Longitudinal outcome prediction of prostate cancer patients on active surveillance using multiple instance learning
We show that avoiding Gleason grades is beneficial for longitudinal outcome prediction of prostate cancer. Our results suggest that benign prostate tissue contains prognostic information. However, before our models could be used clinically, much more work remains to improve the generalization.
Authors
- Anders Bjartell (ORCID: https://orcid.org/0000-0002-5761-3786)
- Athanasios Simoulis (ORCID: https://orcid.org/0000-0001-6669-9481)
- Felicia-Elena Marginean
- Agnieszka Krzyzanowska (ORCID: https://orcid.org/0000-0002-1288-7054)
- Filip Winzell
- Kalle Åström (ORCID: https://orcid.org/0000-0002-8689-7810)
- Anders Heyden (ORCID: https://orcid.org/0000-0002-3063-355X)
- Ida Arvidsson
- Niels Christian Overgaard
Institutions
- Statistics Sweden (SE)
- Lund University (SE)
- Skåne University Hospital (SE)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2025-10-14
- DOI
- https://doi.org/10.1117/1.jmi.12.6.061408
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Linköpings Universitet