Group Replicator Dynamics: A Novel Group-Wise Evolutionary Approach for Sparse Brain Network Detection
Group Replicator Dynamics: A Novel Group-Wise Evolutionary Approach for Sparse Brain Network Detection
复制标题
DOI：
10.1109/tmi.2011.2173699
复制
发表时间：
2012-03-01
影响因子：
10.6
通讯作者：
Abugharbieh, Rafeef
中科院分区：
文献类型：
--
作者：
Bernard Ng;McKeown, Martin J.;Abugharbieh, Rafeef
功能性磁共振成像（fMRI）越来越多地用于研究大脑的功能整合。然而，功能连接的受试者间差异很大，特别是在疾病人群中，使得代表性群体网络的检测具有挑战性。在本文中，我们提出了一种新的技术，“组复制动力学”（GRD），用于检测稀疏功能的大脑网络，是共同的一组科目。我们扩展的复制动力学（RD）的方法，我们证明是一个解决方案的非负稀疏主成分分析问题，通过将组信息集成到每个主题的RD过程。我们所提出的策略有效地哄所有科目的网络向集团的共同网络。这导致稀疏网络包括跨受试者的相同大脑区域，但具有所识别的大脑区域的受试者特定权重。因此，与传统的平均方法相比，GRD能够对受试者间的变异性进行建模，这有助于统计组推断。GRD对合成数据的定量验证表明，与标准方法相比，GRD具有上级网络检测性能。当应用于真实的功能磁共振成像数据时，GRD检测到的任务特定网络与先前的神经科学知识非常一致。
Functional magnetic resonance imaging (fMRI) is increasingly used for studying functional integration of the brain. However, large inter-subject variability in functional connectivity, particularly in disease populations, renders detection of representative group networks challenging. In this paper, we propose a novel technique, "group replicator dynamics" (GRD), for detecting sparse functional brain networks that are common across a group of subjects. We extend the replicator dynamics (RD) approach, which we show to be a solution of the nonnegative sparse principal component analysis problem, by integrating group information into each subject's RD process. Our proposed strategy effectively coaxes all subjects' networks to evolve towards the common network of the group. This results in sparse networks comprising the same brain regions across subjects yet with subject-specific weightings of the identified brain regions. Thus, in contrast to traditional averaging approaches, GRD enables inter-subject variability to be modeled, which facilitates statistical group inference. Quantitative validation of GRD on synthetic data demonstrated superior network detection performance over standard methods. When applied to real fMRI data, GRD detected task-specific networks that conform well to prior neuroscience knowledge.