Multi-view manifold learning of human brain-state trajectories
Multi-view manifold learning of human brain-state trajectories
复制标题
DOI：
10.1038/s43588-023-00419-0
复制
发表时间：
2023-03-27
期刊：
影响因子：
--
通讯作者：
Turk-Browne, Nicholas B.
中科院分区：
文献类型：
--
作者：
Busch, Erica L.;Huang, Jessie;Turk-Browne, Nicholas B.
人类大脑的复杂性给人一种错觉，认为大脑活动本质上是高维的。非线性降维方法，如均匀流形近似和t分布随机邻居嵌入已被用于高通量生物医学数据。然而，它们还没有被广泛用于大脑活动数据，如功能性磁共振成像（fMRI），主要是由于它们无法保持动态结构。在这里，我们介绍了一个非线性流形学习方法的时间序列数据，包括那些从fMRI称为时间势的热扩散的亲和基过渡嵌入（T-PHATE）。除了从时间序列数据中恢复低维内在流形几何形状外，T-PHATE还利用数据的自相关结构来忠实地去噪和揭示动态轨迹。我们在三个fMRI数据集上对T-PHATE进行了经验验证，结果表明，相对于其他几个最先进的降维基准，它大大提高了数据的可视化、分类和分割。这些改进表明T-PHATE在其他时间扩散过程的高维数据集上具有潜在的应用价值。T-PHATE应用于大脑数据（功能性磁共振成像），它忠实地消除信号噪声，并揭示与认知处理相对应的潜在大脑状态轨迹。
The complexity of the human brain gives the illusion that brain activity is intrinsically high-dimensional. Nonlinear dimensionality-reduction methods such as uniform manifold approximation and t-distributed stochastic neighbor embedding have been used for high-throughput biomedical data. However, they have not been used extensively for brain activity data such as those from functional magnetic resonance imaging (fMRI), primarily due to their inability to maintain dynamic structure. Here we introduce a nonlinear manifold learning method for time-series data-including those from fMRI-called temporal potential of heat-diffusion for affinity-based transition embedding (T-PHATE). In addition to recovering a low-dimensional intrinsic manifold geometry from time-series data, T-PHATE exploits the data's autocorrelative structure to faithfully denoise and unveil dynamic trajectories. We empirically validate T-PHATE on three fMRI datasets, showing that it greatly improves data visualization, classification, and segmentation of the data relative to several other state-of-the-art dimensionality-reduction benchmarks. These improvements suggest many potential applications of T-PHATE to other high-dimensional datasets of temporally diffuse processes.A manifold learning method called T-PHATE is developed for high-dimensional time-series data. T-PHATE is applied to brain data (functional magnetic resonance imaging) where it faithfully denoises signals and unveils latent brain-state trajectories which correspond with cognitive processing.