A comprehensive comparative study of generative adversarial network architectures for synthetic computed tomography generation in the abdomen
The study provided a new benchmark for the abdominal sCT generation task, showing its clinical applicability for treatment planning and further advancing the state-of-the-art. This study also confirmed that image similarity metrics alone can not reliably predict small dosimetric deviations within a clinical threshold; but contributed by identifying specific metrics that correlate with DVH discrepancies above ± 5%, offering valuable tools for training, evaluation, and standardization of reporting across studies.
Authors
- Riccardo Dal Bello (ORCID: https://orcid.org/0000-0002-8755-377X)
- Stephanie Tanadini‐Lang (ORCID: https://orcid.org/0000-0002-4387-1522)
- Matthias Gückenberger (ORCID: https://orcid.org/0000-0002-7146-9071)
- Philipp Wallimann (ORCID: https://orcid.org/0000-0002-7110-6617)
- Nicolaus Andratschke (ORCID: https://orcid.org/0000-0003-3647-5916)
- Manuel Günther (ORCID: https://orcid.org/0000-0003-1489-7448)
- Mariia Lapaeva (ORCID: https://orcid.org/0000-0003-3280-3409)
- Agustina La Greca Saint‐Esteven (ORCID: https://orcid.org/0000-0003-4504-611X)
Institutions
- Zurich Insurance Group (Switzerland) (CH)
- ETH Zurich (CH)
- University Hospital of Zurich (CH)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-08-01
- DOI
- https://doi.org/10.1002/mp.18038
- Citations
- 3
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 5.65
Funders
- ViewRay
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung