4D Pencil Beam Treatment Plan with Conditional Weight Predictions
Abstract
Objective. This work aims to accelerate our four-dimensional (4D) proton pencil beam delivery strategy, which incorporates respiratory motion into a dynamic treatment plan, to improve dose conformity and treatment efficiency for gantry-less and magnet-free scanner designs. Approach. To accelerate the generation and adaptation of 4D treatment plans, we propose a conditional hybrid ResNet18-Transformer model for predicting pencil beam weights. The model predicts either the full set of pencil beam weights or a subset thereof. Main Results. The conditional model can successfully predict the remaining beam weights of a treatment, and the results suggest that extending this approach to full treatment prediction is feasible but requires further investigation. Significance. The acceleration of 4D treatment generation via pencil beam weight prediction takes us one step closer to the feasibility of treating mobile targets with simplified, gantry-less, and magnet-free scanner designs. Reducing system complexity while preserving dosimetric conformity may offer a pathway toward more accessible and cost-effective proton beam therapy for motion-affected tumours. Our code is available here: https://github.com/NairVonMuehlenen/Pencil-Beam-Weight-Prediction
Related
- Magnet-Free Proton Therapy with 4D Pencil Beam Delivery Optimisation
- PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation
- PyDoseRT Photon: Physics-Guided Pencil-Beam Dose Calculation with Neural Priors and Residual Correction for CT and MRI
- Cardio-respiratory-gated proton pencil beam scanning for cardiac ablation: workflow and end-to-end validation
- Comparison of different solutions for applying patient-specific beam quality in treatment planning CT imaging.
BibTeX
@misc{muehlenen2026pencil,
title = {{4D Pencil Beam Treatment Plan with Conditional Weight Predictions}},
author = {Nair N von Muehlenen and Florentin Bieder and Philippe C Cattin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.26294},
eprint = {2609.26294},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.26294},
}
RIS
TY - UNPB
TI - 4D Pencil Beam Treatment Plan with Conditional Weight Predictions
AU - Nair N von Muehlenen
AU - Florentin Bieder
AU - Philippe C Cattin
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.26294
UR - https://arxiv.org/abs/2609.26294
AB - Objective. This work aims to accelerate our four-dimensional (4D) proton pencil beam delivery strategy, which incorporates respiratory motion into a dynamic treatment plan, to improve dose conformity and treatment efficiency for gantry-less and magnet-free scanner designs. Approach. To accelerate the generation and adaptation of 4D treatment plans, we propose a conditional hybrid ResNet18-Transformer model for predicting pencil beam weights. The model predicts either the full set of pencil beam weights or a subset thereof. Main Results. The conditional model can successfully predict the remaining beam weights of a treatment, and the results suggest that extending this approach to full treatment prediction is feasible but requires further investigation. Significance. The acceleration of 4D treatment generation via pencil beam weight prediction takes us one step closer to the feasibility of treating mobile targets with simplified, gantry-less, and magnet-free scanner designs. Reducing system complexity while preserving dosimetric conformity may offer a pathway toward more accessible and cost-effective proton beam therapy for motion-affected tumours. Our code is available here: https://github.com/NairVonMuehlenen/Pencil-Beam-Weight-Prediction
ER -