Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 27 min ago
Peer-reviewedCC BY 4.0Medical Physics

DoseRAD2026: A benchmark dataset for AI‐accelerated photon and proton dose calculation in radiotherapy

  • Fan Xiao1
  • Nikolaos Delopoulos1
  • Niklas Wahl2,3
  • Lennart Volz4
  • Lina Bucher2,3,5,6
  • Matteo Maspero7
  • Miguel Palacios8
  • Muheng Li9
  • Samir Schulz2,3,5,10
  • Viktor Rogowski11
  • Ye Zhang9
  • Zoltan Perko12,13
4 more authors
  • Christopher Kurz1
  • George Dedes1,14
  • Guillaume Landry1,15,16
  • Adrian Thummerer1,17,18
18 affiliations
  1. 1Department of Radiation Oncology LMU University Hospital, LMU Munich Munich Germany
  2. 2Division of Medical Physics in Radiation Oncology German Cancer Research Center (DKFZ) Heidelberg Germany
  3. 3National Center for Radiation Research in Oncology (NCRO) Heidelberg Institute for Radiation Oncology (HIRO) Heidelberg Germany
  4. 4Biophysics Department GSI Helmholtzzentrum für Schwerionenforschung Darmstadt Germany
  5. 5Department of Physics and Astronomy Heidelberg University Heidelberg Germany
  6. 6Institute of Biomedical Engineering Karlsruhe Institute of Technology Baden‐Württemberg Germany
  7. 7Department of Radiotherapy University Medical Center Utrecht Utrecht Netherlands
  8. 8Department of Radiation Oncology, Amsterdam UMC location Vrije Universiteit Amsterdam Cancer Center Amsterdam, Cancer Treatment and Quality of Life Amsterdam Netherlands
  9. 9Center for Proton Therapy, Paul Scherrer Institute (PSI) Villigen Switzerland
  10. 10Department of Radiation Oncology University Hospital Heidelberg Heidelberg Germany
  11. 11Radiation Physics, Department of Hematology, Oncology, and Radiation Physics Skåne University Hospital Lund Sweden
  12. 12Department of Radiation Science and Technology Delft University of Technology Delft the Netherlands
  13. 13Radformation Inc. New York USA
  14. 14Department of Medical Physics, Faculty of Physics Ludwig‐Maximilians‐Universität München Munich Germany
  15. 15German Cancer Consortium (DKTK), partner site Munich, a partnership between DKFZ and LMU University Hospital Munich Germany
  16. 16Bavarian Cancer Research Center (BZKF) Munich Germany
  17. 17Department of Radiation Oncology, Inselspital Bern University Hospital and University of Bern Bern Switzerland
  18. 18Department of Digital Medicine, Faculty of Medicine University of Bern Bern Switzerland
Read full textPDFDOICite

Abstract

Purpose: Accurate dose calculation is a fundamental component of modern radiotherapy, enabling precise tumor irradiation while sparing surrounding healthy tissue. With the increasing adoption of magnetic resonance imaging (MRI)‐guided radiotherapy and growing interest in real‐time adaptive radiotherapy, there is a demand for fast and accurate dose calculation techniques on both computed tomography (CT) and MRI. To facilitate research in this area, the DoseRAD2026 dataset and accompanying challenge introduce a publicly available benchmark dataset comprising paired CT and MRI data with corresponding beam‐level photon and proton Monte Carlo (MC) dose distributions, enabling the development and systematic evaluation of advanced dose calculation and prediction methods.

Acquisition and validation methods: The DoseRAD2026 dataset comprises paired CT and MRI data from 115 patients (75 training, 40 testing) treated on a hybrid MRI‐linear accelerator (MRI‐linac) for thoracic or abdominal lesions and is derived from the SynthRAD2025 dataset. Image pre‐processing included deformable image registration, air‐cavity correction and resampling. Ground‐truth photon (6 MV) and proton dose distributions were generated using open‐source MC dose calculation algorithms and resulted in a training dataset of 40,500 photon beams and 81,000 proton beamlets.

Data format and usage notes: The dataset is organized into photon and proton subsets, each comprising paired CT‐MRI images, beam‐level dose distributions, and JSON files specifying patient‐specific beam configurations. Data are provided in compressed MetaImage (.mha) format with standardized naming linking dose files to beam parameters in the JSON files. The dataset is released under a CC BY‐NC 4.0 license, with the training set available from April 2026 and the test set withheld until March 2030.

Potential applications: The DoseRAD2026 dataset enables benchmarking and development of fast dose calculation methods for radiotherapy applications. Potential use cases include rapid beam‐level dose estimation for photon and proton therapy, MRI‐based dose calculation in MRI‐only and MRI‐guided radiotherapy workflows, and support for real‐time adaptive radiotherapy strategies.

