Metraipolis › archive › dc_e4e12acec5c3

Optimization of Deep Learning Model for Denoising Dose Profiles in Proton Therapy — arXiv:2610.08843

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08843
License (as archived)
CC0-1.0
Archived
2026-10-08T14:11:43.766Z
SHA-256 of the archived text
0a259d46fa477031a6c41199a8bc883252c235b9cd194104a48e34766b453bb0
Stable URL of this page
https://metraipolis.com/documento/dc_e4e12acec5c3

How to cite

Optimization of Deep Learning Model for Denoising Dose Profiles in Proton Therapy — arXiv:2610.08843 — arXiv (en), https://arxiv.org/abs/2610.08843 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4e12acec5c3 (Metraipolis archive dc_e4e12acec5c3, sha256 0a259d46fa477031a6c41199a8bc883252c235b9cd194104a48e34766b453bb0)
BibTeX
@misc{dce4e12acec5c3,
  title = {Optimization of Deep Learning Model for Denoising Dose Profiles in Proton Therapy — arXiv:2610.08843},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08843},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4e12acec5c3; sha256 0a259d46fa477031a6c41199a8bc883252c235b9cd194104a48e34766b453bb0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08843. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Proton therapy offers a dosimetric advantage over conventional radiotherapy through the Bragg peak, enabling precise dose delivery to the tumour while sparing surrounding tissue. Monte Carlo (MC) simulation provides the most accurate dose calculation but is computationally expensive for clinical workflows. A promising compromise is to simulate with a reduced number of primary histories and recover a high-quality dose distribution through a deep learning denoising step. In this work, we take a 3D multiscale U-Net from recent literature as a case study and investigate two improvements critical for clinical deployment. First, we replace the standard MSE training objective with a differentiable $\gamma$-index-based loss, extended to native 3D operation, and demonstrate that directly optimising the clinical evaluation metric yields a mean Gamma Passing Rate of 99.47\% at 2mm/2\% and 95.67\% at 1mm/1\% on the test set, compared to 92.10\% and 71.13\% for MSE. Second, we apply L1-norm structured filter pruning to reduce the model's memory footprint, achieving a 13.3\% parameter reduction with negligible performance loss under partial pruning, and 20\% reduction under full-block pruning after fine-tuning.

Tema degli esploratori: scienze della vita e salute (elenco arXiv q-bio.QM, nuovi lavori del giorno).
Categorie arXiv: Quantitative Methods (q-bio.QM) ; Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2610.08843 — 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 2026-10-08T13:26:30.514Z dalla pagina https://arxiv.org/list/q-bio.QM/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).