Signed graph representation learning for functional-to-structural brain network mapping
Signed graph representation learning for functional-to-structural brain network mapping
复制标题
DOI：
10.1016/j.media.2022.102674
复制
发表时间：
2022-11
影响因子：
10.9
通讯作者：
Haoteng Tang;Lei Guo;Xiyao Fu;Yalin Wang;S. Mackin;O. Ajilore;A. Leow;Paul M. Thompson;Heng Huang;L. Zhan
中科院分区：
文献类型：
--
作者：
Haoteng Tang;Lei Guo;Xiyao Fu;Yalin Wang;S. Mackin;O. Ajilore;A. Leow;Paul M. Thompson;Heng Huang;L. Zhan
MRI衍生的大脑网络已被广泛用于了解大脑区域之间的功能和结构相互作用，以及影响它们的因素，如大脑发育和疾病。大脑网络上的图形挖掘可以促进临床表型和神经退行性疾病的新生物标志物的发现。由于脑功能和结构网络从不同的角度描述了大脑拓扑结构，因此探索结合这些跨模态脑网络的表示具有重要的临床意义。目前大多数研究的目的是提取一个融合的表示投影的结构网络的功能。由于功能网络是动态的，而结构网络是静态的，因此将静态对象映射到动态对象可能不是最佳的。然而，在相反方向上的映射（即，从功能网络到结构网络）都受到了由符号图内的负链接引入的挑战。在这里，我们提出了一种新的图学习框架，称为深度签名脑图挖掘或DSBGM，具有签名图编码器，从相反的角度来看，通过将功能网络投影到结构对应物来学习跨模态表示。我们使用两个独立的公开数据集（HCP和OASIS）验证了我们的临床表型和神经退行性疾病预测任务框架。我们的实验结果清楚地证明了我们的模型相比，几个国家的最先进的方法的优势。
MRI-derived brain networks have been widely used to understand functional and structural interactions among brain regions, and factors that affect them, such as brain development and diseases. Graph mining on brain networks can facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. Since brain functional and structural networks describe the brain topology from different perspectives, exploring a representation that combines these cross-modality brain networks has significant clinical implications. Most current studies aim to extract a fused representation by projecting the structural network to the functional counterpart. Since the functional network is dynamic and the structural network is static, mapping a static object to a dynamic object may not be optimal. However, mapping in the opposite direction (i.e., from functional to structural networks) are suffered from the challenges introduced by negative links within signed graphs. Here, we propose a novel graph learning framework, named as Deep Signed Brain Graph Mining or DSBGM, with a signed graph encoder that, from an opposite perspective, learns the cross-modality representations by projecting the functional network to the structural counterpart. We validate our framework on clinical phenotype and neurodegenerative disease prediction tasks using two independent, publicly available datasets (HCP and OASIS). Our experimental results clearly demonstrate the advantages of our model compared to several state-of-the-art methods.