{
  "abstract": "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.01018",
  "author_total": 4,
  "authors": [
    {
      "name": "Lukas Zimmermann"
    },
    {
      "name": "Hermann Fuchs"
    },
    {
      "name": "Attila Simkó"
    },
    {
      "name": "Gerd Heilemann"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3phctte0xdj7s.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.01018",
  "fulltext_url": null,
  "id": "3phctte0xdj7s",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.01018",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "physics.med-ph"
    ],
    [
      "openalex",
      "2740|Radiation Therapy and Dosimetry"
    ]
  ],
  "openalex": "W7206152524",
  "pdf_url": "https://arxiv.org/pdf/2609.01018",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3phctte0xdj7s.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:00Z",
      "native_id": "2609.01018",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.01018"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.med-ph",
      "subfield": "biological-medical"
    }
  ],
  "title": "PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation",
  "title_text": "PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:00Z",
  "url": "https://research.draconitic.com/paper/3phctte0xdj7s",
  "venue": "arXiv",
  "versions": []
}