In brain network analysis, individual-level data can provide biological features of individuals, while population-level data can provide demographic information of populations. However, existing methods mostly utilize either individual- or population-level features separately, inevitably neglecting the multi-level characteristics of brain disorders. To address this issue, we propose an end-to-end multi-graph neural network model called KMGCN. This model simultaneously leverages individual- and population-level features for brain network analysis. At the individual level, we construct multi-graph using both knowledge-driven and data-driven approaches. Knowledge-driven refers to constructing a knowledge graph based on prior knowledge, while data-driven involves learning a data graph from the data itself. At the population level, we construct multi-graph using both imaging and phenotypic data. Additionally, we devise a pooling method tailored for brain networks, capable of selecting brain regions that impact brain disorders. We evaluate the performance of our model on two large datasets, ADNI and ABIDE, and experimental results demonstrate that it achieves state-of-the-art performance, with 86.87% classification accuracy for ADNI and 86.40% for ABIDE, accompanied by around 10% improvements in all evaluation metrics compared to the state-of-the-art models. Additionally, the biomarkers identified by our model align well with recent neuroscience research, indicating the effectiveness of our model in brain network analysis and potential biomarker discovery. The code is available at https://github.com/GN-gjh/KMGCN.

中文翻译：

---

知识驱动的多图卷积网络，用于脑网络分析和潜在生物标志物发现


在脑网络分析中，个体水平的数据可以提供个体的生物学特征，而种群水平的数据可以提供种群的人口统计信息。然而，现有的方法大多分别利用个体或群体水平的特征，不可避免地忽视了脑部疾病的多层次特征。为了解决这个问题，我们提出了一种称为 KMGCN 的端到端多图神经网络模型。该模型同时利用个体和群体水平的特征进行脑网络分析。在个人层面，我们使用知识驱动和数据驱动的方法来构建多图。知识驱动是指基于先验知识构建知识图谱，而数据驱动涉及从数据本身学习数据图谱。在种群水平上，我们使用成像和表型数据构建多图。此外，我们设计了一种为大脑网络量身定制的池化方法，能够选择影响大脑疾病的大脑区域。我们在 ADNI 和 ABIDE 两个大型数据集上评估了模型的性能，实验结果表明，它实现了最先进的性能，ADNI 的分类准确率为 86.87%，ABIDE 的分类准确率为 86.40%，与最先进的模型相比，所有评估指标都提高了约 10%。此外，我们的模型确定的生物标志物与最近的神经科学研究非常吻合，表明我们的模型在脑网络分析和潜在生物标志物发现方面的有效性。该代码可在 https://github.com/GN-gjh/KMGCN 获取。