%0 Journal Article %A Schneider, Moritz %A Gutwein, Simon %A Mönnich, David %A Gani, Cihan %A Fischer, Paul %A Baumgartner, Christian F %A Thorwarth, Daniela %T Development and comprehensive clinical validation of a deep neural network for radiation dose modelling to enhance magnetic resonance imaging guided radiotherapy. %J Physics & Imaging in Radiation Oncology %V 33 %@ 2405-6316 %C Amsterdam [u. a.] %I Elsevier Science %M DKFZ-2025-00673 %P 100723 %D 2025 %X Online adaptive magnetic resonance imaging (MRI)-guided radiotherapy requires fast dose calculation algorithms to reduce intra-fraction motion uncertainties and improve workflow efficiency. While Monte-Carlo simulations are precise but computationally intensive, neural networks promise fast and accurate dose modelling in strong magnetic fields. This study aimed to train and evaluate a deep neural network for dose modelling in MRI-guided radiotherapy using a comprehensive clinical dataset.A dataset of 6595 clinical irradiation segments from 125 1.5 T MRI-Linac radiotherapy plans for various tumors sites was used. A 3D U-Net was trained with 3961 segments using 3D imaging data and field parameters as input, Root Mean Squared Error and a custom loss function, with full Monte-Carlo simulations as ground truth. For 2656 segments from 50 patients, gamma pass rates (γ-PR) for 3 mm/3 %K Artificial intelligence (Other) %K Dose calculation (Other) %K MRI-guided radiotherapy (Other) %K Online adaptive radiotherapy (Other) %F PUB:(DE-HGF)16 %9 Journal Article %$ pmid:40093656 %2 pmc:PMC11908596 %R 10.1016/j.phro.2025.100723 %U https://inrepo02.dkfz.de/record/300196