Related

  1. Comparison of Different Models in Calculation of Tumor Control Probability and Normal Tissue Complication Probability in Breast Cancer Radiotherapy.
    Hayder Tareq, Mahdi Ghorbani, Mohammad Reza Deevband +2
    Journal of medical signals and sensorsPeer-reviewedCC BY-NC-SAFull textApplied physics & instrumentationEurope PMC
  2. Assessment of Calculation Grid Size Impact on Plan Quality and Gamma Evaluation Metrics in Intracranial Stereotactic Radiotherapy
    Ravindra Shende, Joyce Alexis, R. S. Rahul
    Journal of Medical PhysicsPeer-reviewedCC BY-NC-SAFull textApplied physics & instrumentationDOAJ
  3. Separating active irradiation from passive outcome learning in radiotherapy: a finite-model computational benchmark
    Yuntao Wang
    arXivPreprintarXiv licenceFull textBiological & medical physicsarXiv
  4. OpenGray: a benchmark for evaluating the decisions of radiotherapy planning agents
    Humza Nusrat, Kundan Thind
    arXivPreprintCC BY 4.0Full textBiological & medical physicsarXiv
  5. From Radiotherapy Dataset to Cherenkov Dose Map: A Digital Linac Monte Carlo Simulation Pipeline
    Xianghuan He, Changyu Sun, Andy N. Wiles +4
    arXivPreprintarXiv licenceFull textBiological & medical physicsarXiv

Cite

BibTeXRIS
BibTeX
@article{xiao2026doserad2026,
  title = {{DoseRAD2026: A benchmark dataset for AI‐accelerated photon and proton dose calculation in radiotherapy}},
  author = {Fan Xiao and Nikolaos Delopoulos and Niklas Wahl and Lennart Volz and Lina Bucher and Matteo Maspero and Miguel Palacios and Muheng Li and Samir Schulz and Viktor Rogowski and Ye Zhang and Zoltan Perko and Christopher Kurz and George Dedes and Guillaume Landry and Adrian Thummerer},
  journal = {Medical Physics},
  year = {2026},
  month = oct,
  doi = {10.1002/mp.70714},
  url = {https://doi.org/10.1002/mp.70714},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - DoseRAD2026: A benchmark dataset for AI‐accelerated photon and proton dose calculation in radiotherapy
AU  - Fan Xiao
AU  - Nikolaos Delopoulos
AU  - Niklas Wahl
AU  - Lennart Volz
AU  - Lina Bucher
AU  - Matteo Maspero
AU  - Miguel Palacios
AU  - Muheng Li
AU  - Samir Schulz
AU  - Viktor Rogowski
AU  - Ye Zhang
AU  - Zoltan Perko
AU  - Christopher Kurz
AU  - George Dedes
AU  - Guillaume Landry
AU  - Adrian Thummerer
PY  - 2026
DA  - 2026/10/26
JO  - Medical Physics
DO  - 10.1002/mp.70714
UR  - https://doi.org/10.1002/mp.70714
AB  - Purpose: Accurate dose calculation is a fundamental component of modern radiotherapy, enabling precise tumor irradiation while sparing surrounding healthy tissue. With the increasing adoption of magnetic resonance imaging (MRI)‐guided radiotherapy and growing interest in real‐time adaptive radiotherapy, there is a demand for fast and accurate dose calculation techniques on both computed tomography (CT) and MRI. To facilitate research in this area, the DoseRAD2026 dataset and accompanying challenge introduce a publicly available benchmark dataset comprising paired CT and MRI data with corresponding beam‐level photon and proton Monte Carlo (MC) dose distributions, enabling the development and systematic evaluation of advanced dose calculation and prediction methods.  Acquisition and validation methods: The DoseRAD2026 dataset comprises paired CT and MRI data from 115 patients (75 training, 40 testing) treated on a hybrid MRI‐linear accelerator (MRI‐linac) for thoracic or abdominal lesions and is derived from the SynthRAD2025 dataset. Image pre‐processing included deformable image registration, air‐cavity correction and resampling. Ground‐truth photon (6 MV) and proton dose distributions were generated using open‐source MC dose calculation algorithms and resulted in a training dataset of 40,500 photon beams and 81,000 proton beamlets.  Data format and usage notes: The dataset is organized into photon and proton subsets, each comprising paired CT‐MRI images, beam‐level dose distributions, and JSON files specifying patient‐specific beam configurations. Data are provided in compressed MetaImage (.mha) format with standardized naming linking dose files to beam parameters in the JSON files. The dataset is released under a CC BY‐NC 4.0 license, with the training set available from April 2026 and the test set withheld until March 2030.  Potential applications: The DoseRAD2026 dataset enables benchmarking and development of fast dose calculation methods for radiotherapy applications. Potential use cases include rapid beam‐level dose estimation for photon and proton therapy, MRI‐based dose calculation in MRI‐only and MRI‐guided radiotherapy workflows, and support for real‐time adaptive radiotherapy strategies.
SN  - 0094-2405
SN  - 2473-4209
ER  -