Hu Shunbo, Wei Lifang, Gao Yaozong, Guo Yanrong, Wu Guorong, Shen Dinggang
School of Information, Linyi University, Linyi, 276005, China.
Department of Radiology and BRIC, University of North Carolina, Chapel Hill, NC, 27599, USA.
Med Phys. 2017 Jan;44(1):158-170. doi: 10.1002/mp.12007.
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 (a) large anatomical changes due to fast brain development and (b) 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 (a) one model learning the relationship between local image appearance (of one development phase) and its displacement toward the template (of another development phase) and (b) 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.
许多脑发育研究致力于探究生命第一年中大脑动态的结构和功能变化。为了在这个动态时期定量测量大脑发育，对于年龄差距可能较大的不同婴儿受试者进行精确的图像配准有很高的要求。尽管已经针对年轻和老年大脑图像提出了许多先进的图像配准方法，但由于（a）大脑快速发育导致的巨大解剖结构变化以及（b）白质髓鞘化引起的动态外观变化，很少有配准方法适用于生命第一年获取的婴儿脑图像。
为了解决这两个难题，我们提出一种基于学习的配准方法，不仅要对齐解剖结构，还要通过利用回归森林预测初始位移向量和外观变化，来减轻任意两张婴儿磁共振图像（年龄差距大）之间的外观差异。具体而言，在训练阶段，分别训练两个回归模型，（a）一个模型学习（一个发育阶段的）局部图像外观与其向（另一个发育阶段的）模板的位移之间的关系，（b）另一个模型学习两个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配准到模板，我们首先通过两个学习到的回归模型预测其体素级位移和外观变化。由于这样的初始化可以减轻新婴儿图像与模板之间显著的外观和形状差异，所以很容易仅使用传统的配准方法来优化剩余的配准。
我们将所提出的配准方法应用于对齐24名婴儿受试者在五个不同时间点（即2周龄、3月龄、6月龄、9月龄和12月龄）的图像，与先进的配准方法相比，取得了更准确、更稳健的配准结果。
所提出的基于学习的配准方法解决了婴儿脑图像配准这一具有挑战性的任务，并且与其他同类配准方法相比，实现了更高的配准精度。
