Zhang Lichi, Wang Qian, Gao Yaozong, Wu Guorong, Shen Dinggang
Med-X Research Institute, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China.
Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 and Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599.
Med Phys. 2016 Mar;43(3):1175-86. doi: 10.1118/1.4941011.
Automatic brain image labeling is highly demanded in the field of medical image analysis. Multiatlas-based approaches are widely used due to their simplicity and robustness in applications. Also, random forest technique is recognized as an efficient method for labeling, although there are several existing limitations. In this paper, the authors intend to address those limitations by proposing a novel framework based on the hierarchical learning of atlas forests.
Their proposed framework aims to train a hierarchy of forests to better correlate voxels in the MR images with their corresponding labels. There are two specific novel strategies for improving brain image labeling. First, different from the conventional ways of using a single level of random forests for brain labeling, the authors design a hierarchical structure to incorporate multiple levels of forests. In particular, each atlas forest in the bottom level is trained in accordance with each individual atlas, and then the bottom-level forests are clustered based on their capabilities in labeling. For each clustered group, the authors retrain a new representative forest in the higher level by using all atlases associated with the lower-level atlas forests in the current group, as well as the tentative label maps yielded from the lower level. This clustering and retraining procedure is conducted iteratively to yield a hierarchical structure of forests. Second, in the testing stage, the authors also present a novel atlas forest selection method to determine an optimal set of atlas forests from the constructed hierarchical structure (by disabling those nonoptimal forests) for accurately labeling the test image.
For validating their proposed framework, the authors evaluate it on the public datasets, including Alzheimer's disease neuroimaging initiative, Internet brain segmentation repository, and LONI LPBA40. The authors compare the results with the conventional approaches. The experiments show that the use of the two novel strategies can significantly improve the labeling performance. Note that when more levels are constructed in the hierarchy, the labeling performance can be further improved, but more computational time will be also required.
The authors have proposed a novel multiatlas-based framework for automatic and accurate labeling of brain anatomies, which can achieve accurate labeling results for MR brain images.
医学图像分析领域对脑图像自动标注有很高的需求。基于多图谱的方法因其在应用中的简单性和稳健性而被广泛使用。此外，随机森林技术虽存在一些现有局限性，但仍被认为是一种有效的标注方法。在本文中，作者旨在通过提出一种基于图谱森林分层学习的新框架来解决这些局限性。
他们提出的框架旨在训练森林层次结构，以便更好地将磁共振图像中的体素与其相应标签关联起来。有两种特定的新颖策略用于改进脑图像标注。首先，与使用单一层级随机森林进行脑标注的传统方法不同，作者设计了一种分层结构来纳入多个层级的森林。具体而言，底层的每个图谱森林根据每个单独的图谱进行训练，然后根据它们的标注能力对底层森林进行聚类。对于每个聚类组，作者使用与当前组中较低层级图谱森林相关联的所有图谱以及较低层级产生的暂定标签图，在较高层级重新训练一个新的代表性森林。这种聚类和重新训练过程迭代进行以产生森林的分层结构。其次，在测试阶段，作者还提出了一种新颖的图谱森林选择方法，从构建的分层结构中确定一组最优的图谱森林（通过禁用那些非最优森林），以准确标注测试图像。
为了验证他们提出的框架，作者在包括阿尔茨海默病神经影像倡议、互联网脑分割库和LONI LPBA40在内的公共数据集上对其进行评估。作者将结果与传统方法进行比较。实验表明，使用这两种新颖策略可以显著提高标注性能。请注意，当在层次结构中构建更多层级时，标注性能可以进一步提高，但也需要更多的计算时间。
作者提出了一种基于多图谱的新颖框架，用于脑解剖结构的自动和准确标注，该框架可以实现磁共振脑图像的准确标注结果。
