Brain Connectivity Network Structure Learning For Brain Disorder Diagnosis

2025-09-20

AI Summary

Conventional brain connectivity network construction relies on predefined thresholds, often introducing spurious connections or missing critical interactions; moreover, scarce labeled data hinder representation generalization. Method: We propose a self-supervised framework for brain functional disorder diagnosis that adaptively learns individualized, optimal connectivity network structures and representations—without manual thresholding. Our approach innovatively integrates dual whole-brain connectome-based complementary network structure learners, coupled with a multi-state graph encoder and a joint iterative optimization strategy, to jointly enhance structural discovery and feature representation while enabling few-shot transfer. Contribution/Results: Pretrained on large-scale unlabeled fMRI data, the framework achieves state-of-the-art performance on cross-dataset brain disease diagnosis tasks, demonstrating superior generalizability and clinical applicability. The code is publicly available.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recent studies in neuroscience highlight the significant potential of brain connectivity networks, which are commonly constructed from functional magnetic resonance imaging (fMRI) data for brain disorder diagnosis. Traditional brain connectivity networks are typically obtained using predefined methods that incorporate manually-set thresholds to estimate inter-regional relationships. However, such approaches often introduce redundant connections or overlook essential interactions, compromising the value of the constructed networks. Besides, the insufficiency of labeled data further increases the difficulty of learning generalized representations of intrinsic brain characteristics. To mitigate those issues, we propose a self-supervised framework to learn an optimal structure and representation for brain connectivity networks, focusing on individualized generation and optimization in an unsupervised manner. We firstly employ two existing whole-brain connectomes to adaptively construct their complementary brain network structure learner, and then introduce a multi-state graph-based encoder with a joint iterative learning strategy to simultaneously optimize both the generated network structure and its representation. By leveraging self-supervised pretraining on large-scale unlabeled brain connectivity data, our framework enables the brain connectivity network learner to generalize e ffectively to unseen disorders, while requiring only minimal finetuning of the encoder for adaptation to new diagnostic tasks. Extensive experiments on cross-dataset brain disorder diagnosis demonstrate that our method consistently outperforms state-of-the-art approaches, validating its effectiveness and generalizability. The code is publicly available at https://github.com/neochen1/BCNSL.

Problem

• Traditional brain connectivity networks use predefined thresholds causing redundant connections
• Insufficient labeled data hinders learning generalized brain characteristic representations
• Need unsupervised framework to optimize brain network structure and representation

Innovation

• Self-supervised framework for brain network structure learning
• Adaptive construction of complementary brain network structure
• Multi-state graph encoder with joint iterative optimization