Landmark- and Intensity-Based Registration with Large Deformations via Quasi-conformal Maps
Landmark- and Intensity-Based Registration with Large Deformations via Quasi-conformal Maps
复制标题
DOI：
10.1137/130943406
复制
发表时间：
2014-01-01
影响因子：
2.1
通讯作者：
Lui, Lok Ming
中科院分区：
文献类型：
--
作者：
Lam, Ka Chun;Lui, Lok Ming
我们提出了一种利用拟共形映射的地标和强度信息获得大变形微分同胚配准的新方法。基本思想是最小化包含贝尔特拉米系数项的能量泛函，该系数项测量拟共形映射的畸变。贝尔特拉米系数有效地控制了配准的客观性和平滑性。在本文中，我们首先提出了拟共形地标配准（QCLR）算法来获得图像或表面之间的微分同构（1-1和on）配准。使用QCLR，即使具有较大的几何差异或大量的地标约束，也可以获得图像或表面之间的地标对齐的微分同态。然后将该算法扩展到准保形混合配准（QCHR）算法，该算法将地标和强度（如图像强度或表面曲率）信息相结合，以获得更精确的配准结果。对合成数据和实际数据进行了实验。结果证明了该算法在图像或曲面间差分配准方面的稳定性和有效性。
We present a new approach to obtain diffeomorphic registrations with large deformations using landmark and intensity information via quasi-conformal maps. The basic idea is to minimize an energy functional involving a Beltrami coefficient term, which measures the distortion of the quasi-conformal map. The Beltrami coefficient effectively controls the bijectivity and smoothness of the registration. In this paper, we first propose the quasi-conformal landmark registration (QCLR) algorithm to obtain diffeomorphic (1-1 and onto) registrations between images or surfaces. Using QCLR, landmark-aligned diffeomorphisms between images or surfaces can be obtained, even with a large geometric difference or a large number of landmark constraints. This algorithm is then extended to the quasi-conformal hybrid registration (QCHR) algorithm, which combines landmark and intensity (such as image intensity or surface curvature) information to achieve a more accurate registration result. Experiments have been carried out on both synthetic and real data. Results demonstrate the stability and efficacy of the proposed algorithm to obtain diffeomorphic registrations between images or surfaces.