DoseRAD2026 Challenge dataset: AI accelerated photon and proton dose calculation for radiotherapy

Fan Xiao; Nikolaos Delopoulos; Niklas Wahl; Lennart Volz; Lina Bucher; Matteo Maspero; Miguel Palacios; Muheng Li

physics.med-phApr 14, 2026

DoseRAD2026 Challenge dataset: AI accelerated photon and proton dose calculation for radiotherapy

Authors: Fan Xiao, Nikolaos Delopoulos, Niklas Wahl, Lennart Volz, Lina Bucher, Matteo Maspero, Miguel Palacios, Muheng Li,

Organizations: Department of Radiation Oncology, LMU University Hospital, LMU Munich, Munich, Germany · Division of Medical Physics in Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany · National Center for Radiation Research in Oncology (NCRO), Heidelberg Institute for Radiation Oncology (HIRO), Heidelberg, Germany · GSI Helmholtzzentrum für Schwerionenforschung, Biophysics Department, Darmstadt, Germany · Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany · Institute of Biomedical Engineering, Karlsruhe Institute of Technology, Baden-Württemberg, Germany · Department of Radiotherapy, University Medical Center Utrecht, Utrecht, Netherlands · Department of Radiation Oncology, Amsterdam UMC location Vrije Universiteit Amsterdam, Cancer Center Amsterdam, Cancer Treatment and Quality of Life, Amsterdam, Netherlands · Center for Proton Therapy, Paul Scherrer Institute (PSI), Villigen, Switzerland · Department of Radiation Oncology, University Hospital Heidelberg, Heidelberg, Germany · Radiation Physics, Department of Hematology, Oncology, and Radiation Physics, Sk˚ane University Hospital, Lund, Sweden · Delft University of Technology, Department of Radiation Science and Technology, Delft, Netherlands · Radformation Inc., New York, US · Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Munich, Germany · German Cancer Consortium (DKTK), partner site Munich, a partnership between DKFZ and LMU University Hospital, Germany · Bavarian Cancer Research Center (BZKF), Munich, Germany · Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland · Department of Digital Medicine, Faculty of Medicine, University of Bern, Bern, Switzerland

Abstract

Purpose: Accurate dose calculation is essential in radiotherapy for precise tumor irradiation while sparing healthy tissue. With the growing adoption of MRI-guided and real-time adaptive radiotherapy, fast and accurate dose calculation on CT and MRI is increasingly needed. The DoseRAD2026 dataset and challenge provide a public benchmark of paired CT and MRI data with beam-level photon and proton Monte Carlo dose distributions for developing and evaluating advanced dose calculation methods. Acquisition and validation methods: The dataset comprises paired CT and MRI from 115 patients (75 training, 40 testing) treated on an MRI-linac for thoracic or abdominal lesions, derived from the SynthRAD2025 dataset. Pre-processing included deformable image registration, air-cavity correction, and resampling. Ground-truth photon (6 MV) and proton dose distributions were computed using open-source Monte Carlo algorithms, yielding 40,500 photon beams and 81,000 proton beamlets. Data format and usage notes: Data are organized into photon and proton subsets with paired CT-MRI images, beam-level dose distributions, and JSON beam configuration files. Files are provided in compressed MetaImage (.mha) format. The dataset is released under CC BY-NC 4.0, with training data available from April 2026 and the test set withheld until March 2030. Potential applications: The dataset supports benchmarking of fast dose calculation methods, including beam-level dose estimation for photon and proton therapy, MRI-based dose calculation in MRI-guided workflows, and real-time adaptive radiotherapy.

Figures & tables

	Thorax		Abdomen
	Train	Test	Train	Test
Manufacturer	ViewRay
Model	MRIdian
Field strength (T)	0.35
Sequence	balanced steady-state free-precession (bSSFP, TrueFISP)
Acquisition	2D, breath-hold, no contrast

Table 1: MRI acquisition parameters for thorax and abdomen datasets (train/test splits). Voxel spacing is reported as in-plane resolution (isotropic); percentages indicate proportion of scans with each value.

	Thorax		Abdomen
	Train	Test	Train	Test
Manufacturer	Canon Medical Aquilion/LB (97%) Siemens SOMATOM Drive (3%)	Canon Medical Aquilion/LB	Canon Medical Aquilion/LB	Canon Medical Aquilion/LB
kVp	120	120	120	120
Exposure time (ms)	500	500	500 (94%) 750 (6%)	500
Tube current (mA)	40 – 305	40 – 140	40 – 440	40 – 190
Rows	512	512	512	512

Table 2: CT acquisition parameters for thorax and abdomen datasets (train/test splits). Voxel spacing is reported as in-plane resolution (isotropic); percentages indicate proportion of scans with each value.

Region	Training	Testing	External Testing	Total
Thoracic	39	14	7	60
Abdominal	36	26	–	62
Total	75	40	7	122

Table 3: Patient distribution in DoseRAD2026 by anatomical region and dataset split. Training and Testing are from SynthRAD2025 Center B.

