An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study
Abstract
Objective: Head and neck (HN) proton therapy spans six to seven weeks of anatomical change, while offline replanning takes about a week. We present an uncertainty-guided digital twin (UGDT) framework that forecasts treatment-day anatomy before treatment and evaluate whether it generates online adaptive proton therapy (APT) plans of clinical quality. Approach: A library of 302 longitudinal deformations from 88 previously treated HN patients was transported onto each new patient's treatment planning CT (TPCT) using two-step multi-atlas deformable image registration (DIR) built on a pretrained CT foundation model, generating about 284 predicted CTs (pdCTs) with contours per patient. Dispersion of propagated clinical target volume (CTV) contours defined a patient-specific robust margin. In ten patients, the quality assurance CT (QACT) triggering a replan represented treatment-day anatomy, and the physician-approved replan was the baseline. The pdCT most similar to the QACT (pdCT-H) and one from the lowest quartile (pdCT-L) were planned to within about 5% of baseline plan quality, forward-calculated on the QACT, and reoptimized to generate online APT plans. Main results: pdCT plans scored within -0.7% (pdCT-H) and -1.0% (pdCT-L) of baseline. Forward calculation on QACT reduced high-dose CTV D98% to 88.3% and 85.5%. After online reoptimization, D98% recovered to 98.3 +/- 0.3% and 98.2 +/- 0.3%, versus 98.5 +/- 0.4% at baseline. Spinal cord and brainstem doses remained below tolerance, and plan quality scores were within -1.1% (p = 0.19) and -1.7% (p = 0.01) of baseline. Significance: UGDT generated online APT plans comparable in quality to physician-approved offline replans using anatomy forecast before treatment, enabling a transition from reactive offline replanning toward anticipatory online adaptation.
Related
- A digital-twin framework for forecasting treatment-day imaging with contour uncertainty in adaptive proton radiotherapy
- Deep Learning-based Volumetric Modulated Arc Therapy Dose Prediction with Uncertainty Quantification for Left- and Right-sided Breast Cancer: A Single-institution Feasibility Study
- Model-Uncertainty-Aware Digital Twins for Non-Markovian Quantum Repeater Memories
- Evolutionary dynamics of collective-risk social dilemma game with risk uncertainty and adaptive strategy
- Feasibility of reduced PTV margins in magnetic resonance image-guided online adaptive radiotherapy for bladder cancer: a personalised approach.
BibTeX
@misc{wu2026uncertaintyguided,
title = {{An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study}},
author = {Yizhou Wu and Ryan J. Sanford and Huiqiao Xie and Jie Ding and Shupeng Chen and Tung-Ho Wu and Ping-Hsiu Wu and Justin Roper and Jun Zhou and Minglei Kang and Bill Stokes and Sibo Tian and David S. Yu and Xiaofeng Yang and Chih-Wei Chang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.39010},
eprint = {2609.39010},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.39010},
}
RIS
TY - UNPB
TI - An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study
AU - Yizhou Wu
AU - Ryan J. Sanford
AU - Huiqiao Xie
AU - Jie Ding
AU - Shupeng Chen
AU - Tung-Ho Wu
AU - Ping-Hsiu Wu
AU - Justin Roper
AU - Jun Zhou
AU - Minglei Kang
AU - Bill Stokes
AU - Sibo Tian
AU - David S. Yu
AU - Xiaofeng Yang
AU - Chih-Wei Chang
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.39010
UR - https://arxiv.org/abs/2609.39010
AB - Objective: Head and neck (HN) proton therapy spans six to seven weeks of anatomical change, while offline replanning takes about a week. We present an uncertainty-guided digital twin (UGDT) framework that forecasts treatment-day anatomy before treatment and evaluate whether it generates online adaptive proton therapy (APT) plans of clinical quality. Approach: A library of 302 longitudinal deformations from 88 previously treated HN patients was transported onto each new patient's treatment planning CT (TPCT) using two-step multi-atlas deformable image registration (DIR) built on a pretrained CT foundation model, generating about 284 predicted CTs (pdCTs) with contours per patient. Dispersion of propagated clinical target volume (CTV) contours defined a patient-specific robust margin. In ten patients, the quality assurance CT (QACT) triggering a replan represented treatment-day anatomy, and the physician-approved replan was the baseline. The pdCT most similar to the QACT (pdCT-H) and one from the lowest quartile (pdCT-L) were planned to within about 5% of baseline plan quality, forward-calculated on the QACT, and reoptimized to generate online APT plans. Main results: pdCT plans scored within -0.7% (pdCT-H) and -1.0% (pdCT-L) of baseline. Forward calculation on QACT reduced high-dose CTV D98% to 88.3% and 85.5%. After online reoptimization, D98% recovered to 98.3 +/- 0.3% and 98.2 +/- 0.3%, versus 98.5 +/- 0.4% at baseline. Spinal cord and brainstem doses remained below tolerance, and plan quality scores were within -1.1% (p = 0.19) and -1.7% (p = 0.01) of baseline. Significance: UGDT generated online APT plans comparable in quality to physician-approved offline replans using anatomy forecast before treatment, enabling a transition from reactive offline replanning toward anticipatory online adaptation.
ER -