Learning-based deformable image registration for infant MR images in the first year of life.
Learning-based deformable image registration for infant MR images in the first year of life.
复制标题
通过将随机森林与自动上下文模型相结合，进行基于学习的婴儿 MRI 变形配准
DOI：
10.1002/mp.12007
复制
发表时间：
2017-01
期刊：
影响因子：
3.8
通讯作者：
Shen D
中科院分区：
文献类型：
--
作者：
Hu S;Wei L;Gao Y;Guo Y;Wu G;Shen D
许多脑发育研究致力于研究生命第一年的动态结构和功能变化。为了定量地测量在这样一个动态时期的大脑发育，准确的图像配准不同的婴儿科目可能有很大的年龄差距是很高的要求。尽管已经针对年轻和老年脑图像提出了许多最先进的图像配准方法，但是很少有配准方法适用于在生命的第一年中获取的婴儿脑图像，这是因为（1）由于快速脑发育而导致的大的解剖学变化和（2）由于白色物质髓鞘形成而导致的动态外观变化。为了解决这两个困难，我们提出了一种基于学习的配准方法，不仅对齐的解剖结构，但也减轻了两个任意的婴儿MR图像（具有较大的年龄差距）之间的外观差异，通过利用回归森林来预测初始位移矢量和外观变化。具体地，在训练阶段，分别训练两个回归模型，其中（1）一个模型学习（一个发育阶段的）局部图像外观与其朝向（另一个发育阶段的）模板的位移之间的关系，以及（2）另一个模型学习两个大脑发育阶段之间的局部外观变化。然后，在测试阶段，为了将新的婴儿图像注册到模板，我们首先通过两个学习的回归模型预测其体素位移和外观变化。由于这样的初始化可以减轻新婴儿图像和模板之间的显著外观和形状差异，因此很容易仅使用传统的配准方法来细化剩余的配准。我们应用我们提出的配准方法在五个不同的时间点（即，2周龄、3月龄、6月龄、9月龄和12月龄），并且与最先进的配准方法相比，实现更准确和鲁棒的配准结果。所提出的基于学习的配准方法解决了具有挑战性的任务，注册婴儿大脑图像，并实现了更高的配准精度相比，其他同行的配准方法。
Many brain development studies have been devoted to investigate dynamic structural and functional changes in the first year of life. To quantitatively measure brain development in such a dynamic period, accurate image registration for different infant subjects with possible large age gap is of high demand. Although many state-of-the-art image registration methods have been proposed for young and elderly brain images, very few registration methods work for infant brain images acquired in the first year of life, because of (1) large anatomical changes due to fast brain development and (2) dynamic appearance changes due to white matter myelination. To address these two difficulties, we propose a learning-based registration method to not only align the anatomical structures but also alleviate the appearance differences between two arbitrary infant MR images (with large age gap) by leveraging the regression forest to predict both the initial displacement vector and appearance changes. Specifically, in the training stage, two regression models are trained separately, with (1) one model learning the relationship between local image appearance (of one development phase) and its displacement toward the template (of another development phase) and (2) another model learning the local appearance changes between the two brain development phases. Then, in the testing stage, to register a new infant image to the template, we first predict both its voxel-wise displacement and appearance changes by the two learned regression models. Since such initializations can alleviate significant appearance and shape differences between new infant image and the template, it is easy to just use a conventional registration method to refine the remaining registration. We apply our proposed registration method to align 24 infant subjects at five different time points (i.e., 2-week-old, 3-month-old, 6-month-old, 9-month-old, and 12-month-old), and achieve more accurate and robust registration results, compared to the state-of-the-art registration methods. The proposed learning-based registration method addresses the challenging task of registering infant brain images and achieves higher registration accuracy compared with other counterpart registration methods.