Finite-Dimensional Lie Algebras for Fast Diffeomorphic Image Registration.
Finite-Dimensional Lie Algebras for Fast Diffeomorphic Image Registration.
复制标题
DOI：
10.1007/978-3-319-19992-4_19
复制
发表时间：
2015-01-01
期刊：
影响因子：
--
通讯作者：
Fletcher, P Thomas
中科院分区：
文献类型：
--
作者：
Zhang, Miaomiao;Fletcher, P Thomas
提出了一种差分图像配准的快速测地线拍摄算法。首先在限带速度场空间上引入了一种新的有限维李代数结构。然后，我们证明该空间可以有效地表示微分同构图像配准的初始速度，其维数比通常使用的低得多，而配准精度几乎没有损失。然后，我们利用这样一个事实，即测地线演化方程以及梯度下降方法所需的伴随Jacobi场方程，可以完全在这个有限维李代数中计算。结果是一种用于大变形度量映射（LDDMM）的测地线拍摄方法，它比最先进的方法快得多，占用的内存也少得多。我们证明了我们的模型在注册3D脑图像方面的有效性，并将其注册精度、运行时间和内存消耗与领先的LDDMM方法进行了比较。我们还展示了我们的算法如何突破了差胚图谱构建的时间和内存要求。
This paper presents a fast geodesic shooting algorithm for diffeomorphic image registration. We first introduce a novel finite-dimensional Lie algebra structure on the space of bandlimited velocity fields. We then show that this space can effectively represent initial velocities for diffeomorphic image registration at much lower dimensions than typically used, with little to no loss in registration accuracy. We then leverage the fact that the geodesic evolution equations, as well as the adjoint Jacobi field equations needed for gradient descent methods, can be computed entirely in this finite-dimensional Lie algebra. The result is a geodesic shooting method for large deformation metric mapping (LDDMM) that is dramatically faster and less memory intensive than state-of-the-art methods. We demonstrate the effectiveness of our model to register 3D brain images and compare its registration accuracy, run-time, and memory consumption with leading LDDMM methods. We also show how our algorithm breaks through the prohibitive time and memory requirements of diffeomorphic atlas building.