DW-DGAT: Dynamically Weighted Dual Graph Attention Network for Neurodegenerative Disease Diagnosis

TL;DR

This paper introduces DW-DGAT, a novel neural network that fuses multi-metric neuroimaging data and addresses class imbalance to improve early diagnosis of Parkinson's and Alzheimer's diseases.

Contribution

The paper presents a dynamically weighted dual graph attention network that integrates data fusion, dual graph attention architecture, and class imbalance mitigation for neurodegenerative disease diagnosis.

Findings

Achieves state-of-the-art performance on PPMI and ADNI datasets.

Effectively fuses multi-metric data with a general-purpose strategy.

Mitigates class imbalance with a new class weight generation mechanism.

Abstract

Parkinson's disease (PD) and Alzheimer's disease (AD) are the two most prevalent and incurable neurodegenerative diseases (NDs) worldwide, for which early diagnosis is critical to delay their progression. However, the high dimensionality of multi-metric data with diverse structural forms, the heterogeneity of neuroimaging and phenotypic data, and class imbalance collectively pose significant challenges to early ND diagnosis. To address these challenges, we propose a dynamically weighted dual graph attention network (DW-DGAT) that integrates: (1) a general-purpose data fusion strategy to merge three structural forms of multi-metric data; (2) a dual graph attention architecture based on brain regions and inter-sample relationships to extract both micro- and macro-level features; and (3) a class weight generation mechanism combined with two stable and effective loss functions to mitigate class imbalance. Rigorous experiments, based on the Parkinson Progression Marker Initiative (PPMI) and Alzheimer's Disease Neuroimaging Initiative (ADNI) studies, demonstrate the state-of-the-art performance of our approach.