Han Dong, Gao Yaozong, Wu Guorong, Yap Pew-Thian, Shen Dinggang
Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA; Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea.
Comput Med Imaging Graph. 2015 Dec;46 Pt 3(0 3):277-90. doi: 10.1016/j.compmedimag.2015.09.002. Epub 2015 Sep 25.
Comparison of human brain MR images is often challenged by large inter-subject structural variability. To determine correspondences between MR brain images, most existing methods typically perform a local neighborhood search, based on certain morphological features. They are limited in two aspects: (1) pre-defined morphological features often have limited power in characterizing brain structures, thus leading to inaccurate correspondence detection, and (2) correspondence matching is often restricted within local small neighborhoods and fails to cater to images with large anatomical difference. To address these limitations, we propose a novel method to detect distinctive landmarks for effective correspondence matching. Specifically, we first annotate a group of landmarks in a large set of training MR brain images. Then, we use regression forest to simultaneously learn (1) the optimal sets of features to best characterize each landmark and (2) the non-linear mappings from the local patch appearances of image points to their 3D displacements towards each landmark. The learned regression forests are used as landmark detectors to predict the locations of these landmarks in new images. Because each detector is learned based on features that best distinguish the landmark from other points and also landmark detection is performed in the entire image domain, our method can address the limitations in conventional methods. The deformation field estimated based on the alignment of these detected landmarks can then be used as initialization for image registration. Experimental results show that our method is capable of providing good initialization even for the images with large deformation difference, thus improving registration accuracy.
人脑磁共振图像的比较常常受到个体间巨大结构变异性的挑战。为了确定磁共振脑图像之间的对应关系，大多数现有方法通常基于某些形态特征进行局部邻域搜索。它们在两个方面存在局限性：（1）预定义的形态特征在表征脑结构方面的能力往往有限，从而导致对应关系检测不准确；（2）对应匹配通常局限于局部小邻域内，无法适应解剖差异较大的图像。为了解决这些局限性，我们提出了一种新颖的方法来检测独特的地标以进行有效的对应匹配。具体而言，我们首先在大量训练磁共振脑图像中标记一组地标。然后，我们使用回归森林同时学习：（1）最能表征每个地标的最优特征集；（2）从图像点的局部补丁外观到其朝向每个地标3D位移的非线性映射。所学习的回归森林用作地标检测器，以预测新图像中这些地标的位置。由于每个检测器是基于最能将地标与其他点区分开的特征进行学习的，并且地标检测是在整个图像域中进行的，因此我们的方法可以解决传统方法中的局限性。基于这些检测到的地标对齐估计的变形场随后可用于图像配准的初始化。实验结果表明，即使对于变形差异较大的图像，我们的方法也能够提供良好的初始化，从而提高配准精度。
