当前位置:
X-MOL 学术
›
Inform. Fusion
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Depression recognition using high-order generalized multilayer brain functional network fused with EEG multi-domain information
Information Fusion ( IF 14.7 ) Pub Date : 2024-09-30 , DOI: 10.1016/j.inffus.2024.102723 Shanshan Qu, Dixin Wang, Chang Yan, Na Chu, Zhigang Li, Gang Luo, Huayu Chen, Xuesong Liu, Xuan Zhang, Qunxi Dong, Xiaowei Li, Shuting Sun, Bin Hu
Information Fusion ( IF 14.7 ) Pub Date : 2024-09-30 , DOI: 10.1016/j.inffus.2024.102723 Shanshan Qu, Dixin Wang, Chang Yan, Na Chu, Zhigang Li, Gang Luo, Huayu Chen, Xuesong Liu, Xuan Zhang, Qunxi Dong, Xiaowei Li, Shuting Sun, Bin Hu
Major Depressive Disorder (MDD) is a serious and highly heterogeneous psychological disorder. According to the network hypothesis, depression originates from abnormal neural network information processing, typically resulting in aberrant changes in the topological structure of the brain’s functional network. Recent evidence further reveals that depression involves dynamic changes related to both within- and cross-frequency coupling. Therefore, we utilize second-order tensor expansion to integrate frequency- and time-varying multilayer brain functional networks based on node sharing, thus propose a generalized multilayer brain functional network (GMBFN) incorporating multi-domain information. Concurrently, we derive global and local topological properties from both the frequency and temporal domains to characterize the novel network structure. To uncover more reliable biomarkers and explore various coupling features that can assess the interaction between signals from different perspectives, we conduct research in two datasets employing four sets of within- and cross-frequency coupling. Leveraging the novel multi-domain high-order GMBFNs, abnormalities of information integration abilities in patients with MDD are observed, particularly in the theta-band and overall temporal-domain. Through the fusion of topological properties across both domains with multiple classifiers, the alpha-band can serve as a potential biomarker for depression identification. More importantly, the combination of global topological properties from both domains, on average, enhances the classification performance for identifying patients with MDD by 5.18% compared to using just one domain. This study presents a systematic framework for comprehending the aberrant mechanisms of MDD from multiple perspectives, offering significant value for clinical applications aimed at assisting in depression diagnosis and intervention.
中文翻译:
使用融合脑电多域信息的高阶广义多层脑功能网络进行抑郁识别
重度抑郁症 (MDD) 是一种严重且高度异质的心理障碍。根据网络假说,抑郁症源于异常的神经网络信息处理,通常会导致大脑功能网络拓扑结构的异常变化。最近的证据进一步表明,抑郁症涉及与内频耦合和交叉频耦合相关的动态变化。因此,我们利用二阶张量扩展来整合基于节点共享的频变和时变多层脑功能网络,从而提出了一种包含多域信息的广义多层脑功能网络 (GMBFN)。同时,我们从频率域和时间域推导出全局和局部拓扑属性,以表征新的网络结构。为了发现更可靠的生物标志物并探索可以从不同角度评估信号之间相互作用的各种耦合特征,我们在两个数据集中进行了研究,采用了四组内频耦合和交叉频耦合。利用新的多域高阶 GMBFN,观察到 MDD 患者信息整合能力的异常,特别是在 θ 带和整个颞域。通过将两个域的拓扑特性与多个分类器融合,α 波段可以作为抑郁症识别的潜在生物标志物。更重要的是,与仅使用一个域相比,来自两个域的全局拓扑特性的组合平均将识别 MDD 患者的分类性能提高了 5.18%。 本研究提出了一个从多个角度理解 MDD 异常机制的系统框架,为旨在协助抑郁症诊断和干预的临床应用提供了重要价值。
更新日期:2024-09-30
中文翻译:
使用融合脑电多域信息的高阶广义多层脑功能网络进行抑郁识别
重度抑郁症 (MDD) 是一种严重且高度异质的心理障碍。根据网络假说,抑郁症源于异常的神经网络信息处理,通常会导致大脑功能网络拓扑结构的异常变化。最近的证据进一步表明,抑郁症涉及与内频耦合和交叉频耦合相关的动态变化。因此,我们利用二阶张量扩展来整合基于节点共享的频变和时变多层脑功能网络,从而提出了一种包含多域信息的广义多层脑功能网络 (GMBFN)。同时,我们从频率域和时间域推导出全局和局部拓扑属性,以表征新的网络结构。为了发现更可靠的生物标志物并探索可以从不同角度评估信号之间相互作用的各种耦合特征,我们在两个数据集中进行了研究,采用了四组内频耦合和交叉频耦合。利用新的多域高阶 GMBFN,观察到 MDD 患者信息整合能力的异常,特别是在 θ 带和整个颞域。通过将两个域的拓扑特性与多个分类器融合,α 波段可以作为抑郁症识别的潜在生物标志物。更重要的是,与仅使用一个域相比,来自两个域的全局拓扑特性的组合平均将识别 MDD 患者的分类性能提高了 5.18%。 本研究提出了一个从多个角度理解 MDD 异常机制的系统框架,为旨在协助抑郁症诊断和干预的临床应用提供了重要价值。