TY  - JOUR
AU  - Schneider, Moritz
AU  - Gutwein, Simon
AU  - Mönnich, David
AU  - Gani, Cihan
AU  - Fischer, Paul
AU  - Baumgartner, Christian F
AU  - Thorwarth, Daniela
TI  - Development and comprehensive clinical validation of a deep neural network for radiation dose modelling to enhance magnetic resonance imaging guided radiotherapy.
JO  - Physics & Imaging in Radiation Oncology
VL  - 33
SN  - 2405-6316
CY  - Amsterdam [u. a.]
PB  - Elsevier Science
M1  - DKFZ-2025-00673
SP  - 100723
PY  - 2025
AB  - 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
KW  - Artificial intelligence (Other)
KW  - Dose calculation (Other)
KW  - MRI-guided radiotherapy (Other)
KW  - Online adaptive radiotherapy (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:40093656
C2  - pmc:PMC11908596
DO  - DOI:10.1016/j.phro.2025.100723
UR  - https://inrepo02.dkfz.de/record/300196
ER  -