Zhao Qingyu, Honnorat Nicolas, Adeli Ehsan, Pohl Kilian M
Stanford University.
SRI International.
Inf Process Med Imaging. 2019 Jun;11492:867-879. doi: 10.1007/978-3-030-20351-1_68. Epub 2019 May 22.
Resting-state functional connectivity states are often identified as clusters of dynamic connectivity patterns. However, existing clustering approaches do not distinguish major states from rarely occurring minor states and hence are sensitive to noise. To address this issue, we propose to model major states using a non-linear generative process guided by a Gaussian-mixture distribution in a low-dimensional latent space, while separately modeling the connectivity patterns of minor states by a non-informative uniform distribution. We embed this truncated Gaussian-Mixture model in a Variational Autoencoder framework to obtain a general joint clustering and outlier detection approach, tGM-VAE. When applied to synthetic data with known ground-truth, tGM-VAE is more accurate in clustering connectivity patterns than existing approaches. On the rs-fMRI of 593 healthy adolescents, tGM-VAE identifies meaningful major connectivity states. The dwell time of these states significantly correlates with age.
静息态功能连接状态通常被识别为动态连接模式的聚类。然而，现有的聚类方法无法区分主要状态和罕见的次要状态，因此对噪声敏感。为了解决这个问题，我们建议在低维潜在空间中使用由高斯混合分布引导的非线性生成过程对主要状态进行建模，同时通过非信息性均匀分布分别对次要状态的连接模式进行建模。我们将这个截断的高斯混合模型嵌入到变分自编码器框架中，以获得一种通用的联合聚类和异常值检测方法，即tGM-VAE。当应用于具有已知真实情况的合成数据时，tGM-VAE在聚类连接模式方面比现有方法更准确。在593名健康青少年的静息态功能磁共振成像数据上，tGM-VAE识别出有意义的主要连接状态。这些状态的停留时间与年龄显著相关。
