CNN-based prediction using early post-radiotherapy MRI as a proxy for toxicity in the murine head and neck
The high CNN classification ACC, the regions highlighted by the explainability analysis and the strong correlations between model predictions and toxicity suggest that CNNs, together with post-irradiation magnetic resonance imaging, may identify individuals at risk of developing toxicity.
Authors
- Nina Frederike Jeppesen Edin (ORCID: https://orcid.org/0000-0002-6995-131X)
- Oliver Tomić (ORCID: https://orcid.org/0000-0003-1595-9962)
- Olga Zlygosteva (ORCID: https://orcid.org/0000-0002-2744-9663)
- Cecilia Marie Futsæther (ORCID: https://orcid.org/0000-0001-7944-0719)
- Inga Solgård Juvkam (ORCID: https://orcid.org/0000-0002-6317-5671)
- Bao Ngoc Huynh (ORCID: https://orcid.org/0000-0001-5210-132X)
- Eirik Malinen (ORCID: https://orcid.org/0000-0002-1308-9871)
- Manish Kakar
Institutions
- Oslo University Hospital (NO)
- University of Oslo (NO)
- Norwegian Cancer Society (NO)
- Norwegian University of Life Sciences (NO)
Publication Details
- Journal
- Acta Oncologica
- Published
- 2025-09-25
- DOI
- https://doi.org/10.2340/1651-226x.2025.44020
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Universitetet i Oslo
- Helse Sør-Øst RHF