Figure 1: Representative photon segment dose distributions overlaid on CT (Task 1, top row) and MRI (Task 2, bottom row) images for thoracic (left column) and abdominal (right column) cases.

Figure 2: Representative proton beamlet dose distributions overlaid on CT (Task 3, top row) and MRI (Task 4, bottom row) images for thoracic (left column) and abdominal (right column) cases.

E (MeV)	$\boldsymbol{\sigma_{E}}$ (MeV)	$\boldsymbol{\sigma_{s}}$ (mm)	E (MeV)	$\boldsymbol{\sigma_{E}}$ (MeV)	$\boldsymbol{\sigma_{s}}$ (mm)	E (MeV)	$\boldsymbol{\sigma_{E}}$ (MeV)	$\boldsymbol{\sigma_{s}}$ (mm)
31.73	6.11	7.49	114.54	1.47	5.85	162.93	0.99	4.49
36.80	5.19	7.62	116.53	1.44	5.78	164.45	0.98	4.46
41.38	4.56	7.70	118.49	1.42	5.70	165.96	0.97	4.44
45.60	4.09	7.77	120.43	1.39	5.63	167.46	0.96	4.41
49.54	3.74	7.82	122.34	1.37	5.56	168.95	0.95	4.39
53.25	3.45	7.86	124.23	1.34	5.50	170.43	0.94	4.36

Table 4: Proton beam model parameters: energy, energy spread (

\sigma_{E}

), and spot size (

\sigma_{s}

) for 85 energy levels (values rounded to 2 decimal places).

Component	Repository URL
Pre-processing scripts	https://github.com/DoseRAD2026/preprocessing
Geant4 simulation scripts	https://github.com/DoseRAD2026/geant4-dose-sim
Geant4 toolkit version	https://geant4.web.cern.ch/download/11.0.3.html
matRad VMAT planning scripts	https://github.com/DoseRAD2026/matrad-vmat-example
matRad commit used in this study	https://github.com/e0404/matRad/tree/71c95e96a1ecc7c7e025b9d75240ea009bdbc063
pyRadPlan pencil beam baseline	https://github.com/DoseRAD2026/pyradplan-pb-baseline

Table 5: Availability of DoseRAD2026 code and scripts.

Figure 3: Folder structure for the photon dataset. B, beam; CP, control point.

Figure 4: Folder structure for the proton dataset. B, beam; R, ray; L, beamlet.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Parameter	Description	Value
disp_hwd	The displacement range in voxels of the discretised search space	6
grid_sp	The grid spacing in voxels used for the effective resolution of features and deformable transformation	5
convex_mind_r	The MIND radius in voxels	2
convex_mind_d	The MIND dilation in voxels	2
adam_mind_r	The MIND radius in voxels	1
adam_mind_d	The MIND dilation in voxels	2

Appendix

Table 6: The convexAdam hyperparameters used for MR-to-CT deformable image registration. Detailed description of parameters is provided in Siebert et al. 38 .

Field	Unit	Description
Per beam
beam_idx	–	Sequential beam index (0-indexed)
iso_center	mm	3D coordinate of the beam rotation center in patient
num_mlc_leaf_pairs	–	Number of leaf pairs to shape the segment
control_points	–	Discrete beam delivery sampling points along the arc
Per control point

Appendix

Table 7: Photon plan JSON field description.

Field	Unit	Description
iso_center	mm	3D coordinate of the beam rotation center in patient
Per beam
beam_idx	–	Sequential beam index (0-indexed)
gantry_angle	deg	Angle of the proton beam direction around patient
rays	–	A group of pencil beamlets from the same BEV grid position within the beam
Per ray

Appendix

Table 8: Proton plan JSON field description.

Radiotherapy Dose Prediction

See all 12 papers

Sep 4, 2026

BEAM3R: Beam's-eye-view architecture with Mamba-3 for implicit dose reconstruction

To enable accurate and rapid photon control point and proton beamlet dose calculation in the DoseRAD2026 challenge, we present BEAM3R, a dose estimation framework operating in beam's-eye-view (BEV). Our core innovation combines a Mamba-3 state-space depth-sequence core with physics-based transport conditioning to model long-range depth transport without expensive 3D convolutions. BEAM3R shares a 2D CNN encoder-decoder architecture for photon and proton dose tasks, processing per-plane BEV slices. Proton beamlets are conditioned on water equivalent thickness and remaining range, encoding the parameters determining Bragg peak position. Photon models use a bidirectional Mamba-3 core to capture dose contributions from materials downstream of the calculation point, while the proton model uses a forward core with learned energy-prefix tokens and a Bragg-peak refinement module. To reduce interpolation artifacts and support high spatial resolution, we introduce axial grid alignment of BEV lattices with CT slices and an implicit super-resolution representation via sub-pixel phase packing, evaluated by a differentiable Triton-accelerated resampler that reconstructs packed cubic B-spline coefficients directly in CT space. For MRI-based tasks, synthetic CTs (sCT) are generated by a patch-based conditional GAN with a SwinUNETR backbone. On the preliminary DoseRAD2026 test set, CT-to-photon and CT-to-proton models achieved 1%/1 mm local gamma pass rates of 96.8% and 96.0%, with stratified plan-level MAEs of 0.0041 and 0.0079. Substituting sCT reduced gamma pass rates to 89.7% for photon and 75.4% proton plan level doses, with stratified plan-level MAEs of 0.0093 and 0.0336. Standardised runtimes were 23.4 s and 18.4 s for CT-to-photon and CT-to-proton prediction, increasing to 39.7 s and 42.8 s for the corresponding MRI-based pipelines.

