AUTHOR=Ling Ronghua , Cen Xingxing , Wu Shaoyou , Wang Min , Zhang Ying , Jiang Juanjuan , Lu Jiaying , Liu Yingqian , Zuo Chuantao , Jiang Jiehui , Yang Yinghui , Yan Zhuangzhi TITLE=Explainable graph neural network based on metabolic brain imaging for differential diagnosis of parkinsonism JOURNAL=Frontiers in Aging Neuroscience VOLUME=Volume 17 - 2025 YEAR=2025 URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2025.1580910 DOI=10.3389/fnagi.2025.1580910 ISSN=1663-4365 ABSTRACT=BackgroundAccurate differentiation of parkinsonian syndromes remains challenging due to overlapping clinical manifestations and subtle neuroimaging variations. This study introduces an explainable graph neural network (GNN) framework integrating a Regional Radiomics Similarity Network (R2SN) and Transformer-based attention mechanisms to address this diagnostic dilemma.MethodsOur study prospectively enrolled 1,495 participants, including 220 healthy controls and 1,275 patients diagnosed with idiopathic Parkinson’s disease (IPD), multiple system atrophy (MSA), or progressive supranuclear palsy (PSP), all undergoing standardized 18F-fluorodeoxyglucose positron emission tomography imaging. Metabolic networks were constructed by encoding edge weights derived from radiomic feature similarity matrices, enabling simultaneous quantification of microscopic metabolic heterogeneity and macroscale network reorganization.ResultsThe proposed framework achieved superior classification performance with F1-scores of 92.5% (MSA), 96.3% (IPD), and 86.7% (PSP), significantly outperforming comparators by 5.5–8.3%. Multiscale interpretability analysis revealed: (1) Regional hypometabolism in pathognomonic nodes (putamen in IPD, midbrain tegmentum in PSP); (2) Disease-specific connectivity disruptions (midbrain-prefrontal disconnection in PSP, cerebellar-pontine decoupling in MSA). The substructure attention mechanism reduced computational complexity by 41% while enhancing diagnostic specificity (PSP precision +5.2%).ConclusionThe proposed R2SN-based explainable GNN framework for parkinsonian syndrome differentiation establishes a new paradigm for precision subtyping of neurodegenerative disorders, with methodological extensibility to other network-driven neurological conditions.