Automated <scp>MRI</scp> ‐Based Classification of Parkinsonism: A Deep Learning Approach to Distinguish <scp>PD</scp> From <scp>PSP</scp>
The automated MRPI method improves diagnostic accuracy for differentiating PD from PSP, providing a reliable and clinically applicable tool. The integration of a super-resolution technique to convert 2D MRI data into high-resolution images expands the potential of MRPI as a neuroimaging biomarker.
Authors
- Tianbin Song (ORCID: https://orcid.org/0000-0002-9646-6539)
- Ying Zhou (ORCID: https://orcid.org/0000-0002-5666-6405)
- Zehong Cao (ORCID: https://orcid.org/0000-0003-3656-0328)
- Feng Shi (ORCID: https://orcid.org/0000-0003-1522-9943)
- Weizhao Lu (ORCID: https://orcid.org/0000-0002-2941-9791)
- Xiaofei Hu (ORCID: https://orcid.org/0000-0001-5376-2779)
- Jie Lu (ORCID: https://orcid.org/0000-0003-0425-3921)
- Rui Hua (ORCID: https://orcid.org/0000-0001-7507-6155)
- Yingjie Zhu (ORCID: https://orcid.org/0009-0003-4524-894X)
- Donglan Peng
Institutions
- Army Medical University (CN)
- Capital Medical University (CN)
- Southwest Hospital (CN)
- United Imaging Healthcare (China) (CN)
Publication Details
- Journal
- CNS Neuroscience & Therapeutics
- Published
- 2025-11-01
- DOI
- https://doi.org/10.1111/cns.70645
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation