A multi‐view learning approach with diffusion model to synthesize FDG PET from MRI T1WI for diagnosis of Alzheimer's disease
We propose a diffusion model with two strategies to synthesize fluorodeoxyglucose positron emission tomography (FDG PET) from magnetic resonance imaging T1 weighted imaging (MRI T1WI). We raise multi-view learning with MRl T1Wl and synthesized FDG PET for Alzheimer's disease (AD) diagnosis. We provide a comprehensive experimental comparison for the synthesized FDG PET view. The feasibility of synthesized FDG PET view in AD diagnosis is validated with various experiments. We demonstrate the ability of synthesized FDG PET to enhance the performance of machine learning-based AD diagnosis.
Authors
- Tom Dening (ORCID: https://orcid.org/0000-0003-3387-4241)
- Akram A. Hosseini (ORCID: https://orcid.org/0000-0003-0133-9842)
- Yiming Zhang (ORCID: https://orcid.org/0000-0002-9570-8962)
- Yueqin Huang (ORCID: https://orcid.org/0000-0003-4413-2921)
- Ke Chen (ORCID: https://orcid.org/0000-0002-3855-8363)
- Weizhong Xiao
- Ying Weng (ORCID: https://orcid.org/0000-0003-4338-713X)
Institutions
- Nottingham University Hospitals NHS Trust (GB)
- University of Nottingham Ningbo China (CN)
- University of Nottingham (GB)
- Peking University (CN)
- Queen's Medical Centre (GB)
- Peking University Third Hospital (CN)
- Peking University Sixth Hospital (CN)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2024-12-06
- DOI
- https://doi.org/10.1002/alz.14421
- Citations
- 6
- Primary Topic
- Advanced Neuroimaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 2.43
Funders
- Medical Research Council
- National Institute on Aging