Ling Ronghua, Cen Xingxing, Wu Shaoyou, Wang Min, Zhang Ying, Jiang Juanjuan, Lu Jiaying, Liu Yingqian, Zuo Chuantao, Jiang Jiehui, Yang Yinghui, Yan Zhuangzhi
School of Communication and Information Engineering, Shanghai University, Shanghai, China.
School of Medical Imaging, Shanghai University of Medicine and Health Science, Shanghai, China.
Front Aging Neurosci. 2025 Apr 11;17:1580910. doi: 10.3389/fnagi.2025.1580910. eCollection 2025.
Accurate 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.
Our 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 F-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.
The 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%).
The 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.
由于临床表现重叠和神经影像学细微变化，帕金森综合征的准确鉴别仍然具有挑战性。本研究引入了一种可解释的图神经网络（GNN）框架，该框架整合了区域放射组学相似性网络（R2SN）和基于Transformer的注意力机制，以解决这一诊断难题。
我们的研究前瞻性纳入了1495名参与者，包括220名健康对照者和1275名被诊断为特发性帕金森病（IPD）、多系统萎缩（MSA）或进行性核上性麻痹（PSP）的患者，所有患者均接受标准化的F-氟脱氧葡萄糖正电子发射断层扫描成像。通过对从放射组学特征相似性矩阵导出的边权重进行编码来构建代谢网络，从而能够同时量化微观代谢异质性和宏观网络重组。
所提出的框架实现了卓越的分类性能，F1分数分别为92.5%（MSA）、96.3%（IPD）和86.7%（PSP），显著优于比较器5.5 - 8.3%。多尺度可解释性分析显示：（1）特征性节点区域代谢减低（IPD中的壳核，PSP中的中脑被盖）；（2）疾病特异性的连接中断（PSP中的中脑-前额叶断开，MSA中的小脑-脑桥解耦）。子结构注意力机制在提高诊断特异性（PSP精度提高5.2%）的同时，将计算复杂度降低了41%。
所提出的基于R2SN的可解释GNN框架用于帕金森综合征鉴别，为神经退行性疾病的精确亚型分类建立了新范例，其方法具有扩展到其他网络驱动的神经疾病的潜力。
