Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.
Neuropsychiatry Imaging Center, Department of Radiology, Shenzhen Kangning Hospital, Shenzhen Mental Health Center, Shenzhen, China.
J Affect Disord. 2024 Nov 1;364:266-273. doi: 10.1016/j.jad.2024.08.014. Epub 2024 Aug 11.
Functional connectivity has been shown to fluctuate over time. The present study aimed to identifying major depressive disorders (MDD) with dynamic functional connectivity (dFC) from resting-state fMRI data, which would be helpful to produce tools of early depression diagnosis and enhance our understanding of depressive etiology.
The resting-state fMRI data of 178 subjects were collected, including 89 MDD and 89 healthy controls. We propose a spatio-temporal learning and explaining framework for dFC analysis. A yet effective spatio-temporal model is developed to classifying MDD from healthy controls with dFCs. The model is a stacking neural network model, which learns network structure information by a multi-layer perceptron based spatial encoder, and learns time-varying patterns by a Transformer based temporal encoder. We propose to explain the spatio-temporal model with a two-stage explanation method of importance feature extracting and disorder-relevant pattern exploring. The layer-wise relevance propagation (LRP) method is introduced to extract the most relevant input features in the model, and the attention mechanism with LRP is applied to extract the important time steps of dFCs. The disorder-relevant functional connections, brain regions, and brain states in the model are further explored and identified.
We achieved the best classification performance in identifying MDD from healthy controls with dFC data. The top important functional connectivity, brain regions, and dynamic states closely related to MDD have been identified.
The data preprocessing may affect the classification performance of the model, and this study needs further validation in a larger patient population.
The experimental results demonstrate that the proposed spatio-temporal model could effectively classify MDD, and uncover structural and temporal patterns of dFCs in depression.
功能连接在时间上是波动的。本研究旨在从静息态 fMRI 数据中识别出主要抑郁障碍（MDD）的动态功能连接（dFC），这将有助于产生早期抑郁诊断的工具，并增强我们对抑郁病因的理解。
采集了 178 名受试者的静息态 fMRI 数据，包括 89 名 MDD 和 89 名健康对照者。我们提出了一种用于 dFC 分析的时空学习和解释框架。我们开发了一个有效的时空模型，通过 dFC 将 MDD 从健康对照组分类。该模型是一个堆叠神经网络模型，通过基于多层感知机的空间编码器学习网络结构信息，通过基于 Transformer 的时间编码器学习时变模式。我们提出了一种两阶段的解释方法，通过重要特征提取和紊乱相关模式探索来解释时空模型。引入层间相关性传播（LRP）方法提取模型中最相关的输入特征，应用具有 LRP 的注意力机制提取 dFC 的重要时间步。进一步探索和识别模型中与紊乱相关的功能连接、脑区和脑状态。
我们在使用 dFC 数据识别 MDD 与健康对照组方面取得了最佳的分类性能。确定了与 MDD 密切相关的最重要的功能连接、脑区和动态状态。
数据预处理可能会影响模型的分类性能，本研究需要在更大的患者群体中进一步验证。
实验结果表明，所提出的时空模型可以有效地对 MDD 进行分类，并揭示了抑郁中 dFC 的结构和时间模式。
