¹⁹F MRI radiomic features: in vitro and in vivo repeatability
KEY POINTS: We analyzed 194 ¹⁹F MRI scans and 772 segments obtained in phantoms at 7 T. Cross-agent stability identified 466 radiomic features meeting concordance correlation coefficient ≥ 0.85 and normalized dynamic range ≥ 0.90. Of these phantom-stable features, 401 of 466 remained stable in vivo in a tumor mouse model. Intensity features were most repeatable, while shape features were least stable across sessions. Median concordance correlation coefficient dropped from 0.886 intrasession to 0.683 intersession.
Authors
- Mariah R. R. Daal (ORCID: https://orcid.org/0000-0002-2509-3739)
- Mangala Srinivas (ORCID: https://orcid.org/0000-0002-3835-1995)
- Manon Boeije
- Leila Akkari (ORCID: https://orcid.org/0000-0001-5479-641X)
- Serena Vegna (ORCID: https://orcid.org/0000-0003-0518-9319)
- Sajjad Rostami
- Zuhir Bodalal (ORCID: https://orcid.org/0000-0002-2617-8128)
- Olga Maxouri (ORCID: https://orcid.org/0000-0002-4709-1929)
- Diana Ivonne Rodríguez Sánchez
- R.G.H. Beets-Tan
- Natalie Proost
- Stephan Ursprung
- Marieke van de Ven
Institutions
- University of Southern Denmark (DK)
- Maastricht University Medical Centre (NL)
- The Netherlands Cancer Institute (NL)
- Maastricht University (NL)
- Oncode Institute (NL)
- Cancer Genomics Centre (NL)
- University of Tübingen (DE)
- Wageningen University & Research (NL)
Publication Details
- Journal
- European Radiology Experimental
- Published
- 2026-03-16
- DOI
- https://doi.org/10.1186/s41747-026-00694-2
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00