Hi-STMNA-GCN: A Hierarchical Spatio-Temporal Multi-Neighbor Graph Convolutional Network for Robust Alzheimer’s Disease Detection From fMRI Data

Early detection of Alzheimer’s Disease (AD), particularly at the Mild Cognitive Impairment (MCI) stage, is essential for effective intervention and disease management. Traditional deep learning models often struggle to simultaneously capture both local and global brain connectivity patterns from functional Magnetic Resonance Imaging (fMRI) data. To address these challenges, we propose the Hierarchical Spatio-Temporal Multi-Neighbour Aggregation Graph Convolutional Network (Hi-STMNA-GCN), a novel deep learning framework designed for robust AD classification. The Hi-STMNA-GCN model operates at two levels: at the Region Level, it employs multi-neighbour aggregation graph convolutional networks to comprehensively capture spatial dependencies by aggregating information from neighbouring nodes across multiple scales, while Gated Recurrent Units (GRU) effectively model the temporal dynamics of brain activity. At the Population Level, a hypergraph-based module is introduced to learn complex inter-subject relationships, enhancing the global discriminative power of the model. Additionally, a Masked Relation Learning (MRL) mechanism is integrated to prune redundant connections, ensuring that the most informative brain region interactions are preserved. Extensive experiments demonstrate that Hi-STMNA-GCN significantly outperforms existing methods, achieving classification accuracies of 96% (AD vs. Cognitively Normal (CN)), 94.8% (AD vs. MCI), and 98% (MCI vs. CN). These results highlight the model’s potential for early, reliable AD detection and its applicability in advancing neuroimaging-based diagnostic tools.

• Publication year

  2026

• Venue

  IEEE Access

• Publication date

  Unknown publication date

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1109/ACCESS.2025.3648664
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Alzheimer's Disease Diagnosis Using Ensemble of Random Weighted Features and Fuzzy Least Square Twin Support Vector Machine

  2025cited by this paper
• MssNet: An Efficient Spatial Attention Model for Early Recognition of Alzheimer's Disease

  2025cited by this paper
• Brain-Inspired Fuzzy Graph Convolution Network for Alzheimer's Disease Diagnosis Based on Imaging Genetics Data

  2025cited by this paper
• Recent advances in Alzheimer’s disease: mechanisms, clinical trials and new drug development strategies

  2024influential reference
• A Multigraph Combination Screening Strategy Enabled Graph Convolutional Network for Alzheimer’s Disease Diagnosis

  2024cited by this paper
• IG-GCN: Empowering e-Health Services for Alzheimer’s Disease Prediction

  2024influential reference
• Multi-Modal Diagnosis of Alzheimer’s Disease Using Interpretable Graph Convolutional Networks

  2024influential reference
• A Hybrid Multi-Scale Attention Convolution and Aging Transformer Network for Alzheimer's Disease Diagnosis

  2023cited by this paper
• Multi-relation graph convolutional network for Alzheimer's disease diagnosis using structural MRI

  2023influential reference
• GCCN: Graph Capsule Convolutional Network for Progressive Mild Cognitive Impairment Prediction and Pathogenesis Identification Based on Imaging Genetic Data

  2023cited by this paper
• Class activation attention transfer neural networks for MCI conversion prediction

  2023cited by this paper
• Multimodal cross enhanced fusion network for diagnosis of Alzheimer's disease and subjective memory complaints

  2023cited by this paper
• Attention-based and micro designed EfficientNetB2 for diagnosis of Alzheimer's disease

  2023cited by this paper
• Deep Fusion of Multi-Template Using Spatio-Temporal Weighted Multi-Hypergraph Convolutional Networks for Brain Disease Analysis

  2023cited by this paper
• Research of spatial context convolutional neural networks for early diagnosis of Alzheimer’s disease

  2023influential reference
• A-GCL: Adversarial graph contrastive learning for fMRI analysis to diagnose neurodevelopmental disorders

  2023cited by this paper
• Population-based GCN method for diagnosis of Alzheimer's disease using brain metabolic or volumetric features

  2023cited by this paper
• An extensible hierarchical graph convolutional network for early Alzheimer's disease identification

  2023cited by this paper
• An Evolving Hypergraph Convolutional Network for the Diagnosis of Alzheimer’s Disease

  2022cited by this paper
• Interpretable learning based Dynamic Graph Convolutional Networks for Alzheimer's Disease analysis

  2022cited by this paper
• Alzheimer's Disease Diagnosis With Brain Structural MRI Using Multiview-Slice Attention and 3D Convolution Neural Network

  2022cited by this paper
• Regional Brain Fusion: Graph Convolutional Network for Alzheimer's Disease Prediction and Analysis

  2022cited by this paper
• Hypergraph Structural Information Aggregation Generative Adversarial Networks for Diagnosis and Pathogenetic Factors Identification of Alzheimer’s Disease With Imaging Genetic Data

  2022cited by this paper
• AUTOMATED PREDICTION SYSTEM FOR ALZHEIMER DETECTION BASED ON DEEP RESIDUAL AUTOENCODER AND SUPPORT VECTOR MACHINE

  2022cited by this paper
• Signed graph representation learning for functional-to-structural brain network mapping

  2022cited by this paper
• VGG-TSwinformer: Transformer-based deep learning model for early Alzheimer's disease prediction

  2022cited by this paper
• FedNI: Federated Graph Learning With Network Inpainting for Population-Based Disease Prediction

  2021cited by this paper
• A Prior Guided Adversarial Representation Learning and Hypergraph Perceptual Network for Predicting Abnormal Connections of Alzheimer's Disease

  2021influential reference
• A Convolutional Neural Network Combined With Prototype Learning Framework for Brain Functional Network Classification of Autism Spectrum Disorder

  2021cited by this paper
• Automated

  2021cited by this paper
• Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Prediction

  2021cited by this paper
• Graph Convolutional Networks for Hyperspectral Image Classification

  2020cited by this paper
• Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition

  2020cited by this paper
• Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction

  2020cited by this paper
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

  2020cited by this paper
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

  2019influential reference
• Metric learning with spectral graph convolutions on brain connectivity networks

  2018cited by this paper
• Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer's disease

  2018cited by this paper
• Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications

  2017cited by this paper
• Deriving reproducible biomarkers from multi‐site resting‐state data: An Autism‐based example

  2016cited by this paper
• On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

  2014cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014cited by this paper
• Machine Learning-Based Method for Personalized and Cost-Effective Detection of Alzheimer's Disease

  2013cited by this paper
• Alzheimer's Disease Neuroimaging Initiative (ADNI)

  2010cited by this paper
• Credit

  1980cited by this paper

• No citing papers are available for this paper.