A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-based Graph Contrastive Learning

TL;DR

This paper introduces DGCL, a diffusion-based graph contrastive learning method for constructing brain networks that improves consistency, efficiency, and disease prediction accuracy, aiding neuroscience research.

Contribution

The paper presents a novel end-to-end brain network construction pipeline using diffusion processes and graph contrastive learning, enhancing reproducibility and interpretability.

Findings

DGCL outperforms traditional and deep learning methods in disease stage prediction.

The method improves the consistency and efficiency of brain network construction.

DGCL demonstrates potential for disease interpretability in neuroscience.

Abstract

Brain network analysis plays an increasingly important role in studying brain function and the exploring of disease mechanisms. However, existing brain network construction tools have some limitations, including dependency on empirical users, weak consistency in repeated experiments and time-consuming processes. In this work, a diffusion-based brain network pipeline, DGCL is designed for end-to-end construction of brain networks. Initially, the brain region-aware module (BRAM) precisely determines the spatial locations of brain regions by the diffusion process, avoiding subjective parameter selection. Subsequently, DGCL employs graph contrastive learning to optimize brain connections by eliminating individual differences in redundant connections unrelated to diseases, thereby enhancing the consistency of brain networks within the same group. Finally, the node-graph contrastive loss and classification loss jointly constrain the learning process of the model to obtain the reconstructed brain network, which is then used to analyze important brain connections. Validation on two datasets, ADNI and ABIDE, demonstrates that DGCL surpasses traditional methods and other deep learning models in predicting disease development stages. Significantly, the proposed model improves the efficiency and generalization of brain network construction. In summary, the proposed DGCL can be served as a universal brain network construction scheme, which can effectively identify important brain connections through generative paradigms and has the potential to provide disease interpretability support for neuroscience research.