Uncovering shape signatures of resting-state functional connectivity by geometric deep learning on Riemannian manifold.
Uncovering shape signatures of resting-state functional connectivity by geometric deep learning on Riemannian manifold.
复制标题
DOI：
10.1002/hbm.25897
复制
发表时间：
2022-09
影响因子：
4.8
通讯作者：
Wu, Guorong
中科院分区：
文献类型：
--
作者：
Dan, Tingting;Huang, Zhuobin;Cai, Hongmin;Lyday, Robert G.;Laurienti, Paul J.;Wu, Guorong
关键词：
功能性神经活动表现出几何模式，这一点可以通过功能性连接（FC）的网络拓扑结构的演变来证明，即使在静息状态下。在这项工作中，我们提出了一种新的基于流形的功能性脑网络几何神经网络（简称“Geo‐ Net 4 Net”），以学习黎曼流形上静息态脑网络的内在低维特征表示。这个工具使我们能够回答FC的自发波动如何支持行为和认知的科学问题。我们部署了一组正映射和校正线性单元（ReLU）层，以利用相关矩阵的对称正定（SPD）形式来揭示黎曼流形上功能性大脑网络的内在低维特征表示。由于在静息状态下缺乏定义良好的基础事实，现有的基于学习的方法仅限于无监督方法。为了超越这一边界，我们建议通过利用在底层静息状态之前和之后发生的基于任务的对应物来自我监督静息状态功能网络的特征表征学习。有了这个额外的启发式算法，我们的Geo‐ Net 4 Net允许我们通过捕获几何模式（aka.光谱/形状签名）与黎曼流形上的静止状态相关联。我们对来自人类连接组项目（HCP）数据库的模拟数据和基于任务的功能性共振磁成像（fMRI）数据进行了广泛的实验，我们的Geo‐ Net 4 Net不仅比其他最先进的对应方法实现了更准确的变化检测结果，而且还产生了普遍存在的几何模式，表明了对大脑功能的假定见解。在黎曼流形上学习静息态脑网络的低维特征签名。捕捉静息状态下进化功能波动的几何模式。提出了FC的自发波动如何支持行为和认知的问题。
Functional neural activities manifest geometric patterns, as evidenced by the evolving network topology of functional connectivities (FC) even in the resting state. In this work, we propose a novel manifold‐based geometric neural network for functional brain networks (called “Geo‐Net4Net” for short) to learn the intrinsic low‐dimensional feature representations of resting‐state brain networks on the Riemannian manifold. This tool allows us to answer the scientific question of how the spontaneous fluctuation of FC supports behavior and cognition. We deploy a set of positive maps and rectified linear unit (ReLU) layers to uncover the intrinsic low‐dimensional feature representations of functional brain networks on the Riemannian manifold taking advantage of the symmetric positive‐definite (SPD) form of the correlation matrices. Due to the lack of well‐defined ground truth in the resting state, existing learning‐based methods are limited to unsupervised methodologies. To go beyond this boundary, we propose to self‐supervise the feature representation learning of resting‐state functional networks by leveraging the task‐based counterparts occurring before and after the underlying resting state. With this extra heuristic, our Geo‐Net4Net allows us to establish a more reasonable understanding of resting‐state FCs by capturing the geometric patterns (aka. spectral/shape signature) associated with resting states on the Riemannian manifold. We have conducted extensive experiments on both simulated data and task‐based functional resonance magnetic imaging (fMRI) data from the Human Connectome Project (HCP) database, where our Geo‐Net4Net not only achieves more accurate change detection results than other state‐of‐the‐art counterpart methods but also yields ubiquitous geometric patterns that manifest putative insights into brain function. Learning low‐dimensional feature signatures of resting‐state brain network on Riemannian manifold. Capturing the geometric patterns manifested in evolving functional fluctuations in resting state. Answering the question of how the spontaneous fluctuation of FC supports behavior and cognition.
登录
查看更多内容
影响因子：
4.8
作者：
Gao S;Mishne G;Scheinost D
通讯作者：
Scheinost D
影响因子：
3.7
作者：
Allen, Elena A.;Damaraju, Eswar;Calhoun, Vince D.
通讯作者：
Calhoun, Vince D.
来自静止状态fMRI的大规模稀疏功能网络。
影响因子：
5.7
作者：
Li H;Satterthwaite TD;Fan Y
通讯作者：
Fan Y
睡眠剥夺对工作记忆的影响：背注意，默认模式和额叶网络之间的功能连通性变化。
影响因子：
2.9
作者：
Dai C;Zhang Y;Cai X;Peng Z;Zhang L;Shao Y;Wang C
通讯作者：
Wang C
影响因子：
5.7
作者：
Hutchison RM;Womelsdorf T;Allen EA;Bandettini PA;Calhoun VD;Corbetta M;Della Penna S;Duyn JH;Glover GH;Gonzalez-Castillo J;Handwerker DA;Keilholz S;Kiviniemi V;Leopold DA;de Pasquale F;Sporns O;Walter M;Chang C
通讯作者：
Chang C