HDGNN-Mamba2: Mamba-Based Spatiotemporal Heterogeneous Dynamic Graph Neural Network for Major Depressive Disorder Classification.

Overview

1. College of Electronic and Information Engineering, Tongji University, Shanghai 201804, (H.L.)

Abstract

Highlights: What are the main findings?

HDGNN-Mamba2, a novel Mamba2-GNN hybrid with cross-attention fusion, jointly models temporal dynamics and spatial topology of fMRI brain networks, overcoming the limitations of Transformers and existing GNNs.

The framework achieves 83.88% accuracy on REST-meta-MDD, demonstrating competitive performance among GNN-based approaches, with higher sensitivity (86.52%).

What are the implications of the main findings?

The heterogeneous graph module integrates spatiotemporal brain features with non-imaging demographic data via dynamic edge updating, enabling more comprehensive subject representations beyond existing approaches.

The framework identifies interpretable MDD-related model-attributed regions consistent with existing studies, demonstrating its potential as an exploratory framework for MDD classification using multimodal brain imaging and demographic data.

Abstract: Background: Major depressive disorder (MDD) affects 332 million people worldwide, yet diagnosis remains reliant on subjective clinical interviews with substantial inter-rater variability. Objective neuroimaging model-attributed regions offer a path toward precision psychiatry, but existing computational approaches often lack clinical interpretability. Methods: We propose HDGNN-Mamba2, a Mamba-based spatiotemporal heterogeneous dynamic graph neural network. A hybrid Mamba2-GNN block with cross-attention fusion is developed to capture individual spatiotemporal contextual features and identify model-attributed regions. A heterogeneous global graph block with dynamic edge updating is constructed, integrating individual brain features with non-imaging phenotypic information (sex, age, education) to extract embeddings through inter-individual relationship modeling. Heterogeneous Graph Supervised Contrastive Learning is integrated to enhance discriminative capacity. Results: Evaluated on 533 subjects from the REST-meta-MDD dataset, HDGNN-Mamba2 achieved 83.88% accuracy, 86.52% sensitivity, and 80.85% specificity in ten-fold cross-validation. The identified model-attributed regions include the anterior cingulate cortex, parahippocampal gyrus, and thalamus. Conclusions: HDGNN-Mamba2 demonstrates competitive performance as an algorithmic framework for MDD classification, offering complementary architectural advantages in spatiotemporal fusion and interpretable region identification.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper says that its authors' code is available on request: it was not published with the paper, so there is nothing to verify.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none (its code is available on request), so it has no map.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The REST-meta-MDD dataset is publicly available at http://rfmri.org/REST-meta-MDD (accessed on 12 August 2026). The code for HDGNN-Mamba2 is available from the corresponding author upon reasonable request.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 5 keywords, 2 funders, 38 references.

Cite

This paper

Yan, J., Gui, R., Liang, H., & Wang, Y. (2026). HDGNN-Mamba2: Mamba-Based Spatiotemporal Heterogeneous Dynamic Graph Neural Network for Major Depressive Disorder Classification. Brain sciences, 16(8), 872. https://doi.org/10.3390/brainsci16080872

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1002/brb3.71339

Altered Dynamic Functional Connectivity of the Frontoparietal Network in Major Depressive Disorder: Evidence From a Large-Scale Resting-State fMRI Study.

Journal: Brain and behavior

In common: depression, fMRI, systems, 2 references

[2] doi:10.1155/da/8792696 [code]

Connectome Gradient-Based Subtyping of Major Depressive Disorder Reveals Distinct Neurobiological and Transcriptomic Signatures.

Journal: Depression and anxiety

In common: depression, fMRI, 2 references

[3] doi:10.1038/s41398-026-04135-x

Sad emotion processing-related theta oscillation patterns link suicide attempt to childhood trauma in depression: evidence from MEG.

Journal: Translational psychiatry

In common: depression, 2 references

[4] doi:10.1017/s0033291726104711

Cell-type and spatiotemporal transcriptional signatures of white matter morphometric similarity network alterations in major depressive disorder.

Journal: Psychological medicine

In common: depression, 2 references

[5] doi:10.3390/diagnostics16172746

Benchmarking Synolitic Graphs for Autism Classification from Multisite Resting-State fMRI.

Journal: Diagnostics (Basel, Switzerland)

In common: fMRI, 2 references

[6] doi:10.1016/j.isci.2026.116173 [code]

Hierarchical sparse spatiotemporal graph neural network for brain graph classification.

Journal: iScience

In common: fMRI, 2 references

[7] doi:10.1038/s41398-026-04025-2 [code]

Brain energetic landscapes shape state dysregulation in major depressive disorder: a morphological network controllability perspective.

Journal: Translational psychiatry

In common: depression, 2 references

[8] doi:10.1038/s42003-026-10156-5 [code]

Brain-heart interactions in late-onset major depressive disorder revealed by multimodal HRV-driven fMRI.

Journal: Communications biology

In common: depression, fMRI, 1 reference

[9] doi:10.1038/s41540-026-00699-y [code]

Inferring relationships among major psychiatric disorders in a resting-state functional connectivity-informed embedding space.

Journal: NPJ systems biology and applications

In common: depression, fMRI, 1 reference

[10] doi:10.31083/ap48336

Brain Functional Network Alterations in Adolescents With Major Depressive Disorder and Suicidal Attempt: A Resting-State fMRI Study.

Journal: Alpha psychiatry

In common: depression, fMRI, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.