Zhang Hua, Zeng Weiming, Li Ying, Deng Jin, Wei Boyang
Shanghai Maritime University, Shanghai 201306, China.
Shanghai Institute of Technology, Shanghai 201418, China.
Comput Methods Programs Biomed. 2025 Mar;260:108573. doi: 10.1016/j.cmpb.2024.108573. Epub 2025 Jan 2.
Inferring large-scale brain networks from functional magnetic resonance imaging (fMRI) provides more detailed and richer connectivity information, which is critical for gaining insight into brain structure and function and for predicting clinical phenotypes. However, as the number of network nodes increases, most existing methods suffer from the following limitations: (1) Traditional shallow models often struggle to estimate large-scale brain networks. (2) Existing deep graph structure learning models rely on downstream tasks and labels. (3) They rely on sparse postprocessing operations. To overcome these limitations, this paper proposes a novel framework for revealing large-scale functional brain connectivity networks through graph contrastive structure learning, called BGCSL.
Unlike traditional supervised graph structure learning methods, this framework does not rely on labeled information. It consists of two important modules: sparse graph structure learner and graph contrastive learning (GCL). It employs dynamic augmentation in GCL to train a sparse graph structure learner, enabling it to capture the intrinsic structure of the data.
We conducted extensive experiments on 12 synthetic datasets and 2 public functional magnetic resonance imaging datasets, demonstrating the effectiveness of our proposed framework. In the synthetic datasets, particularly in cases where node features are insufficient, BGCSL still maintains state-of-the-art performance. More importantly, on the ABIDE-I and HCP-rest datasets, BGCSL improved the downstream task performance of GCN-based models, including the original GCN, dGCN, and ContrastPool, to varying degrees.
Our proposed method holds significant potential as a valuable reference for future large-scale brain network estimation and representation and is conducive to supporting the exploration of more fine-grained biomarkers.
从功能磁共振成像（fMRI）推断大规模脑网络可提供更详细、更丰富的连接信息，这对于深入了解脑结构与功能以及预测临床表型至关重要。然而，随着网络节点数量的增加，大多数现有方法存在以下局限性：（1）传统浅层模型往往难以估计大规模脑网络。（2）现有的深度图结构学习模型依赖于下游任务和标签。（3）它们依赖于稀疏后处理操作。为克服这些局限性，本文提出一种通过图对比结构学习揭示大规模功能性脑连接网络的新颖框架，称为BGCSL。
与传统的监督图结构学习方法不同，该框架不依赖标记信息。它由两个重要模块组成：稀疏图结构学习器和图对比学习（GCL）。它在GCL中采用动态增强来训练稀疏图结构学习器，使其能够捕获数据的内在结构。
我们在12个合成数据集和2个公开的功能磁共振成像数据集上进行了广泛实验，证明了我们提出的框架的有效性。在合成数据集中，特别是在节点特征不足的情况下，BGCSL仍保持领先性能。更重要的是，在ABIDE-I和HCP-rest数据集上，BGCSL在不同程度上提高了基于GCN的模型（包括原始GCN、dGCN和ContrastPool）的下游任务性能。
我们提出的方法作为未来大规模脑网络估计和表示的有价值参考具有巨大潜力，有利于支持对更细粒度生物标志物的探索。
