A Robust Residual Three-dimensional Convolutional Neural Networks Model for Prediction of Amyloid-β Positivity by Using FDG-PET
We demonstrated that residual 3DCNN can learn complex 3D spatial patterns in FDG-PET images and robustly predict amyloid-β positivity with significantly less reliance on site harmonization preprocessing.
Authors
- Sunil Kumar Maurya (ORCID: https://orcid.org/0000-0001-8839-8559)
- Ilya Ardakani (ORCID: https://orcid.org/0000-0002-7024-724X)
- Sayaka Iwano (ORCID: https://orcid.org/0009-0008-9679-7486)
- Kazunari Ishii (ORCID: https://orcid.org/0000-0001-6601-952X)
- T Yamada (ORCID: https://orcid.org/0000-0002-0930-6546)
Institutions
- Kindai University Hospital (JP)
- Alzheimer’s Disease Neuroimaging Initiative (US)
- Artistic Realization Technologies (US)
- Kindai University (JP)
Publication Details
- Journal
- Clinical Nuclear Medicine
- Published
- 2025-06-17
- DOI
- https://doi.org/10.1097/rlu.0000000000005966
- Citations
- 2
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 2.94