Campbell Kristen M, Fletcher P Thomas
Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT.
Shape Med Imaging (2018). 2018 Sep;11167:232-243. doi: 10.1007/978-3-030-04747-4_22. Epub 2018 Nov 23.
We propose a technique for analyzing longitudinal imaging data that models individual changes with diffeomorphic geodesic regression and aggregates these geodesics into a nonparametric group average trend. Our model is specifically tailored to the unbalanced and sparse characteristics of longitudinal imaging studies. That is, each individual has few data points measured over a short period of time, while the study population as a whole spans a wide age range. We use geodesic regression to estimate individual trends, which is an appropriate model for capturing shape changes over a short time window, as is typically found within an individual. Geodesics are also adept at handling the low sample sizes found within individuals, and can model the change between as few as two timepoints. However, geodesics are limited for modeling longer-term trends, where constant velocity may not be appropriate. Therefore, we develop a novel nonparametric regression to aggregate individual trends into an average group trend. We demonstrate the power of our method to capture non-geodesic group trends on hippocampal volume (real-valued data) and diffeomorphic registration of full 3D MRI from the longitudinal OASIS data.
我们提出了一种用于分析纵向成像数据的技术，该技术使用微分同胚测地线回归对个体变化进行建模，并将这些测地线汇总为非参数组平均趋势。我们的模型是专门针对纵向成像研究的不平衡和稀疏特征量身定制的。也就是说，每个个体在短时间内测量的数据点很少，而整个研究人群涵盖了很广的年龄范围。我们使用测地线回归来估计个体趋势，这是一种适合在短时间窗口内捕捉形状变化的模型，就像在个体中通常发现的那样。测地线也擅长处理个体内样本量少的情况，并且可以对少至两个时间点之间的变化进行建模。然而，测地线在建模长期趋势方面存在局限性，因为恒定速度可能不合适。因此，我们开发了一种新颖的非参数回归方法，将个体趋势汇总为平均组趋势。我们展示了我们的方法在从纵向OASIS数据中捕捉海马体积（实值数据）的非测地线组趋势和全三维磁共振成像的微分同胚配准方面的能力。
