Using AI to improve cross‐sectional and longitudinal Amyloid PET quantification: A validation study across 7 large cohorts
Deep learning provides a significant advance in PET quantification of amyloid, outperforming standard methods both cross-sectionally and longitudinally in both observational and interventional studies. DeepSUVR improves the ability to harmonise large datasets and different PET tracers. This is particularly important for consistent decision making and when the outcome measure of an intervention is expected to be subtle such as altering the rate of accumulation.
Authors
- Vincent Doré (ORCID: https://orcid.org/0000-0002-8051-0558)
- Ariane Bollack (ORCID: https://orcid.org/0000-0002-9169-7530)
- Georgios Zisis (ORCID: https://orcid.org/0000-0003-2967-0318)
- Ashley Gillman (ORCID: https://orcid.org/0000-0001-9130-1092)
- Azadeh Feizpour
- Colin Louis Masters (ORCID: https://orcid.org/0000-0003-3072-7940)
- Pamela LaMontagne (ORCID: https://orcid.org/0000-0002-6752-8518)
- Timothy Cox (ORCID: https://orcid.org/0000-0002-7232-5096)
- Duygu Tosun (ORCID: https://orcid.org/0000-0001-5174-3910)
- Gill Farrar (ORCID: https://orcid.org/0000-0002-0726-723X)
- C. Rowe
- Frederik Barkhof
- Pierrick Bourgeat
- Ying Xia
- Tammie L.S. Benzinger
- Jurgen Fripp
- Michael S. W. Weiner
- Manu S. Goyal
- Victor L. Villemagne
- John C. Morris
- Reisa A. Sperling
Institutions
- Brigham and Women's Hospital (US)
- Commonwealth Scientific and Industrial Research Organisation (AU)
- San Francisco VA Medical Center (US)
- The University of Melbourne (AU)
- University of Pittsburgh (US)
- University of California, San Francisco (US)
- Washington University in St. Louis (US)
- Florey Institute of Neuroscience and Mental Health (AU)
- Mallinckrodt (United States) (US)
- Australian e-Health Research Centre (AU)
- CSIRO Health and Biosecurity (AU)
- Advanced Imaging Research (United States) (US)
- Amsterdam University Medical Centers (NL)
- Austin Health (AU)
- Vrije Universiteit Amsterdam (NL)
- Amsterdam UMC Location Vrije Universiteit Amsterdam (NL)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1002/alz70856_104230
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00