Skip to content

DPGR-Net: A disentangled population-guided graph neural network for major depressive disorder identification.

Sep 2026 · Neural Networks · Vol 205 Pt C, pp. 109616 · 0 citations · 53 references
Medicine

TL;DR

A population-guided dynamic optimization mechanism for individual brain graphs, which feeds the stable disease-discriminative information learned at the population level back into the structural updating of individual brain graphs, thereby enhancing disease-related connections while suppressing site-related noisy connections.

Abstract

Major depressive disorder (MDD) is a brain disorder characterized by substantial individual heterogeneity, and its accurate diagnosis remains challenging in clinical practice. Graph neural networks applied to functional brain networks (FBNs) constructed from resting-state functional magnetic resonance imaging (rs-fMRI) data have shown promise for MDD diagnosis. However, in multicenter settings, site differences are often entangled with disease-related information, which not only interferes with the model's learning of disease patterns but also compromises the reliable modeling of topological patterns in individual FBNs, thereby limiting identification performance. To address this problem, we propose a disentangled population-guided graph neural network with dynamic refinement (DPGR-Net) for MDD identification. Specifically, DPGR-Net first constructs individual FBN from rs-fMRI data and learns discriminative subject-level brain graph representations. To mitigate the interference of site effects, we disentangle disease-related associations from site-related variations at the population level and impose an independence constraint to learn more stable cross-site disease-discriminative representations. On this basis, we innovatively design a population-guided dynamic optimization mechanism for individual brain graphs, which feeds the stable disease-discriminative information learned at the population level back into the structural updating of individual brain graphs, thereby enhancing disease-related connections while suppressing site-related noisy connections. Experimental results on the public REST-meta-MDD dataset show that the proposed method achieves an ACC of 92.37% and outperforms existing state-of-the-art methods. Furthermore, DPGR-Net identifies discriminative brain regions and aberrant functional connectivity patterns associated with MDD, thereby advancing the interpretability and clinical utility of rs-fMRI for MDD diagnosis.

View source

Similar papers

Sep 2026

Modeling inter-subject heterogeneity improves multisite rs-fMRI identification of major depressive disorder: An interpretable graph neural network approach.

BACKGROUND Major depressive disorder (MDD) is a highly heterogeneous affective disorder, and the identification of reliable neuroimaging markers remains challenging. Resting-state functional magnetic resonance imaging offers a promising approach for characterizing altered brain functional organization in MDD. However,...

Ting Mei, Man-Yun Zhu, Hongbo Zhu et al. · 0 citations
Conference Open access Sep 2026

BrainCGT: A Brain Graph Transformer for Modeling Causal Connectivity in Neurological Disorder Diagnosis

Experimental results on three large-scale fMRI datasets demonstrate that BrainCGT achieves consistently better performance than existing graph-based methods for neurological disorder classification, highlighting the importance of incorporating causal directionality into brain graph transformer architectures for robust...

Ahsan Shehzad, Dong-Yu Zhang, Shagufta Abid et al. · 0 citations
Open access Sep 2026

Identifying shared and personalized brain functional connectivity subspace across neuropsychiatric disorders

Objective. Neuropsychiatric disorders exhibit complex functional connectivity (FC) alterations, yet disentangling transdiagnostic mechanisms from disorder-specific network perturbations remains challenging due to clinical heterogeneity and multisite data confounds. Approach. We aggregated large-scale resting-state fMRI...

Shi Liu, Zhi-Chao Wang, Yue-Ming Wang et al. · 0 citations
Preprint Aug 2026

M2LG-DG: A Multi-modal Local-Global Domain Generalization Framework for Cross-site Major Depressive Disorder Classification

Classification models based on resting-state functional magnetic resonance imaging (rs-fMRI) often show lower performance at imaging sites not included during model development, which can limit their use in clinical settings. Domain generalization (DG) addresses this issue by learning representations from source sites...

Muhammad Asif Hasan, Yan-Ming Zhu, Xuefei Yin et al. · 0 citations
Open access Sep 2026

Major depressive disorder recurrence and medication status shape brain network topology

Findings indicate that MDD is associated with altered multiscale functional organization, combining less compact global integration with an increased prevalence of cross-network hole-defining cycles, with these features varying systematically with illness course and current medication, suggesting that topology-informed...

Javier F. Castilla-Jiménez, Juan Carlos Díaz-Patiño, S. Enriquez-Geppert et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.