Deep learning prediction of scenario doses for direct plan robustness evaluations in IMPT for head-and-neck.

Autor:	Nomer HAA; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands., Knuth F; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands., van Genderingen J; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands., Nguyen D; Department of Radiation Oncology, UT Southwestern Medical Center, Medical Artificial Intelligence and Automation (MAIA) Laboratory, Dallas, TX, United States of America., Sattler M; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands., Zolnay A; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands., Oelfke U; Joint Department of Physics, The Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, London, United Kingdom., Jiang S; Department of Radiation Oncology, UT Southwestern Medical Center, Medical Artificial Intelligence and Automation (MAIA) Laboratory, Dallas, TX, United States of America., Rossi L; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands., Heijmen BJM; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands., Breedveld S; Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center, Rotterdam, The Netherlands.
Jazyk:	angličtina
Zdroj:	Physics in medicine and biology [Phys Med Biol] 2024 Nov 12; Vol. 69 (22). Date of Electronic Publication: 2024 Nov 12.
DOI:	10.1088/1361-6560/ad8c95
Abstrakt:	Objective . Intensity modulated proton therapy (IMPT) is susceptible to uncertainties in patient setup and proton range. Robust optimization is employed in IMPT treatment planning to ensure sufficient coverage of the clinical target volume (CTV) in predefined scenarios, albeit at a price of increased planning times. We investigated a deep learning (DL) strategy for dose predictions in individual error scenarios in head and neck cancer IMPT treatment planning, enabling direct evaluation of plan robustness. The model is able to differentiate between scenarios by using embeddings of the scenario index. Approach . To accommodate resolution disparities in planning CT-scans and accommodate the setup error scenarios, we introduced scenario-specific isocentric distance maps as inputs to the DL models. For 392 H&N cancer patients, high-quality 9-scenario ground truth (GT) robust plans were generated with wish-list driven fully automated multi-criteria optimization. The scenario index is converted to one-hot-vector that is used to derive the scenarios embeddings through the training of the DL model, aiding the model to predict a scenario specific dose distribution. Main results . The model achieved within 1%-point of agreement with the GT the predictedV95%of the voxelwise minimum dose for CTV Low and CTV High for 96% and 75% respectively of the test patients. Considering all robustness scenarios, median differences were 0.035%-point for CTV HighV95%, 0.11%-point for CTV LowV95%, 0.29 GyE for parotidsDmean, 0.7 GyE for submandibular glandsDmeanand 0.9 GyE for oral cavityDmean. Prediction of full 3D dose distributions for all scenarios took around 14 s. Significance . Predicting individual scenarios for robust proton therapy using DL dose prediction is feasible, enabling direct robustness evaluation of the predicted scenario doses. (Creative Commons Attribution license.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu