Neuroscience Research Institute, Suwon University, 17, Wauangil, Bongdam-eup, Hwaseong-si, Gyeonggi-do, South Korea.
Depart of Neurosurgery, School of Medicine Gachon University, Incheon, South Korea.
J Neurosci Methods. 2019 Sep 1;325:108361. doi: 10.1016/j.jneumeth.2019.108361. Epub 2019 Jul 20.
MR tractography from diffusion tensor imaging provides a non-invasive way to explore white matter pathways in the human brain. However, a challenge to extracting reliable anatomical information from these data is the use of reliable and effective clustering methodologies. In this paper, we implemented a new version of a robust unsupervised clustering method from MR tractography data using the density-based spatial clustering of applications with noise (DBSCAN) algorithm.
Conventional DBSCAN clustering methods for MR tractography data use each fiber's start and end point as well as the distance between start and end points. Instead, in this study, we extracted and used a fiber-distance matrix generated for all fiber combinations from the tractography dataset in DBSCAN clustering. The two DBSCAN parameters-minimum point number and maximum radius of the neighborhood-were selected according to the value generated with the cluster stability index (CSI).
Performing the proposed CSI-optimized DBSCAN-based clustering method on MR tractography data of the superior longitudinal fasciculus generated 6 robust, non-overlapping, clusters that are neuroanatomically related.
Conventional DBSCAN-based clustering methods have intrinsic error potential in the clustering results due to deviations in fiber shape and fiber location. The proposed method did not exhibit clustering error caused by deviation in fiber trajectory or fiber location.
We implemented a new, robust DBSCAN-based fiber clustering method for MR tractography data. The CSI-optimized DBSCAN-based unsupervised clustering is applicable to investigation of the neuroconnectome and the fiber structure of the brain.
磁共振弥散张量成像的轨迹追踪提供了一种无创的方法来探索人类大脑中的白质通路。然而，从这些数据中提取可靠的解剖学信息的一个挑战是使用可靠和有效的聚类方法。在本文中，我们使用基于密度的空间聚类应用噪声（DBSCAN）算法实现了一种从磁共振轨迹追踪数据中提取可靠的无监督聚类方法的新版本。
常规的磁共振轨迹追踪数据的 DBSCAN 聚类方法使用每条纤维的起点和终点以及起点和终点之间的距离。相反，在本研究中，我们从轨迹追踪数据集中提取并使用了在 DBSCAN 聚类中为所有纤维组合生成的纤维距离矩阵。两个 DBSCAN 参数-最小点数和邻域的最大半径-根据聚类稳定性指数（CSI）生成的值进行选择。
对上纵束的磁共振轨迹追踪数据执行基于 CSI 优化的 DBSCAN 聚类方法，生成了 6 个稳健、不重叠的与神经解剖学相关的聚类。
基于常规 DBSCAN 的聚类方法由于纤维形状和纤维位置的偏差，在聚类结果中存在固有误差潜力。所提出的方法没有表现出由于纤维轨迹或纤维位置的偏差而导致的聚类错误。
我们实现了一种新的、稳健的基于 DBSCAN 的磁共振轨迹追踪数据纤维聚类方法。CSI 优化的基于 DBSCAN 的无监督聚类适用于神经连接组和大脑纤维结构的研究。
