Metraipolis › archive › dc_82b89e59bc4f
PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation — arXiv:2609.01018
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01018
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:14:05.030Z
- SHA-256 of the archived text
b4294b85726aa3da123c44c1f826e78bf1535d272614e9d9788245cce1d184b3- Stable URL of this page
https://metraipolis.com/documento/dc_82b89e59bc4f
How to cite
PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation — arXiv:2609.01018 — arXiv (en), https://arxiv.org/abs/2609.01018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_82b89e59bc4f (Metraipolis archive dc_82b89e59bc4f, sha256 b4294b85726aa3da123c44c1f826e78bf1535d272614e9d9788245cce1d184b3)
BibTeX
@misc{dc82b89e59bc4f,
title = {PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation — arXiv:2609.01018},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01018},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_82b89e59bc4f; sha256 b4294b85726aa3da123c44c1f826e78bf1535d272614e9d9788245cce1d184b3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Medical Physics (physics.med-ph) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01018 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:00:59.019Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).