Disentangled Sequential Graph Autoencoder for Preclinical Alzheimer’s Disease Characterizations from ADNI Study
Disentangled Sequential Graph Autoencoder for Preclinical Alzheimer’s Disease Characterizations from ADNI Study
复制标题
ADNI 研究中用于临床前阿尔茨海默病特征的解缠结序列图自动编码器
DOI：
10.1007/978-3-030-87196-3_34
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Kim, Won Hwa
中科院分区：
文献类型：
--
作者：
Yang, Fan;Meng, Rui;Cho, Hyuna;Guorong;Kim, Won Hwa
给定在脑网络上定义的群体纵向神经成像测量，利用数据序列内的时间依赖性和在图上定义的对应潜在变量（即，感兴趣区域（ROI）之间的网络编码关系）可以非常有利于表征大脑。这里，重要的是区分时变（例如，纵向测量）和时间不变（例如，性别）成分，分别进行分析。为此，我们提出了一种创新和突破性的解纠缠顺序图自动编码器，它利用顺序变分自动编码器（SVAE），图形卷积和半监督框架一起学习由时变和时不变潜变量组成的潜在空间，以表征整个ROI上测量的解纠缠表示。在解码器中使用监督损失来描述目标信息，使我们能够实现更有效的表示学习，以改进分类。我们验证我们提出的方法上的纵向皮层厚度数据阿尔茨海默病神经影像倡议（ADNI）的研究。我们的方法优于传统技术的基线，证明了有效的纵向数据表示预测标签和纵向数据生成的好处。
Given a population longitudinal neuroimaging measurements defined on a brain network, exploiting temporal dependencies within the sequence of data and corresponding latent variables defined on the graph (i.e., network encoding relationships between regions of interest (ROI)) can highly benefit characterizing the brain. Here, it is important to distinguish time-variant (e.g., longitudinal measures) and time-invariant (e.g., gender) components to analyze them individually. For this, we propose an innovative and ground-breaking Disentangled Sequential Graph Autoencoder which leverages the Sequential Variational Autoencoder (SVAE), graph convolution and semi-supervising framework together to learn a latent space composed of time-variant and time-invariant latent variables to characterize disentangled representation of the measurements over the entire ROIs. Incorporating target information in the decoder with a supervised loss let us achieve more effective representation learning towards improved classification. We validate our proposed method on the longitudinal cortical thickness data from Alzheimer’s Disease Neuroimaging Initiative (ADNI) study. Our method outperforms baselines with traditional techniques demonstrating benefits for effective longitudinal data representation for predicting labels and longitudinal data generation.