An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study

2026-09-30

AI Summary

This study addresses the conflict between rapid anatomical changes and time-consuming offline replanning in head-and-neck proton therapy by proposing an uncertainty-guided digital twin framework. Methodologically, it integrates a pretrained CT foundation model, two-step multi-atlas deformable registration, and uncertainty quantification to accurately predict treatment-day anatomy and generate online adaptive plans. This work achieves a paradigm shift from passive offline replanning to proactive online adaptation, substantially improving treatment timeliness. Experimental results demonstrate that the generated online plans achieve quality comparable to clinically approved offline plans while meeting target coverage requirements, offering an efficient new pathway for online adaptive proton therapy.

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.

Problem

• proton therapy
• head and neck cancer
• online adaptive planning
• anatomical changes
• offline replanning

Innovation

• Digital Twin
• Online Adaptive Proton Therapy
• Deformable Image Registration
• Foundation Model
• Uncertainty-Guided