Automatic multi-resolution shape modeling of multi-organ structures.
Automatic multi-resolution shape modeling of multi-organ structures.
复制标题
DOI：
10.1016/j.media.2015.04.003
复制
发表时间：
2015-10
影响因子：
10.9
通讯作者：
Linguraru MG
中科院分区：
文献类型：
--
作者：
Cerrolaza JJ;Reyes M;Summers RM;González-Ballester MÁ;Linguraru MG
点分布模型 (PDM) 是最流行的形状描述技术之一，其实用性已在各种医学成像应用中得到证明。然而，为了充分表征底层建模群体，必须拥有具有代表性的训练样本数量，但这并不总是可能的。随着建模结构复杂性的增加，这个问题尤其重要，多个 3D 器官的整体建模是最具挑战性的案例之一。在本文中，我们在多器官分析的背景下引入了一种新的通用多分辨率 PDM（GEM-PDM），能够有效地表征不同的对象间关系，以及每个对象分别的特定位置。重要的是，与以前的方法不同，由于这里提出了一种新的聚集地标聚类方法，该算法的配置是自动化的，该方法同样允许我们识别器官内较小的解剖学上重要的区域。与之前的两种方法（PDM 和分层 PDM）相比，GEM-PDM 方法在形状建模准确性和对噪声的鲁棒性方面具有显着优势，已在两个不同的多器官组数据库（六个皮质下脑结构和七个腹部器官）中得到成功验证。最后，我们建议将新的形状建模框架集成到基于主动形状模型的分割算法中。当应用于 3D 脑部 MRI 分割时，生成的算法（名为 GEMA）比所测试的两种经典方法（ASM 和分层 ASM）提供了更好的整体性能。
Point Distribution Models (PDM) are among the most popular shape description techniques and their usefulness has been demonstrated in a wide variety of medical imaging applications. However, to adequately characterize the underlying modeled population it is essential to have a representative number of training samples, which is not always possible. This problem is especially relevant as the complexity of the modeled structure increases, being the modeling of ensembles of multiple 3D organs one of the most challenging cases. In this paper, we introduce a new GEneralized Multi-resolution PDM (GEM-PDM) in the context of multi-organ analysis able to efficiently characterize the different inter-object relations, as well as the particular locality of each object separately. Importantly, unlike previous approaches, the configuration of the algorithm is automated thanks to a new agglomerative landmark clustering method proposed here, which equally allows us to identify smaller anatomically significant regions within organs. The sig-nificant advantage of the GEM-PDM method over two previous approaches (PDM and hierarchical PDM) in terms of shape modeling accuracy and robustness to noise, has been successfully verified for two different databases of sets of multiple organs: six subcortical brain structures, and seven abdominal organs. Finally, we propose the integration of the new shape modeling framework into an active shape-model-based segmentation algorithm. The resulting algorithm, named GEMA, provides a better overall performance than the two classical approaches tested, ASM, and hierarchical ASM, when applied to the segmentation of 3D brain MRI.
登录
查看更多内容
影响因子：
6.2
作者：
Praun, E;Hoppe, H
通讯作者：
Hoppe, H
影响因子：
10.9
作者：
Rajamani, Kumar T.;Styner, Martin A.;Ballester, Miguel A. Gonzalez
通讯作者：
Ballester, Miguel A. Gonzalez
DOI：
10.1109/tbme.2013.2271383
发表时间：
2013-11
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Islam A;Reza SM;Iftekharuddin KM
通讯作者：
Iftekharuddin KM
影响因子：
4.7
作者：
Hamarneh, G;Gustavsson, T
通讯作者：
Gustavsson, T
影响因子：
10.9
作者：
Gonzalez Ballester, MA;Zisserman, AP;Brady, M
通讯作者：
Brady, M