Predicting near‐complete pathological response to (chemo)radiotherapy in patients with rectal cancer: A federated learning study
The model trained with federated learning showed good discriminative performance, which indicates that it could be useful to identify which patients with rectal cancer would benefit the most from a radiotherapy boost. This study shows that federated learning has the potential to lead to better models by allowing access to more data.
Authors
- Giuditta Chiloiro (ORCID: https://orcid.org/0000-0002-7722-290X)
- Maria Antonietta Gambacorta (ORCID: https://orcid.org/0000-0001-5455-8737)
- Mariachiara Savino (ORCID: https://orcid.org/0000-0001-9666-4407)
- Biche Osong (ORCID: https://orcid.org/0000-0003-1499-0896)
- Andrea Damiani (ORCID: https://orcid.org/0000-0001-8705-3241)
- Iñigo Bermejo (ORCID: https://orcid.org/0000-0001-9105-8088)
- Yves C. P. Willems (ORCID: https://orcid.org/0000-0003-0727-7822)
- Maaike Berbée
- Nikola Dino Capocchiano (ORCID: https://orcid.org/0000-0003-3556-9232)
- Pedro Mateus (ORCID: https://orcid.org/0000-0002-3047-7630)
- André Dekker
Institutions
- Maastricht University Medical Centre (NL)
- Agostino Gemelli University Polyclinic (IT)
- Maastro Clinic (NL)
- Hasselt University (BE)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-08-01
- DOI
- https://doi.org/10.1002/mp.18034
- Citations
- 1
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 1.05
Funders
- Bowel Research UK