divide a complex segmentation scenario into less difficult sub-problems reducing the scenario's statistical complexity. We demonstrate the method's strength by segmenting a set of brain MR images into 31 different anatomical structures as well as comparing it to other methods.
高质量的脑部磁共振图像分割是一项具有挑战性的任务。为解决这一问题，许多自动分割方法依赖于解剖结构的图谱信息。我们通过在期望最大化框架中引入解剖结构的层次表示，进一步研究了这一研究方向。这种新方法使我们能够将复杂的分割场景分解为难度较小的子问题，从而降低场景的统计复杂性。我们通过将一组脑部磁共振图像分割为31种不同的解剖结构，并与其他方法进行比较，证明了该方法的优势。
Zotero 插件