Beyond Gleason grading: MRI radiomics to differentiate cribriform growth from non-cribriform growth in prostate cancer men
The radiomics MRI-based model, trained on Gleason sub-patterns segmented on whole-mount specimen, was able to differentiate GP4Crib+ from GP3/GP4Crib- patterns with moderate accuracy. The most dominant feature was the 90th percentile ADC. This exploratory study highlights 90th percentile ADC as a potential biomarker for cribriform growth differentiation, providing insights into future MRI-based risk assessment strategies.
Authors
- Elise M. Bekers (ORCID: https://orcid.org/0000-0001-5159-1697)
- Pim J. van Leeuwen (ORCID: https://orcid.org/0000-0002-5531-6104)
- Marcos A.S. Guimaraes
- Malgorzata Deręgowska-Cylke
- Mar Fernandez Salamanca (ORCID: https://orcid.org/0000-0001-8845-1794)
- Ivo G. Schoots (ORCID: https://orcid.org/0000-0002-9804-0603)
- Rita Simões
- Uulke A van der Heide
- H.G. Van Der Poel
Institutions
- Medical University of Warsaw (PL)
- Erasmus MC (NL)
- The Netherlands Cancer Institute (NL)
- Oncode Institute (NL)
- Amsterdam University Medical Centers (NL)
Publication Details
- Journal
- Magnetic Resonance Materials in Physics Biology and Medicine
- Published
- 2025-04-29
- DOI
- https://doi.org/10.1007/s10334-025-01251-5
- Citations
- 2
- Primary Topic
- Prostate Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 3.04
Funders
- KWF Kankerbestrijding