Bayesian estimation of regularization and atlas building in diffeomorphic image registration.
Bayesian estimation of regularization and atlas building in diffeomorphic image registration.
复制标题
DOI：
10.1007/978-3-642-38868-2_4
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Fletcher PT
中科院分区：
文献类型：
--
作者：
Zhang M;Singh N;Fletcher PT
本文提出了一种用于差射图像配准和图集构建的产生式贝叶斯模型。我们发展了一种同时估计控制微分同胚变换光滑性的参数的atlas估计方法。为此，我们引入了一种蒙特卡罗期望最大化算法，其中期望步长通过微分同胚流形上的哈密顿蒙特卡罗抽样来逼近。这种随机方法的另一个好处是，它可以成功地解决涉及大变形的困难配准问题，其中直接测地线优化失败。利用已知参数的正演模型生成的合成数据，我们证明了我们的模型能够成功地恢复地图集和正则化参数。在三维脑图像的图谱估计问题中，我们也证明了该方法的有效性。
This paper presents a generative Bayesian model for diffeomorphic image registration and atlas building. We develop an atlas estimation procedure that simultaneously estimates the parameters controlling the smoothness of the diffeomorphic transformations. To achieve this, we introduce a Monte Carlo Expectation Maximization algorithm, where the expectation step is approximated via Hamiltonian Monte Carlo sampling on the manifold of diffeomorphics. An added benefit of this stochastic approach is that it can successfully solve difficult registration problems involving large deformations, where direct geodesic optimization fails. Using synthetic data generated from the forward model with known parameters, we demonstrate the ability of our model to successfully recover the atlas and regularization parameters. We also demonstrate the effectiveness of the proposed method in the atlas estimation problem for 3D brain images.