Isotropic Total Variation Regularization of Displacements in Parametric Image Registration
Isotropic Total Variation Regularization of Displacements in Parametric Image Registration
复制标题
DOI：
10.1109/tmi.2016.2610583
复制
发表时间：
2017-02-01
影响因子：
10.6
通讯作者：
Goksel, Orcun
中科院分区：
文献类型：
--
作者：
Vishnevskiy, Valery;Gass, Tobias;Goksel, Orcun
空间正则化是图像配准中的关键问题，是一个不适定问题。正则化可以帮助避免物理上不可信的位移场和优化过程中的局部极小值。Tikhonov正则化(平方L(2)范数)不能正确地表示非光滑位移场，例如，在呼吸过程中，可能发生在图像时间序列中胸腹部滑动界面上的非光滑位移场。本文采用各向同性总变分(TV)正则化方法，实现了此类界面附近的精确配准。我们进一步发展了参数位移场的TV正则化，并利用交替方向乘子法(ADMM)提供了一种有效的数值求解方案。该方法被成功地应用于四个临床数据库，包括CT肺和MR肝脏图像，捕捉呼吸运动。它提供了整个卷的准确配准结果。我们提出的方法的一个关键优点是它不依赖于器官面具，而许多算法通常需要器官面具来避免滑动界面上的错误。此外，我们的方法对参数选择是健壮的，允许对所有测试的数据库使用相同的参数。我们的方法的平均目标配准误差(TrE)优于文献中的其他方法(10%到40%)。它在公开可用的呼吸运动数据库(DIR 4D CT的平均tres为0.95 mm，DIR COPDgene的平均tres为0.96 mm，POPI数据库的平均tres为0.91 mm)上提供亚像素精度的精确运动量化和滑动检测。
Spatial regularization is essential in image registration, which is an ill-posed problem. Regularization can help to avoid both physically implausible displacement fields and local minima during optimization. Tikhonov regularization (squared l(2)-norm) is unable to correctly represent non-smooth displacement fields, that can, for example, occur at sliding interfaces in the thorax and abdomen in image time-series during respiration. In this paper, isotropic Total Variation (TV) regularization is used to enable accurate registration near such interfaces. We further develop the TV-regularization for parametric displacement fields and provide an efficient numerical solution scheme using the Alternating Directions Method of Multipliers (ADMM). The proposed method was successfully applied to four clinical databases which capture breathing motion, including CT lung and MR liver images. It provided accurate registration results for the whole volume. A key strength of our proposed method is that it does not depend on organ masks that are conventionally required by many algorithms to avoid errors at sliding interfaces. Furthermore, our method is robust to parameter selection, allowing the use of the same parameters for all tested databases. The average target registration error (TRE) of our method is superior (10% to 40%) to other techniques in the literature. It provides precise motion quantification and sliding detection with sub-pixel accuracy on the publicly available breathing motion databases (mean TREs of 0.95 mm for DIR 4D CT, 0.96 mm for DIR COPDgene, 0.91 mm for POPI databases).