Multiple Kernel Learning Model for Relating Structural and Functional Connectivity in the Brain.

Multiple Kernel Learning Model for Relating Structural and Functional Connectivity in the Brain.
复制标题

DOI:
10.1038/s41598-018-21456-0
复制
发表时间:
2018-02-19
期刊:
影响因子:
4.6
通讯作者:
Roy D
Roy D
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Surampudi SG;Naik S;Surampudi RB;Jirsa VK;Sharma A;Roy D

文献摘要

参考文献

被引文献

相似文献

认知神经科学中的一个挑战性问题是将结构连接性(SC)与功能连接性(FC)联系起来,以更好地理解人类认知的大规模网络动力学如何从相对固定的SC架构中出现。最近的建模尝试点的可能性,一个单一的扩散内核提供了一个很好的估计FC。我们强调了单扩散核模型(SDK)的缺点,并提出了一个多尺度扩散方案。我们的多尺度模型被表述为一个反应扩散系统,在固定拓扑结构上产生时空模式。我们假设存在区域间的协同激活(潜在参数),联合收割机扩散内核在多个尺度来表征FC如何可能从SC产生。我们制定了一个多核学习(MKL)计划来估计潜在参数的训练数据。我们的模型在分析上易于处理,并且足够复杂,可以捕捉到潜在生物现象的细节。通过MKL模型学习的参数可以以71%的速度从测试数据集中高度准确地预测特定于主题的FC,超过了现有线性和非线性模型的性能。我们提供了一个例子,这些潜在的参数可以用来表征年龄特异性重组的大脑结构和功能。
A challenging problem in cognitive neuroscience is to relate the structural connectivity (SC) to the functional connectivity (FC) to better understand how large-scale network dynamics underlying human cognition emerges from the relatively fixed SC architecture. Recent modeling attempts point to the possibility of a single diffusion kernel giving a good estimate of the FC. We highlight the shortcomings of the single-diffusion-kernel model (SDK) and propose a multi-scale diffusion scheme. Our multi-scale model is formulated as a reaction-diffusion system giving rise to spatio-temporal patterns on a fixed topology. We hypothesize the presence of inter-regional co-activations (latent parameters) that combine diffusion kernels at multiple scales to characterize how FC could arise from SC. We formulated a multiple kernel learning (MKL) scheme to estimate the latent parameters from training data. Our model is analytically tractable and complex enough to capture the details of the underlying biological phenomena. The parameters learned by the MKL model lead to highly accurate predictions of subject-specific FCs from test datasets at a rate of 71%, surpassing the performance of the existing linear and non-linear models. We provide an example of how these latent parameters could be used to characterize age-specific reorganization in the brain structure and function.
DOI: 10.1523/jneurosci.1091-13.2013
发表时间: 2013-07-03
影响因子: 5.3
作者:
Deco, Gustavo;Ponce-Alvarez, Adrian;Corbetta, Maurizio
通讯作者: Corbetta, Maurizio
DOI: 10.1103/physreve.79.051914
发表时间: 2009-05-01
期刊: PHYSICAL REVIEW E
影响因子: 2.4
作者:
Barnett, L.;Buckley, C. L.;Bullock, S.
通讯作者: Bullock, S.
DOI: 10.1371/journal.pcbi.1005543
发表时间: 2017-05-01
影响因子: 4.3
作者:
Hahn, Gerald;Ponce-Alvarez, Adrian;Fregnac, Yves
通讯作者: Fregnac, Yves
DOI: 10.1073/pnas.0901831106
发表时间: 2009-06-23
影响因子: 11.1
作者:
Deco, Gustavo;Jirsa, Viktor;Koetter, Rolf
通讯作者: Koetter, Rolf
DOI: 10.1038/ncomms10340
发表时间: 2016-01-21
影响因子: 16.6
作者:
Atasoy S;Donnelly I;Pearson J
通讯作者: Pearson J