AI Insight
Researchers developed a new machine learning framework to identify major depressive disorder (MDD) from brain imaging scans across different medical sites, addressing the challenge that scanning protocols and equipment vary between locations. The method combines multiple ways of analyzing brain connectivity patterns using graph neural networks with hyperbolic geometry and aligns data from different sources to reduce site-specific biases while preserving disease-relevant information. Testing across seven different target datasets, the framework achieved 73.60% accuracy and 71.90% AUC in identifying MDD patients.
Why it matters
This approach could enable more reliable cross-site diagnosis of depression using brain imaging, potentially allowing medical centers to share and validate diagnostic models despite using different scanning equipment. The framework's ability to generalize across heterogeneous data sources represents an important step toward clinical deployment of AI-based mental health diagnostics.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Cross-site identification of major depressive disorder (MDD) from resting-state functional magnetic resonance imaging (rs-fMRI) is hindered by inter-site distribution shifts and heterogeneous functional connectivity (FC) views. These views capture complementary neural relationships but exhibit distinct site biases and graph topologies, complicating alignment without sacrificing disease-relevant information or cross-view consistency. Existing studies largely treat multi-view connectome learning and cross-site adaptation separately. To the best of our knowledge, few studies have jointly modeled multiple FC views under multi-source unsupervised domain adaptation for cross-site rs-fMRI-based MDD classification. We construct Pearson correlation, sparse representation, and Granger causality graphs, each encoded by a view-specific graph attention network. Dual-stream adaptive fusion explicitly integrates pairwise cross-view interactions, followed by lightweight hyperbolic residual encoding for curvature-aware representation refinement. Class-wise Cauchy–Schwarz alignment reduces inter-source and source-target discrepancies, complemented by adversarial learning, information maximization, and confidence-aware pseudo-labeling. Across seven unlabeled target domains, our framework achieves 73.60% mean accuracy and 71.90% AUC, demonstrating effective generalization under heterogeneous acquisition conditions. These results highlight the effectiveness of unified heterogeneous-view modeling, curvature-aware refinement, and multi-source domain adaptation for cross-site MDD identification.The source code is at https://github.com/OPUS-Lightphenexx/MM-HyperGDA