Hald Ditte Høvenhoff, Henao Ricardo, Winther Ole
DTU Compute B321, Technical University of Denmark, DK-2800 Lyngby, Denmark.
DTU Compute B321, Technical University of Denmark, DK-2800 Lyngby, Denmark; Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA.
Neuroimage. 2017 May 15;152:563-574. doi: 10.1016/j.neuroimage.2017.02.070. Epub 2017 Feb 27.
Functional Magnetic Resonance Imaging (fMRI) gives us a unique insight into the processes of the brain, and opens up for analyzing the functional activation patterns of the underlying sources. Task-inferred supervised learning with restrictive assumptions in the regression set-up, restricts the exploratory nature of the analysis. Fully unsupervised independent component analysis (ICA) algorithms, on the other hand, can struggle to detect clear classifiable components on single-subject data. We attribute this shortcoming to inadequate modeling of the fMRI source signals by failing to incorporate its temporal nature. fMRI source signals, biological stimuli and non-stimuli-related artifacts are all smooth over a time-scale compatible with the sampling time (TR). We therefore propose Gaussian process ICA (GPICA), which facilitates temporal dependency by the use of Gaussian process source priors. On two fMRI data sets with different sampling frequency, we show that the GPICA-inferred temporal components and associated spatial maps allow for a more definite interpretation than standard temporal ICA methods. The temporal structures of the sources are controlled by the covariance of the Gaussian process, specified by a kernel function with an interpretable and controllable temporal length scale parameter. We propose a hierarchical model specification, considering both instantaneous and convolutive mixing, and we infer source spatial maps, temporal patterns and temporal length scale parameters by Markov Chain Monte Carlo. A companion implementation made as a plug-in for SPM can be downloaded from https://github.com/dittehald/GPICA.
功能磁共振成像（fMRI）使我们能够独特地洞察大脑的活动过程，并为分析潜在源的功能激活模式提供了可能。在回归设置中采用具有限制性假设的任务推断监督学习，限制了分析的探索性。另一方面，完全无监督的独立成分分析（ICA）算法在处理单受试者数据时，可能难以检测到清晰可分类的成分。我们将这一缺点归因于未能纳入fMRI源信号的时间特性，从而对其进行了不充分的建模。fMRI源信号、生物刺激和与非刺激相关的伪影在与采样时间（TR）兼容的时间尺度上都是平滑的。因此，我们提出了高斯过程ICA（GPICA），它通过使用高斯过程源先验来促进时间依赖性。在两个具有不同采样频率的fMRI数据集上，我们表明，与标准的时间ICA方法相比，GPICA推断的时间成分和相关的空间图允许更明确的解释。源的时间结构由高斯过程的协方差控制，该协方差由具有可解释和可控时间长度尺度参数的核函数指定。我们提出了一个层次模型规范，同时考虑瞬时混合和卷积混合，并通过马尔可夫链蒙特卡罗推断源空间图、时间模式和时间长度尺度参数。可以从https://github.com/dittehald/GPICA下载作为SPM插件的配套实现。
