Modularity-Constrained Dynamic Representation Learning for Interpretable Brain Disorder Analysis with Functional MRI.
Modularity-Constrained Dynamic Representation Learning for Interpretable Brain Disorder Analysis with Functional MRI.
复制标题
使用功能 MRI 进行可解释脑疾病分析的模块化约束动态表示学习。
DOI：
10.1007/978-3-031-43907-0_5
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Liu,Mingxia
中科院分区：
文献类型：
--
作者：
Wang,Qianqian;Wu,Mengqi;Fang,Yuqi;Wang,Wei;Qiao,Lishan;Liu,Mingxia
静息态功能磁共振成像（rs-fMRI）越来越多地用于检测由大脑疾病引起的功能连接模式的改变，从而促进大脑病理学的客观量化。现有研究通常使用各种机器/深度学习方法提取功能磁共振成像特征，但生成的成像生物标志物通常难以解释。此外，大脑作为一个具有许多认知/拓扑模块的模块化系统运行，其中每个模块都包含密集互连的感兴趣区域 (ROI) 的子集，这些感兴趣区域与其他模块中的 ROI 稀疏连接。然而，目前的方法无法有效地表征大脑的模块化。本文提出了一种模块化约束动态表示学习 (MDRL) 框架，用于使用 rs-fMRI 进行可解释的脑部疾病分析。 MDRL 由 3 部分组成：(1) 动态图构建，(2) 用于动态特征学习的模块化约束时空图神经网络 (MSGNN)，以及 (3) 预测和生物标志物检测。特别是，MSGNN 旨在学习 fMRI 的时空动态表示，受到 3 个功能模块（即中央执行网络、显着网络和默认模式网络）的约束。为了增强学习特征的判别能力，我们鼓励 MSGNN 重建输入图的网络拓扑。在两个公共数据集和一个私人数据集（总共 1, 155 名受试者）上进行的实验结果证实，我们的 MDRL 在基于功能磁共振成像的脑部疾病分析中优于多种最先进的方法。检测到的功能磁共振成像生物标志物具有良好的可解释性，可用于改善临床诊断。
Resting-state functional MRI (rs-fMRI) is increasingly used to detect altered functional connectivity patterns caused by brain disorders, thereby facilitating objective quantification of brain pathology. Existing studies typically extract fMRI features using various machine/deep learning methods, but the generated imaging biomarkers are often challenging to interpret. Besides, the brain operates as a modular system with many cognitive/topological modules, where each module contains subsets of densely inter-connected regions-of-interest (ROIs) that are sparsely connected to ROIs in other modules. However, current methods cannot effectively characterize brain modularity. This paper proposes a modularity-constrained dynamic representation learning (MDRL) framework for interpretable brain disorder analysis with rs-fMRI. The MDRL consists of 3 parts: (1) dynamic graph construction, (2) modularity-constrained spatiotemporal graph neural network (MSGNN) for dynamic feature learning, and (3) prediction and biomarker detection. In particular, the MSGNN is designed to learn spatiotemporal dynamic representations of fMRI, constrained by 3 functional modules (i.e., central executive network, salience network, and default mode network). To enhance discriminative ability of learned features, we encourage the MSGNN to reconstruct network topology of input graphs. Experimental results on two public and one private datasets with a total of 1, 155 subjects validate that our MDRL outperforms several state-of-the-art methods in fMRI-based brain disorder analysis. The detected fMRI biomarkers have good explainability and can be potentially used to improve clinical diagnosis.