Cross‐site harmonization of diffusion <scp>MRI</scp> data without matched training subjects
RISH-GLM can learn cross-site harmonization both from matched and unmatched groups of training subjects and can effectively be used to harmonize data of multiple sites in one single step.
Authors
- John Cornelis Van Swieten (ORCID: https://orcid.org/0000-0001-6278-6844)
- Suheyla Cetin‐Karayumak (ORCID: https://orcid.org/0000-0002-3315-5821)
- Alexander Leemans (ORCID: https://orcid.org/0000-0002-9306-6126)
- Alberto De Luca (ORCID: https://orcid.org/0000-0002-2553-7299)
- Yogesh Rathi (ORCID: https://orcid.org/0000-0002-9946-2314)
- Ofer Pasternak (ORCID: https://orcid.org/0000-0002-7078-6446)
- Harro Seelaar (ORCID: https://orcid.org/0000-0003-1989-7527)
- Lize Corrine Jiskoot (ORCID: https://orcid.org/0000-0002-1120-1858)
- Tine Swartenbroekx
Institutions
- Brigham and Women's Hospital (US)
- Harvard University (US)
- Erasmus MC (NL)
- University Medical Center Utrecht (NL)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-05-23
- DOI
- https://doi.org/10.1002/mrm.30575
- Primary Topic
- Advanced Neuroimaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institute for Health and Care Research
- Alzheimer Nederland
- National Institutes of Health
- H2020 European Research Council