Chen Cheng, Michael Ferraro, James Grover +2

Image X Institute, The University of Sydney, Sydney, Australia

Radiotherapy Dose Prediction Healthcare

Ask PDF

May 13, 2026

Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report

Radiation therapy (RT) requires precise dose delivery over multiple fractions, with CT fundamental for treatment planning due to its electron density information. Repeated CT acquisitions impose radiation exposure and logistical burdens, MRI lacks electron density, and cone-beam CT (CBCT) requires correction for dose calculation. Synthetic CT (sCT) generation addresses these by converting MRI or CBCT into CT-equivalent images with accurate Hounsfield Unit (HU) values, enabling MRI-only RT and CBCT-based adaptive workflows. Building on SynthRAD2023, SynthRAD2025 benchmarked sCT methods on 2,362 patients from five European centers across head and neck, thorax, and abdomen. Two tasks: MRI-to-CT (890 cases) and CBCT-to-CT (1,472 cases), evaluated via image similarity (MAE, PSNR, MS-SSIM), segmentation (Dice, HD95), and dosimetric metrics from photon and proton plans. With 803 participants and 12/13 valid submissions, Task 1 top performance reached MAE

64.8\pm21.3

HU, PSNR

\sim

30 dB, MS-SSIM

\sim

0.936, Dice 0.79, photon

γ_{2\%/2\text{mm}}>98\%

, proton

γ\approx85\%

. Task 2 improved: MAE

48.3\pm13.4

HU, PSNR 32.6 dB, MS-SSIM 0.968, Dice 0.86, photon

γ>99\%

, proton

γ\approx89\%

. Strong image--segmentation correlations (

ρ=0.78

0.79

) but moderate dose correlations confirmed image quality is insufficient as a dosimetric surrogate. Head-and-neck cases were most consistent; thoracic and abdominal cases showed greater variability. Residual errors at tissue interfaces propagate along beam paths, affecting proton dose more than photon. SynthRAD2025 demonstrates that deep learning yields clinically relevant sCTs, especially for CBCT-to-CT, while identifying persistent MRI-to-CT challenges and underscoring dose-based evaluation as essential for clinical validation.

Viktor Rogowski, Maarten L. Terpstra, Niklas Wahl +30

Radiation Physics, Department of Hematology, Oncology, and Radiation Physics, Skåne University Hospital, Lund, Sweden · Medical Radiation Physics, Department of Clinical Sciences Lund, Lund University, Lund, Sweden · Radiotherapy Department, University Medical Center Utrecht, Utrecht, The Netherlands +20

Cone-Beam CT Medical Image Synthesis Medical Image Benchmarks

Ask PDF

Sep 1, 2026

PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation

Architecture category. Hybrid method: a physics-based analytical pencil-beam (PB) dose engine followed by a 3-D convolutional residual-correction network (RepVGG-U-Net). We addressed the DoseRAD2026 proton dose-prediction task with PyDoseRT Proton, a GPU-accelerated engine implemented in PyTorch and augmented by a learned residual toward Monte Carlo (MC) accuracy. A double-Gaussian PB kernel was calibrated to GATE/Geant4 integrated depth doses in water in two stages: a classical per-energy curve fit, then a gradient-based fit of the full 3-D dose through the PyTorch physics engine as it retains a differentiable execution path for gradient-based optimization of dose-dependent objectives. The engine computes each beamlet on a beam's-eye-view (BEV) lattice with variance-preserving Gaussian splitting, an analytic nuclear halo, and a Fermi-Eyges heterogeneity term, then rotates the result into the patient frame. Additionally, a compact residual U-Net predicts an additive correction in BEV space. It is conditioned on voxelwise material-label embeddings, a discrete energy embedding and spot size. The same model was used for all anatomical sites (thoracic and abdominal). It was trained with a patient-space L1 objective emphasizing the scored high-dose region and multi-scale BEV deep supervision. The submitted CT configuration obtained preliminary-test beamlet MAE 0.0066, image-z IDD distance 0.0025, plan MAE 0.0049, 98.30% gamma pass rate (1%/1 mm), and DVH error 0.460.

Lukas Zimmermann, Hermann Fuchs, Attila Simkó +1

Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria · Christian Doppler Laboratory for Image and Knowledge Driven Precision Radiation Oncology, Medical University of Vienna, Vienna, Austria · Department of Diagnostics and Intervention, Umeå University, Umeå, Sweden

Healthcare Radiotherapy Dose Prediction

Ask PDF

Abstract

Radiotherapy Dose Prediction

Explore similar work

BEAM3R: Beam's-eye-view architecture with Mamba-3 for implicit dose reconstruction

Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report

PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation