Multimodal fusion of multiple rest fMRI networks and MRI gray matter via parallel multilink joint ICA reveals highly significant function/structure coupling in Alzheimer's disease.
Multimodal fusion of multiple rest fMRI networks and MRI gray matter via parallel multilink joint ICA reveals highly significant function/structure coupling in Alzheimer's disease.
复制标题
通过并行多链路联合伊卡对多个静息fMRI网络和MRI灰质进行多模态融合，揭示了阿尔茨海默病中高度显著的功能/结构耦合。
DOI：
10.1002/hbm.26456
复制
发表时间：
2023-10-15
影响因子：
4.8
通讯作者：
Calhoun, Vince D.
中科院分区：
文献类型：
--
作者：
Khalilullah, K. M. Ibrahim;Agcaoglu, Oktay;Sui, Jing;Adali, Tulay;Duda, Marlena;Calhoun, Vince D.
关键词：
在本文中，我们重点评估结构磁共振成像 (sMRI) 灰质 (GM) 和多功能磁共振成像 (fMRI) 内在连接网络 (ICN) 之间的联合关系。为了实现这一目标，我们提出了一种多链路联合独立分量分析（ml-jICA）方法，使用与 jICA 相同的核心算法。为了放宽 jICA 假设，我们提出了另一种扩展，称为并行多链路 jICA (pml-jICA)，它允许在 ml-jICA/jICA 上实现更平衡的权重分配。我们假设 sMRI 和 fMRI 模式共享一个混合矩阵，同时允许使用不同的混合矩阵将 sMRI 数据链接到不同的 ICN。我们引入该模型，然后应用这种方法来研究阿尔茨海默病 (AD) 患者与对照组的静息 fMRI 和 sMRI 数据的差异。 pml-jICA 的结果产生显着差异，效应大小较大，包括默认模式网络重叠部分的区域，以及海马和丘脑。重要的是，我们确定了两个具有部分重叠区域的关节组件，它们对 AD 与对照组显示出相反的效果，但由于与不同的功能和结构模式相关，因此能够分离。这凸显了我们的方法和多模式融合方法的独特优势，通常可以揭示单模式方法可能会错过的大脑疾病的潜在生物标志物。这些结果代表了第一个在多模式数据融合模型中将多个 fMRI ICN 与 GM 组件联系起来的工作，并挑战了大脑结构比 fMRI 对 AD 更敏感的典型观点。在本文中，我们提出了一种多模态融合方法，使用多链路联合独立分量分析 (jICA) 来进行多个休息功能磁共振成像 (fMRI) 网络和 MRI 灰质之间的联合分析。这项研究有几个新颖的方面，包括多个休息fMRI网络和灰质之间的联合关系、jICA参数的交替学习等。结果显示阿尔茨海默病和对照之间的联合耦合存在显着差异。
In this article, we focus on estimating the joint relationship between structural magnetic resonance imaging (sMRI) gray matter (GM), and multiple functional MRI (fMRI) intrinsic connectivity networks (ICNs). To achieve this, we propose a multilink joint independent component analysis (ml‐jICA) method using the same core algorithm as jICA. To relax the jICA assumption, we propose another extension called parallel multilink jICA (pml‐jICA) that allows for a more balanced weight distribution over ml‐jICA/jICA. We assume a shared mixing matrix for both the sMRI and fMRI modalities, while allowing for different mixing matrices linking the sMRI data to the different ICNs. We introduce the model and then apply this approach to study the differences in resting fMRI and sMRI data from patients with Alzheimer's disease (AD) versus controls. The results of the pml‐jICA yield significant differences with large effect sizes that include regions in overlapping portions of default mode network, and also hippocampus and thalamus. Importantly, we identify two joint components with partially overlapping regions which show opposite effects for AD versus controls, but were able to be separated due to being linked to distinct functional and structural patterns. This highlights the unique strength of our approach and multimodal fusion approaches generally in revealing potentially biomarkers of brain disorders that would likely be missed by a unimodal approach. These results represent the first work linking multiple fMRI ICNs to GM components within a multimodal data fusion model and challenges the typical view that brain structure is more sensitive to AD than fMRI. In this article, we proposed a multimodal fusion approach for joint analysis between multiple rest functional magnetic resonance imaging (fMRI) networks and MRI gray matter using multilink joint independent component analysis (jICA). There are several novel aspects of this study including joint relationship between multiple rest fMRI networks and gray matter, alternating learning of jICA parameters, etc. Results show significant differences in joint coupling between Alzheimer's disease and controls.
登录
查看更多内容
DOI：
10.1093/brain/awac285
发表时间：
2022-11-21
期刊：
Brain : a journal of neurology
影响因子：
--
作者：
通讯作者：
--
NeuroMark：基于自动化和自适应 ICA 的管道，用于识别脑部疾病的可重复功能磁共振成像标记。
DOI：
10.1016/j.nicl.2020.102375
发表时间：
2020
期刊：
NeuroImage. Clinical
影响因子：
--
作者：
Du Y;Fu Z;Sui J;Gao S;Xing Y;Lin D;Salman M;Abrol A;Rahaman MA;Chen J;Hong LE;Kochunov P;Osuch EA;Calhoun VD;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
影响因子：
3
作者：
Du W;Levin-Schwartz Y;Fu GS;Ma S;Calhoun VD;Adalı T
通讯作者：
Adalı T
影响因子：
5.7
作者：
Calhoun VD;Liu J;Adali T
通讯作者：
Adali T
影响因子：
4.8
作者：
Lee PL;Chou KH;Chung CP;Lai TH;Zhou JH;Wang PN;Lin CP
通讯作者：
Lin CP