Toward Actionable Digital Twins for Radiation-Based Imaging and Therapy: Mathematical Formulation, Modular Workflow, and an OpenKBP-Based Dose-Surrogate Prototype

TL;DR

This paper introduces a modular framework for digital twins in radiation therapy, integrating patient data, models, and decision modules, demonstrated through an open-data benchmark and a GPU-accelerated dose prediction prototype.

Contribution

It presents a formalized, reproducible framework for actionable digital twins in radiation therapy, including a GPU-ready implementation and uncertainty-aware evaluation methods.

Findings

Achieved mean dose score of 2.65 Gy on 100-patient test set.

Model inference time per patient is approximately 0.58 seconds.

Complete three-fraction loop executes in 10.3 seconds.

Abstract

Digital twins for radiation-based imaging and therapy are most useful when they assimilate patient data, quantify predictive uncertainty, and support clinically constrained decisions. This paper presents a modular framework for actionable digital twins in radiation-based imaging and therapy and instantiates its reproducible open-data component using the \openkbpfull{} benchmark. The framework couples PatientData, Model, Solver, Calibration, and Decision modules and formalizes latent-state updating, uncertainty propagation, and chance-constrained action selection. As an initial implementation, we build a GPU-ready PyTorch/MONAI reimplementation of the \openkbp{} starter pipeline: an 11-channel, 19.2M-parameter 3D U-Net trained with a masked loss over the feasible region and equipped with Monte Carlo dropout for voxel-wise epistemic uncertainty. To emulate the update loop on a static benchmark, we introduce decoder-only proxy recalibration and illustrate uncertainty-aware virtual-therapy evaluation using DVH-based and biological utilities. A complete three-fraction loop including recalibration, Monte Carlo inference, and spatial optimization executes in 10.3~s. On the 100-patient test set, the model achieved mean dose and DVH scores of 2.65 and 1.82~Gy, respectively, with 0.58~s mean inference time per patient. The \openkbp{} case study thus serves as a reproducible test bed for dose prediction, uncertainty propagation, and proxy closed-loop adaptation, while future institutional studies will address longitudinal calibration with delivered-dose logs and repeat imaging.