论文标题
头部冲击运动学的低排名表示：数据驱动的模拟器
Low-rank representation of head impact kinematics: A data-driven emulator
论文作者
论文摘要
鉴于大多数脑损伤指标使用头运动学作为输入，因此被影响引起的头部运动被认为是脑损伤预测中最重要的措施之一。最近，研究人员专注于使用快速方法，例如机器学习，以实时近似脑损伤诊断。但是，这些需要大量的运动学测量，因此，如果可用的现场测量数据有限，则需要扩大数据。在这项研究中，我们提出了一种基于主要成分分析的方法，该方法模拟了经验的低级别替代头部影响运动学，同时需要低计算成本。在表征我们的537个头部影响的现有数据集（由6个自由度测量）组成时，我们发现只有几种模式，例如15在角速度的情况下，足以准确重建整个数据集。此外，这些模式的频率主要低，因为超过70％至90％的角速度响应可以通过频率低于40Hz的模式来捕获。我们将我们提出的方法与现有影响参数化方法进行了比较，并使用一系列基于运动学的基于基于运动学的指标（例如头部损伤标准和旋转损伤标准（RIC）（RIC）以及脑组织变形 - 量表（例如脑部脑角度指标），例如脑部脑角度指标，最大原理（MPS）和轴突纤维菌株（FS）（FS）。在所有情况下，我们的方法都复制了类似于地面真相测量值的伤害指标，没有显着差异，而现有的方法显着不同（p <0.01）值以及不良的伤害分类敏感性和特异性。该仿真器将使我们能够提供必要的数据增强，以构建任何大小的头部影响运动学数据集。
Head motion induced by impacts has been deemed as one of the most important measures in brain injury prediction, given that the majority of brain injury metrics use head kinematics as input. Recently, researchers have focused on using fast approaches, such as machine learning, to approximate brain deformation in real-time for early brain injury diagnosis. However, those requires large number of kinematic measurements, and therefore data augmentation is required given the limited on-field measured data available. In this study we present a principal component analysis-based method that emulates an empirical low-rank substitution for head impact kinematics, while requiring low computational cost. In characterizing our existing data set of 537 head impacts, consisting of 6 degrees of freedom measurements, we found that only a few modes, e.g. 15 in the case of angular velocity, is sufficient for accurate reconstruction of the entire data set. Furthermore, these modes are predominantly low frequency since over 70% to 90% of the angular velocity response can be captured by modes that have frequencies under 40Hz. We compared our proposed method against existing impact parametrization methods and showed significantly better performance in injury prediction using a range of kinematic-based metrics -- such as head injury criterion and rotational injury criterion (RIC) -- and brain tissue deformation-metrics -- such as brain angle metric, maximum principal strain (MPS) and axonal fiber strains (FS). In all cases, our approach reproduced injury metrics similar to the ground truth measurements with no significant difference, whereas the existing methods obtained significantly different (p<0.01) values as well as poor injury classification sensitivity and specificity. This emulator will enable us to provide the necessary data augmentation to build a head impact kinematic data set of any size.
