EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hierarchical neighbor integration graph attention network for autism spectrum disorder diagnosis

Di Ma, Liling Peng, Li Zhang, Weikai Li, Xin Gao

Frontiers in Psychiatry · 20.07.2026 · 17

DOI: 10.3389/fpsyt.2026.1846996 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Psychiatry, online erschienen am 20.07.2026. Verfasst von Di Ma und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Early diagnosis of autism spectrum disorder (ASD) based on resting-state functional magnetic resonance imaging (rs-fMRI) is crucial for effective intervention and rehabilitation. Using rs-fMRI, functional brain networks (FBNs) are constructed to represent interactions among brain regions of interest (ROIs), and existing graph neural network–based methods, particularly Graph Attention Networks (GATs), have shown promise for FBN-based ASD diagnosis. However, most current approaches primarily aggregate ROIs through low-order pairwise interactions, while higher-order neighbors are incorporated only implicitly through increased network depth. This strategy often leads to over-smoothing of node representations and limits the capture of informative higher-order brain interactions.

Methods

To address these challenges, we propose the Hierarchical Neighbor Integration Graph Attention Network (HiNIGAT), a general graph learning framework that explicitly models multi-order interactions in FBNs. Specifically, HiNIGAT introduces a multi-order attention mechanism that constrains each attention head to specialize in a distinct neighborhood order, enabling the model to capture brain interactions from local connectivity to global network structure. Furthermore, a bidirectional gated fusion strategy is proposed to adaptively integrate complementary information across multi-order features, facilitating effective local–global representation collaboration.

Results

Experiments on the ABIDE-I dataset demonstrate the effectiveness of HiNIGAT.

Discussion

The results highlight the importance of explicit multi-order integration for ASD diagnosis.

Schlagwörter

Stichwörter der Autor:innen

autism spectrum disorderfunctional brain networkfunctional magnetic resonance imaginggraph attention networkmulti-order interactions

Autor:innen und Institutionen

  • College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China.
  • Department of PET/MR, Shanghai Universal Medical Imaging Diagnostic Center, Shanghai, China.
  • School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China.

Zitieren

APA

Ma, D., Peng, L., Zhang, L., Li, W., & Gao, X. (2026). Hierarchical neighbor integration graph attention network for autism spectrum disorder diagnosis. Frontiers in Psychiatry, 17. https://doi.org/10.3389/fpsyt.2026.1846996

Vancouver

Ma D, Peng L, Zhang L, Li W, Gao X. Hierarchical neighbor integration graph attention network for autism spectrum disorder diagnosis. Frontiers in Psychiatry. 2026;17. doi:10.3389/fpsyt.2026.1846996

BibTeX
@article{Ma2026,
  author = {Ma, Di and Peng, Liling and Zhang, Li and Li, Weikai and Gao, Xin},
  title = {Hierarchical neighbor integration graph attention network for autism spectrum disorder diagnosis},
  journal = {Frontiers in Psychiatry},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpsyt.2026.1846996}
}
Kostenlos starten →