A generalized framework for analytic regularization of uniform cubic B-spline displacement fields

A generalized framework for analytic regularization of uniform cubic B-spline displacement fields
复制标题

均匀三次 B 样条位移场解析正则化的通用框架

DOI:
10.1088/2057-1976/abf9e6
复制
发表时间:
2021
影响因子:
1.4
通讯作者:
Sharp, Gregory C
Sharp, Gregory C
中科院分区:
--
文献类型:
--
作者:
Shah, Keyur D;Shackleford, James A;Kandasamy, Nagarajan;Sharp, Gregory C

文献摘要

参考文献

相似文献

图像配准是一个固有的不适定问题,它缺乏被配准的两个图像的体素之间的唯一映射所需的约束。因此,必须使注册正规化,以实现物理上有意义的转换。正则化惩罚通常是位移矢量场的导数的函数,可以通过解析或数值来计算。然而,根据图像大小的不同,数值方法的计算代价很高,因此开发了一种计算效率高的分析框架。利用三次B-样条作为配准变换,建立了一个支持五种不同正则化的数学框架:扩散、曲率、线弹性、三阶和总位移。我们通过将每种方法与其相应的数值方法在精度方面进行比较来验证我们的方法。我们还提供了基准测试结果,表明解析解的运行速度比基于有限差分的数值实现快得多,最高可达两个数量级。
Image registration is an inherently ill-posed problem that lacks the constraints needed for a unique mapping between voxels of the two images being registered. As such, one must regularize the registration to achieve physically meaningful transforms. The regularization penalty is usually a function of derivatives of the displacement-vector field and can be calculated either analytically or numerically. The numerical approach, however, is computationally expensive depending on the image size, and therefore a computationally efficient analytical framework has been developed. Using cubic B-splines as the registration transform, we develop a generalized mathematical framework that supports five distinct regularizers: diffusion, curvature, linear elastic, third-order, and total displacement. We validate our approach by comparing each with its numerical counterpart in terms of accuracy. We also provide benchmarking results showing that the analytic solutions run significantly faster—up to two orders of magnitude—than finite differencing based numerical implementations.
DOI: 10.1007/978-3-319-18461-6
发表时间: 2015
期刊: --
影响因子: --
作者:
Jean-François Aujol;M. Nikolova;N. Papadakis
通讯作者: Jean-François Aujol;M. Nikolova;N. Papadakis
DOI: 10.1073/pnas.90.24.11944
发表时间: 1993-12-15
影响因子: 11.1
作者:
MILLER, MI;CHRISTENSEN, GE;GRENANDER, U
通讯作者: GRENANDER, U
稀疏数字高程模型的各向异性三阶正则化
DOI: --
发表时间: 2013
期刊: Scale Space and Variational Methods in Computer Vision
影响因子: --
作者:
J. Lellmann;J. Morel;C. Schönlieb
通讯作者: C. Schönlieb
DOI: 10.1016/j.ejmp.2017.09.122
发表时间: 2017-10-01
影响因子: 3.4
作者:
Miura, Hideharu;Ozawa, Shuichi;Nagata, Yasushi
通讯作者: Nagata, Yasushi