Research Article

Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles

Volume: 17 Number: October, November, December 2026 October 16, 2026

Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles

Abstract

Purpose: Deep learning can accelerate radiotherapy dose prediction, but particle-therapy datasets remain scarce. We evaluated whether a physics-informed ensemble trained exclusively on photon plans could predict proton and carbon-ion dose distributions without particle-dose training. Methods: Using matRad, 90 reference plans (photons, protons and carbon ions) were generated for five anatomies and six beam configurations. A 13-channel tensor combining CT, structure masks and modality-specific ray-tracing/depth-dose channels was input to SOTA-UNet3D, Res-UNet3D and Trans-UNet3D; their voxel-wise mean formed the Voltron ensemble. Leave-one-anatomy-out evaluation used four test anatomies with photon-only training. Performance was assessed with PyMedPhys gamma analysis (3%/3 mm and 2%/2 mm; 10% low-dose threshold) and mean absolute error (MAE). Results: Across four held-out anatomies, mean 3%/3 mm gamma pass rates were 23.5% for photons, 23.3% for protons and 21.5% for carbon ions; 2%/2 mm rates were 15.8%, 15.5% and 14.5%. Mean MAE was approximately 5.2–5.3 Gy. Gamma values reported in an earlier version of this work (73.2/70.8/69.1%) were computed with a non-standard lenient criterion; all values reported here use the standard gamma index. Conclusion: Photon-only training with physics-informed inputs provides a reproducible feasibility baseline for zeroshot particle-dose prediction. Performance is not clinical-grade, but the small cross-modality degradation suggests that anatomical and geometric features learned from photon data can transfer to particle therapy.

Keywords

Supporting Institution

The author declares that this study received no financial support.

Ethical Statement

Not applicable. This study involved only in-silico simulation on a public phantom and demonstration dataset; therefore, no ethics committee approval was required.

Thanks

The author thanks the matRad development group at the German Cancer Research Center (DKFZ, Heidelberg, Germany) for making the matRad toolkit and its example dataset publicly available, which made this study possible.

References

  1. 1. Atun R, Jaffray DA, Barton MB, et al. Expanding global access to radiotherapy. Lancet Oncol. 2015;16:1153–86. DOI:10.1016/S1470-2045(15)00222-3
  2. 2. Kamada T, Tsujii H, Blakely EA, et al. Carbon ion radiotherapy in Japan: an assessment of 20 years of clinical experience. Lancet Oncol. 2015;16:e93–100. DOI:10.1016/S1470-2045(14)70412-7
  3. 3. Tsujii H and Kamada T. A review of update clinical results of carbon ion radiotherapy. Jpn J Clin Oncol. 2012;42:670–85. DOI:10.1093/jjco/hys104
  4. 4. Schulz-Ertner D and Tsujii H. Particle radiation therapy using proton and heavier ion beams. J Clin Oncol. 2007;25:953–64. DOI:10.1200/JCO.2006.09.7816
  5. 5. Mohan R and Grosshans D. Proton therapy – present and future. Adv Drug Deliv Rev. 2017;109:26–44. DOI:10.1016/j.addr.2016.11.006
  6. 6. Ronneberger O, Fischer P and Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, et al., eds. MICCAI 2015. Cham: Springer; 2015. p. 234–41. DOI:10.1007/978-3-319-24574-4_28
  7. 7. Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin S, et al., eds. MICCAI 2016. Cham: Springer; 2016. p. 424–32. DOI:10.1007/978-3-319-46723-8_49
  8. 8. Babier A, Zhang B, Mahmood R, et al. OpenKBP: the open-access knowledge-based planning grand challenge and dataset. Med Phys. 2021;48:5549–61. DOI:10.1002/mp.14845

Details

Primary Language

English

Subjects

Radiology and Organ Imaging, Clinical Sciences (Other)

Journal Section

Research Article

Publication Date

October 16, 2026

Submission Date

May 22, 2026

Acceptance Date

August 25, 2026

Published in Issue

Year 2026 Volume: 17 Number: October, November, December 2026

APA
Bedir, M. E. (2026). Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles. Acıbadem Üniversitesi Sağlık Bilimleri Dergisi, 17(October, November, December 2026). https://doi.org/10.31067/acusaglik.1957061
AMA
1.Bedir ME. Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles. Acibadem Univ Saglik Bilim Derg. 2026;17(October, November, December 2026). doi:10.31067/acusaglik.1957061
Chicago
Bedir, Muhammed Emin. 2026. “Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles”. Acıbadem Üniversitesi Sağlık Bilimleri Dergisi 17 (October, November, December 2026). https://doi.org/10.31067/acusaglik.1957061.
EndNote
Bedir ME (October 1, 2026) Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles. Acıbadem Üniversitesi Sağlık Bilimleri Dergisi 17 October, November, December 2026
IEEE
[1]M. E. Bedir, “Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles”, Acibadem Univ Saglik Bilim Derg, vol. 17, no. October, November, December 2026, Oct. 2026, doi: 10.31067/acusaglik.1957061.
ISNAD
Bedir, Muhammed Emin. “Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles”. Acıbadem Üniversitesi Sağlık Bilimleri Dergisi 17/October, November, December 2026 (October 1, 2026). https://doi.org/10.31067/acusaglik.1957061.
JAMA
1.Bedir ME. Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles. Acibadem Univ Saglik Bilim Derg. 2026;17. doi:10.31067/acusaglik.1957061.
MLA
Bedir, Muhammed Emin. “Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles”. Acıbadem Üniversitesi Sağlık Bilimleri Dergisi, vol. 17, no. October, November, December 2026, Oct. 2026, doi:10.31067/acusaglik.1957061.
Vancouver
1.Muhammed Emin Bedir. Zero-Shot Cross-Modality Dose Prediction in Particle Therapy via Physics-Informed Ensembles. Acibadem Univ Saglik Bilim Derg. 2026 Oct. 1;17(October, November, December 2026). doi:10.31067/acusaglik.1957061