Explainable graph neural network based on metabolic brain imaging for differential diagnosis of parkinsonism
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.
Authors
- Xingxing Cen (ORCID: https://orcid.org/0000-0002-1913-8590)
- Jiaying Lu (ORCID: https://orcid.org/0000-0003-0927-0042)
- Yinghui Yang (ORCID: https://orcid.org/0000-0002-3139-6277)
- Chuantao Zuo (ORCID: https://orcid.org/0000-0002-8856-7217)
- Juanjuan Jiang (ORCID: https://orcid.org/0000-0003-1875-4807)
- Zhuangzhi Yan (ORCID: https://orcid.org/0000-0002-4917-463X)
- Ronghua Ling (ORCID: https://orcid.org/0009-0006-6768-5691)
- Jiehui Jiang (ORCID: https://orcid.org/0000-0003-4948-3683)
- Min Wang (ORCID: https://orcid.org/0000-0002-3436-4246)
- Ying Zhang (ORCID: https://orcid.org/0000-0003-3764-7329)
- Yingqian Liu (ORCID: https://orcid.org/0000-0002-8648-6608)
- Shaoyou Wu
Institutions
- Shanghai University (CN)
- Shandong University (CN)
- Donghua University (CN)
- Shanghai University of Medicine and Health Sciences (CN)
- Shanghai Jian Qiao University (CN)
- Huashan Hospital (CN)
Publication Details
- Journal
- Frontiers in Aging Neuroscience
- Published
- 2025-04-11
- DOI
- https://doi.org/10.3389/fnagi.2025.1580910
- Citations
- 3
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 4.17
Funders
- National Natural Science Foundation of China