Hong Yi, Golland Polina, Zhang Miaomiao
Computer Science Department, University of Georgia, Athens, USA.
Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, USA.
Med Image Comput Comput Assist Interv. 2017 Sep;10433:317-325. doi: 10.1007/978-3-319-66182-7_37. Epub 2017 Sep 4.
Geodesic regression on images enables studies of brain development and degeneration, disease progression, and tumor growth. The high-dimensional nature of image data presents significant computational challenges for the current regression approaches and prohibits large scale studies. In this paper, we present a fast geodesic regression method that dramatically decreases the computational cost of the inference procedure while maintaining prediction accuracy. We employ an efficient low dimensional representation of diffeomorphic transformations derived from the image data and characterize the regressed trajectory in the space of diffeomorphisms by its initial conditions, i.e., an initial image template and an initial velocity field computed as a weighted average of pairwise diffeomorphic image registration results. This construction is achieved by using a first-order approximation of pairwise distances between images. We demonstrate the efficiency of our model on a set of 3D brain MRI scans from the OASIS dataset and show that it is dramatically faster than the state-of-the-art regression methods while producing equally good regression results on the large subject cohort.
图像上的测地线回归能够用于研究大脑发育与退化、疾病进展以及肿瘤生长。图像数据的高维特性给当前的回归方法带来了重大的计算挑战，并且阻碍了大规模研究。在本文中，我们提出了一种快速测地线回归方法，该方法在保持预测准确性的同时，显著降低了推理过程的计算成本。我们采用了一种从图像数据中导出的微分同胚变换的高效低维表示，并通过其初始条件，即在微分同胚空间中作为成对微分同胚图像配准结果的加权平均值计算得到的初始图像模板和初始速度场，来表征回归轨迹。这种构建是通过使用图像之间成对距离的一阶近似来实现的。我们在一组来自OASIS数据集的3D脑部MRI扫描图像上展示了我们模型的效率，并表明它比当前最先进的回归方法快得多，同时在大型受试者队列上产生同样良好的回归结果。
