Segmentation of perivascular spaces in 7T MR image using auto-context model with orientation-normalized features.
Segmentation of perivascular spaces in 7T MR image using auto-context model with orientation-normalized features.
复制标题
DOI：
10.1016/j.neuroimage.2016.03.076
复制
发表时间：
2016-07-01
期刊：
影响因子：
5.7
通讯作者：
Shen D
中科院分区：
文献类型：
--
作者：
Park SH;Zong X;Gao Y;Lin W;Shen D
脑磁共振（MR）图像中血管周围空间（PVS）的定量研究对于了解脑淋巴系统及其与神经系统疾病的关系非常重要。主要挑战之一是在三维 (3D) MR 图像中准确提取具有不同方向的非常薄的管状结构的 PVS。在本文中，我们提出了一种基于学习的 PVS 分割方法来应对这一挑战。具体来说，我们首先通过使用大脑解剖结构和从图像导数的特征值导出的血管信息来确定感兴趣区域（ROI）。然后，在 ROI 中，我们提取许多随机 Haar 特征，这些特征相对于底层图像导数的主方向进行归一化。分类器采用随机森林模型进行训练，可以有效地学习判别特征和分类器参数，以最大化信息增益。最后，使用顺序学习策略进一步将细管状结构周围的各种上下文模式强化到分类器中。为了进行评估，我们将我们提出的方法应用于从 17 名年龄从 25 岁到 37 岁的健康受试者扫描的 7T 大脑 MR 图像。性能通过体素分割精度、聚类分类精度以及几何属性的相似性（例如预测和真实 PVS 之间的体积、长度和直径分布）来衡量。此外，还对具有运动伪影和缺陷的模拟图像进行了准确性评估，以证明我们的方法在从老年人和患者群体中分割 PVS 方面的潜力。实验结果表明，我们提出的方法优于所有现有的 PVS 分割方法。
Quantitative study of perivascular spaces (PVSs) in brain magnetic resonance (MR) images is important for understanding the brain lymphatic system and its relationship with neurological diseases. One of major challenges is the accurate extraction of PVSs that have very thin tubular structures with various directions in three-dimensional (3D) MR images. In this paper, we propose a learning-based PVS segmentation method to address this challenge. Specifically, we first determine a region of interest (ROI) by using the anatomical brain structure and the vesselness information derived from eigenvalues of image derivatives. Then, in the ROI, we extract a number of randomized Haar features which are normalized with respect to the principal directions of the underlying image derivatives. The classifier is trained by the random forest model that can effectively learn both discriminative features and classifier parameters to maximize the information gain. Finally, a sequential learning strategy is used to further enforce various contextual patterns around the thin tubular structures into the classifier. For evaluation, we apply our proposed method to the 7T brain MR images scanned from 17 healthy subjects aged from 25 to 37. The performance is measured by voxel-wise segmentation accuracy, cluster- wise classification accuracy, and similarity of geometric properties, such as volume, length, and diameter distributions between the predicted and the true PVSs. Moreover, the accuracies are also evaluated on the simulation images with motion artifacts and lacunes to demonstrate the potential of our method in segmenting PVSs from elderly and patient populations. The experimental results show that our proposed method outperforms all existing PVS segmentation methods.