Zhang Yizi, Liu Meimei, Zhang Zhengwu, Dunson David
Department of Statistics, Columbia University, New York, NY, United States.
Department of Statistics, Virginia Polytechnic Institute and State University, Blacksburg, VA, United States.
Imaging Neurosci (Camb). 2024 Oct 7;2. doi: 10.1162/imag_a_00303. eCollection 2024.
Mapping of human brain structural connectomes via diffusion magnetic resonance imaging (dMRI) offers a unique opportunity to understand brain structural connectivity and relate it to various human traits, such as cognition. However, head displacement during image acquisition can compromise the accuracy of connectome reconstructions and subsequent inference results. We develop a generative model to learn low-dimensional representations of structural connectomes invariant to motion-induced artifacts, so that we can link brain networks and human traits more accurately, and generate motion-adjusted connectomes. We apply the proposed model to data from the Adolescent Brain Cognitive Development (ABCD) study and the Human Connectome Project (HCP) to investigate how our motion-invariant connectomes facilitate understanding of the brain network and its relationship with cognition. Empirical results demonstrate that the proposed motion-invariant variational autoencoder (inv-VAE) outperforms its competitors in various aspects. In particular, motion-adjusted structural connectomes are more strongly associated with a wide array of cognition-related traits than other approaches without motion adjustment.
通过扩散磁共振成像（dMRI）绘制人类脑结构连接组，为理解脑结构连接性并将其与各种人类特征（如认知）联系起来提供了独特的机会。然而，图像采集过程中的头部位移会影响连接组重建的准确性以及后续的推理结果。我们开发了一种生成模型，以学习对运动诱导伪影具有不变性的结构连接组的低维表示，从而能够更准确地将脑网络与人类特征联系起来，并生成经过运动调整的连接组。我们将所提出的模型应用于青少年大脑认知发展（ABCD）研究和人类连接组计划（HCP）的数据，以研究我们的运动不变连接组如何促进对脑网络及其与认知关系的理解。实证结果表明，所提出的运动不变变分自编码器（inv-VAE）在各个方面都优于其竞争对手。特别是，经过运动调整的结构连接组比其他未进行运动调整的方法与更广泛的认知相关特征有更强的关联。
