Deep learning dose prediction to approach Erasmus-iCycle dosimetric plan quality within seconds for instantaneous treatment planning
Although even for 1000 training patients there was no convergence in obtained prediction accuracy yet, the accuracy for the 6-level model with 1000 training patients may be adequate for the pursued instantaneous planning, which is subject of further research.
Authors
- Linda Rossi (ORCID: https://orcid.org/0000-0002-3705-2504)
- Steve Jiang (ORCID: https://orcid.org/0000-0002-3083-6752)
- A.W. Sharfo (ORCID: https://orcid.org/0000-0003-4487-4108)
- András Zolnay (ORCID: https://orcid.org/0000-0001-8476-9092)
- Hazem A. A. Nomer (ORCID: https://orcid.org/0000-0003-0959-6069)
- Sebastiaan Breedveld (ORCID: https://orcid.org/0000-0001-8954-4554)
- Luca Incrocci (ORCID: https://orcid.org/0000-0001-8981-6310)
- Uwe Oelfke (ORCID: https://orcid.org/0000-0003-2309-0814)
- Dan Nguyen (ORCID: https://orcid.org/0000-0002-9590-0655)
- Franziska Knuth (ORCID: https://orcid.org/0000-0002-6998-8681)
- Ben Heijmen (ORCID: https://orcid.org/0000-0003-1647-0528)
- Joep van Genderingen (ORCID: https://orcid.org/0000-0002-2787-5726)
Institutions
- Royal Marsden NHS Foundation Trust (GB)
- Institute of Cancer Research (GB)
- Southwestern Medical Center (US)
- Erasmus MC Cancer Institute (NL)
- The University of Texas Southwestern Medical Center (US)
Publication Details
- Journal
- Radiotherapy and Oncology
- Published
- 2024-12-06
- DOI
- https://doi.org/10.1016/j.radonc.2024.110662
- Citations
- 7
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 4.25
Funders
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek