AI-Augmented Adaptive Digital Twin Modeling for Brain Tumor Evolution Prediction and Treatment Scheduling

2026-07-15

AI Summary

This study addresses the challenge of long-term, precise prediction of brain tumor growth, which is hindered by spatial heterogeneity, inter-patient variability, and complex interactions with anatomical structures. To overcome these limitations, the authors propose the first AI-augmented adaptive digital twin framework that integrates a mechanistic reaction-diffusion model, a 3D residual neural network, recursive online twin updating, and model predictive control (MPC) to enable patient-specific tumor evolution forecasting and treatment scheduling optimization. Experimental results demonstrate that the hybrid model reduces voxel-wise mean squared error by 84.3% and improves the Dice coefficient by 43.5% on synthetic data compared to baseline methods. Recursive online updating further decreases prediction error by 45.9%, while MPC-based optimization reduces terminal tumor burden by 22.4%, substantially enhancing the efficacy of personalized, dynamic treatment strategies.

Abstract

Brain tumor progression exhibits spatially heterogeneous growth, patient-specific treatment response, and complex interactions with surrounding anatomy, making accurate long-term prediction challenging. We propose an AI-augmented adaptive digital twin (DT) framework for brain tumor evolution prediction and treatment scheduling. The framework integrates an interpretable reaction--diffusion (RD) model, a 3D residual learning module for model-form correction, patient-specific DT updating during recursive rollout, and model predictive control (MPC) for constrained chemotherapy and radiotherapy scheduling. Experiments on 387 synthetic tumor trajectories with 120-step evolution show that the baseline RD model captures tumor location and overall temporal behavior but underestimates heterogeneous tumor burden during long-horizon prediction. Hybrid RD--residual modeling reduces masked voxel-wise mean squared error by 84.3% and increases Dice overlap by 43.5% relative to the RD baseline under dense simulated observations. Online DT updating further reduces mean squared error by 45.9% and improves Dice overlap by 9.6% compared with the non-updated hybrid model. In MPC-based scheduling simulations, the updated DT controller reduces final tumor burden by 22.4% relative to a fixed treatment schedule under the terminal-burden objective. Together, these results demonstrate a unified framework for patient-specific initialization, mechanistic modeling, adaptive learning, and constrained treatment optimization. Although validated using patient-data-informed synthetic trajectories rather than clinical longitudinal data, the proposed framework establishes a foundation for future translation to real-world adaptive treatment planning.

Problem

• brain tumor evolution
• spatial heterogeneity
• treatment response
• long-term prediction
• patient-specific modeling

Innovation

• adaptive digital twin
• reaction-diffusion model
• residual learning
• model predictive control
• tumor evolution prediction