A unified approach to fast image registration and a new curvature based registration technique
A unified approach to fast image registration and a new curvature based registration technique
复制标题
DOI：
10.1016/j.laa.2003.10.021
复制
发表时间：
2004-03-15
影响因子：
1.1
通讯作者：
Modersitzki, J
中科院分区：
文献类型：
--
作者：
Fischer, B;Modersitzki, J
图像配准是当今医学成像中许多挑战的核心。它的应用范围很广。这本便条的目的有两个。首先，我们回顾了目前在医学成像中使用的一些最有前途的非线性配准策略。我们证明了所有这些技术都可以用一个变分问题来表述，并且允许统一处理。其次，在变分框架内，我们引入了一个新的基于曲率类型光滑器的非线性配准模型。我们证明了仿射线性变换属于该正则化子的核。结果，该方法变得对预配准步骤的不良初始化更加健壮。此外，我们还给出了一种基于实数离散余弦变换的新方案的稳定和快速实现。我们展示了合成数据集的新技术的优势，并展示了该算法在MR乳腺X光图像配准中的应用。(C)2003 Elsevier Inc.保留所有权利。
Image registration is central to many challenges in medical imaging today. It has a vast range of applications.The purpose of this note is twofold. First, we review some of the most promising non-linear registration strategies currently used in medical imaging. We show that all these techniques may be phrased in terms of a variational problem and allow for a unified treatment.Second, we introduce, within the variational framework, a new non-linear registration model based on a curvature type smoother. We show that affine linear transformations belong to the kernel of this regularizer. As a result, the approach becomes more robust against poor initializations of a pre-registration step. Furthermore, we develop a stable and fast implementation of the new scheme based on a real discrete cosine transformation. We demonstrate the advantages of the new technique for synthetic data sets and present an application of the algorithm for registering MR-mammography images. (C) 2003 Elsevier Inc. All rights reserved.