Technical and clinical validation of a novel deep learning-based white matter hyperintensity segmentation tool
We developed and systematically validated two novel WMH segmentation algorithms, which demonstrated excellent generalization capabilities. The comprehensive, user-friendly processing pipelines are publicly available as prebuilt software containers and can be applied to a wide range of datasets without re-training or modifications.
Authors
- Julie W. Rutten (ORCID: https://orcid.org/0000-0003-3250-7263)
- Lukas Pirpamer (ORCID: https://orcid.org/0000-0002-4390-9703)
- Saskia A.J. Lesnik Oberstein (ORCID: https://orcid.org/0000-0002-1268-8995)
- Sue Moy
- Minne N. Cerfontaine (ORCID: https://orcid.org/0000-0001-9357-270X)
- Michael Kühne (ORCID: https://orcid.org/0000-0002-2937-3711)
- Pauline Maillard (ORCID: https://orcid.org/0000-0003-3516-6345)
- Dominik Meier (ORCID: https://orcid.org/0000-0003-3680-8426)
- Leo Hermann Bonati (ORCID: https://orcid.org/0000-0003-1163-8133)
- Benno Gesierich (ORCID: https://orcid.org/0000-0003-2842-7105)
- Michael Amann (ORCID: https://orcid.org/0000-0001-8041-4083)
- Marco Duering (ORCID: https://orcid.org/0000-0003-2302-3136)
- Karl G. Helmer (ORCID: https://orcid.org/0000-0002-5113-6843)
- Frank-Erik de Leeuw
Institutions
- Harvard University (US)
- Radboud University Nijmegen (NL)
- University of Basel (CH)
- Leiden University Medical Center (NL)
- University Hospital of Basel (CH)
- Radboud University Medical Center (NL)
- LMU Klinikum (DE)
- Massachusetts General Hospital (US)
- Radboud Institute for Molecular Life Sciences (NL)
- Reha Rheinfelden (CH)
- Ludwig-Maximilians-Universität München (DE)
- University of California, Davis (US)
Publication Details
- Journal
- Cerebral Circulation - Cognition and Behavior
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1016/j.cccb.2025.100393
- Citations
- 1
- Primary Topic
- Advanced Neuroimaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- Alzheimer's Disease Neuroimaging Initiative