Harmonizing CT scanner acquisition variability in an anthropomorphic phantom: A comparative study of image-level and feature-level harmonization using GAN, ComBat, and their combination
While GAN qualitatively enhances image harmonization, ComBat provides superior statistical improvements in feature stability and classification performance, highlighting the importance of robust feature-level harmonization in radiomics.
Authors
- Henry C. Woodruff (ORCID: https://orcid.org/0000-0001-7911-5123)
- Vincent Andrearczyk (ORCID: https://orcid.org/0000-0003-0793-5821)
- Nastaran Mohammadian Rad (ORCID: https://orcid.org/0000-0003-3068-4127)
- Adrien Depeursinge (ORCID: https://orcid.org/0000-0002-2362-0304)
- Philippe Lambin
- Shruti Atul Mali (ORCID: https://orcid.org/0000-0002-8307-8051)
Institutions
- HES-SO University of Applied Sciences and Arts Western Switzerland (CH)
- Maastricht University Medical Centre (NL)
- Centre Hospitalier Universitaire Vaudois (CH)
- Maastricht University (NL)
- Maastro Clinic (NL)
Publication Details
- Journal
- PLoS ONE
- Published
- 2025-05-09
- DOI
- https://doi.org/10.1371/journal.pone.0322365
- Citations
- 1
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- Horizon 2020