Global and regional accuracy of deep learning-based tumor segmentation from whole-body [18F]fluorodeoxyglucose PET/CT images
These results are consistent with previous reports on PET-based segmentation, further validating nnU-Net as a reliable approach for detecting hypermetabolic lesions and assessing global disease burden in FDG-PET imaging. Moreover, the significant relationship between TBR and segmentation accuracy suggests the possibility of further improvements by integrating metabolic profile into the predictive model.
Authors
- Massimo Castellani (ORCID: https://orcid.org/0000-0002-9217-3456)
- Luigia Florimonte (ORCID: https://orcid.org/0000-0002-5254-6852)
- O. Ferrando (ORCID: https://orcid.org/0000-0002-7067-2422)
- Lorenzo Maffioli (ORCID: https://orcid.org/0000-0002-8867-2447)
- F. Foppiano
- Nikola Yosifov
- Andrea Ciarmiello (ORCID: https://orcid.org/0000-0002-6579-656X)
- Bruno Alfano (ORCID: https://orcid.org/0000-0002-7315-3628)
- Giampiero Giovacchini (ORCID: https://orcid.org/0000-0003-3334-2130)
- Amalia Milano
- Matteo Canevari
- Donatella Masciale
Institutions
- NATO Centre for Maritime Research and Experimentation (IT)
- Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT)
- Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori (IT)
- CTO Andrea Alesini (IT)
- Istituti di Ricovero e Cura a Carattere Scientifico (IT)
Publication Details
- Journal
- EJNMMI Research
- Published
- 2025-11-28
- DOI
- https://doi.org/10.1186/s13550-025-01333-4
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00