Modeling the Shape of the Brain Connectome via Deep Neural Networks
Modeling the Shape of the Brain Connectome via Deep Neural Networks
复制标题
DOI：
10.1007/978-3-031-34048-2_23
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Haocheng Dai;M. Bauer;P. Fletcher;S. Joshi
中科院分区：
文献类型：
--
作者：
Haocheng Dai;M. Bauer;P. Fletcher;S. Joshi
扩散加权磁共振成像(DWI)的目标是推断个体受试者大脑在活体内的结构连通性。为了统计研究正常和异常脑连接之间的变异性和差异，需要建立神经连接的数学模型。在本文中，我们将大脑连接体表示为黎曼流形，这允许我们将神经连接建模为测地线。这导致了估计与DWI数据兼容的黎曼度量的挑战性问题，即，使得测地线曲线表示连接的各个纤维束的度量。我们将这一问题归结为求解一组高度非线性的偏微分方程组，并研究了卷积编解码器神经网络(CEDNN)对求解这类几何激励偏微分方程组的适用性。我们的方法在测地线与白质路径的对准方面取得了优异的性能，并解决了以前测地线纤维束成像方法中的一个长期存在的问题：无法恢复高保真的交叉纤维。代码可在https://github.com/aarentai/Metric-Cnn-3D-IPMI.上找到
The goal of diffusion-weighted magnetic resonance imaging (DWI) is to infer the structural connectivity of an individual subject’s brain in vivo. To statistically study the variability and differences between normal and abnormal brain connectomes, a mathematical model of the neural connections is required. In this paper, we represent the brain connectome as a Riemannian manifold, which allows us to model neural connections as geodesics. This leads to the challenging problem of estimating a Riemannian metric that is compatible with the DWI data, i.e., a metric such that the geodesic curves represent individual fiber tracts of the connectomics. We reduce this problem to that of solving a highly nonlinear set of partial differential equations (PDEs) and study the applicability of convolutional encoder-decoder neural networks (CEDNNs) for solving this geometrically motivated PDE. Our method achieves excellent performance in the alignment of geodesics with white matter pathways and tackles a long-standing issue in previous geodesic tractography methods: the inability to recover crossing fibers with high fidelity. Code is available at https://github.com/aarentai/Metric-Cnn-3D-IPMI.