Predicting the hypoxic volume of head and neck tumors from fluorodeoxyglucose positron emission tomography images using artificial intelligence
Voxel-wise prediction of hypoxia for HN cancers from a 2D deep learning model using FDG-PET images as inputs was shown to be feasible. Testing on larger institutional and multi-institutional cohorts is required to establish generalizability.
Authors
- Harini Veeraraghavan (ORCID: https://orcid.org/0000-0002-4054-5529)
- Heiko M. Schöder (ORCID: https://orcid.org/0000-0002-5170-4185)
- Milan Grkovski (ORCID: https://orcid.org/0000-0001-7228-9497)
- Joseph O. Deasy (ORCID: https://orcid.org/0000-0002-9437-266X)
- John L. Humm (ORCID: https://orcid.org/0000-0003-4245-5591)
- Nancy Y. Lee (ORCID: https://orcid.org/0000-0003-3044-9522)
- Aditya Apte (ORCID: https://orcid.org/0000-0001-8120-0669)
- Wei Zhao (ORCID: https://orcid.org/0000-0001-8440-2274)
Institutions
- Memorial Sloan Kettering Cancer Center (US)
Publication Details
- Journal
- Physics and Imaging in Radiation Oncology
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1016/j.phro.2025.100769
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Breast Cancer Research Foundation
- National Institutes of Health
- National Cancer Institute