Glocker Ben, Komodakis Nikos, Navab Nassir, Tziritas Georgios, Paragios Nikos
Laboratoire MAS, Ecole Centrale Paris, Chatenay-Malabry, France.
Inf Process Med Imaging. 2009;21:540-51. doi: 10.1007/978-3-642-02498-6_45.
In this paper we propose a novel approach to define task-driven regularization constraints in deformable image registration using learned deformation priors. Our method consists of representing deformation through a set of control points and an interpolation strategy. Then, using a training set of images and the corresponding deformations we seek for a weakly connected graph on the control points where edges define the prior knowledge on the deformation. This graph is obtained using a clustering technique which models the co-dependencies between the displacements of the control points. The resulting classification is used to encode regularization constraints through connections between cluster centers and cluster elements. Additionally, the global structure of the deformation is encoded through a fully connected graph on the cluster centers. Then, registration of a new pair of images consists of displacing the set of control points where on top of conventional image correspondence costs, we introduce costs that are based on the relative deformation of two control points with respect to the learned deformation. The resulting paradigm is implemented using a discrete Markov Random Field which is optimized using efficient linear programming. Promising experimental results on synthetic and real data demonstrate the potential of our approach.
在本文中，我们提出了一种新颖的方法，用于在使用学习到的变形先验的可变形图像配准中定义任务驱动的正则化约束。我们的方法包括通过一组控制点和一种插值策略来表示变形。然后，利用一组训练图像及其相应的变形，我们在控制点上寻找一个弱连接图，其中边定义了关于变形的先验知识。该图是通过一种聚类技术获得的，该技术对控制点位移之间的共依赖性进行建模。所得分类用于通过聚类中心与聚类元素之间的连接来编码正则化约束。此外，变形的全局结构通过聚类中心上的完全连接图进行编码。然后，一对新图像的配准包括移动控制点集，在传统图像对应成本之上，我们引入基于两个控制点相对于学习到的变形的相对变形的成本。所得范式使用离散马尔可夫随机场实现，并通过高效的线性规划进行优化。在合成数据和真实数据上取得的有前景的实验结果证明了我们方法的潜力。
