Simultaneous Segmentation and Multiresolution Nonrigid Atlas Registration
Simultaneous Segmentation and Multiresolution Nonrigid Atlas Registration
复制标题
DOI：
10.1109/tip.2014.2322447
复制
发表时间：
2014-07-01
影响因子：
10.6
通讯作者：
Goksel, Orcun
中科院分区：
文献类型：
--
作者：
Gass, Tobias;Szekely, Gabor;Goksel, Orcun
在本文中，提出了一种基于马尔可夫随机场（MRF）的新颖方法，用于分割医学图像，同时非刚性地配准图集。在文献中，分割和配准都得到了广泛的研究。对于涉及两者的应用程序，例如通过基于图集的配准进行分割，早期的研究提出通过提供每个的输出来初始化另一个来迭代地解决这些问题。然而，该方案不能保证手头的组合任务的最佳解决方案，因为这两个单独的问题是分开处理的。在本文中，我们将同时配准和分割（SRS）制定为最大后验（MAP）问题。我们分解生成的概率，以便可以使用 MRF 完成 MAP 推断。采用高效的分层实现，允许从粗到细的配准，同时估计像素级的分割。该方法在两个临床数据集上进行评估：1）3D CT 中的下颌骨分割和 2）脑 MRI 的 2D 中矢状切片中的胼胝体分割。还给出了视频跟踪示例。我们的实现使我们能够直接将所提出的方法与单独的分割/注册以及使用完全相同的势函数的迭代方法进行比较。在留一法评估中，SRS 在两个数据集的骰子重叠和表面距离指标方面展示了更准确的结果。我们还定量地表明，与迭代方法相比，SRS 方法对配准中的错误不太敏感。
In this paper, a novel Markov random field (MRF)-based approach is presented for segmenting medical images while simultaneously registering an atlas nonrigidly. In the literature, both segmentation and registration have been studied extensively. For applications that involve both, such as segmentation via atlas-based registration, earlier studies proposed addressing these problems iteratively by feeding the output of each to initialize the other. This scheme, however, cannot guarantee an optimal solution for the combined task at hand, since these two individual problems are then treated separately. In this paper, we formulate simultaneous registration and segmentation (SRS) as a maximum a-posteriori (MAP) problem. We decompose the resulting probabilities such that the MAP inference can be done using MRFs. An efficient hierarchical implementation is employed, allowing coarse-to-fine registration while estimating segmentation at pixel level. The method is evaluated on two clinical data sets: 1) mandibular bone segmentation in 3D CT and 2) corpus callosum segmentation in 2D midsaggital slices of brain MRI. A video tracking example is also given. Our implementation allows us to directly compare the proposed method with the individual segmentation/registration and the iterative approach using the exact same potential functions. In a leave-one-out evaluation, SRS demonstrated more accurate results in terms of dice overlap and surface distance metrics for both data sets. We also show quantitatively that the SRS method is less sensitive to the errors in the registration as opposed to the iterative approach.