Dual Attention Graph Convolutional Network Fusing Imaging and Genetic Data for Early Alzheimer's Disease Diagnosis

Jiaqiang Li , Peng Yang , Junlong Qu

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference +

|

March 5, 2025

View abstract on PubMed

Summary

This study introduces a new dual attention graph convolutional network for early Alzheimer's Disease (AD) diagnosis, integrating imaging and genetic data for improved accuracy. The method shows high proficiency in identifying early-stage AD, aiding clinical decisions.

Area Of Science

Neuroscience
Medical Imaging
Genomics
Artificial Intelligence

Background

Alzheimer's Disease (AD) is a major neurodegenerative disorder demanding early diagnosis for effective intervention.
Current diagnostic methods may lack the precision needed for early-stage detection.
Integrating multi-modal data holds promise for improving diagnostic accuracy.

Purpose Of The Study

To develop and validate a novel deep learning approach for early Alzheimer's Disease diagnosis.
To leverage multi-modal data, including imaging and genetic information, for enhanced diagnostic performance.
To improve the accuracy and efficiency of early AD identification to support clinical decision-making.

Main Methods

A dual attention graph convolutional network (GCN) was designed to integrate multi-modal data.
Image and genetic data were used to construct subject-specific graphs.
GCNs extracted embedded information, with self-attention and cross-attention mechanisms fusing multi-modal states.
The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset was used for validation.

Main Results

The proposed dual attention GCN model demonstrated high proficiency in diagnosing early-stage AD.
The integration of multi-modal data through attention mechanisms significantly enhanced diagnostic precision.
Experimental validation on the ADNI dataset confirmed the model's efficacy.

Conclusions

The novel dual attention graph convolutional network offers a promising tool for early Alzheimer's Disease diagnosis.
The method effectively fuses multi-modal imaging and genetic data for improved diagnostic accuracy.
This approach can assist clinicians in making timely and accurate AD diagnoses.