Patient-specific prediction of glioblastoma growth via reduced order modeling and neural networks

TL;DR

This paper introduces a real-time, patient-specific glioblastoma growth prediction model combining reduced order modeling and neural networks, enabling faster and accurate tumor evolution forecasting from neuroimaging data.

Contribution

It presents a novel framework integrating diffuse-interface modeling, reduced-order techniques, and neural network surrogates for personalized glioblastoma prediction.

Findings

Achieved significant computational speed-up with high accuracy.

Identified key biophysical parameters influencing tumor growth.

Demonstrated robustness through sensitivity analyses.

Abstract

Glioblastoma is among the most aggressive brain tumors in adults, characterized by patient-specific invasion patterns driven by the underlying brain microstructure. In this work, we present a proof-of-concept for a mathematical model of GBL growth, enabling real-time prediction and patient-specific parameter identification from longitudinal neuroimaging data. The framework exploits a diffuse-interface mathematical model to describe the tumor evolution and a reduced-order modeling strategy, relying on proper orthogonal decomposition, trained on synthetic data derived from patient-specific brain anatomies reconstructed from magnetic resonance imaging and diffusion tensor imaging. A neural network surrogate learns the inverse mapping from tumor evolution to model parameters, achieving significant computational speed-up while preserving high accuracy. To ensure robustness and interpretability, we perform both global and local sensitivity analyses, identifying the key biophysical parameters governing tumor dynamics and assessing the stability of the inverse problem solution. These results establish a methodological foundation for future clinical deployment of patient-specific digital twins in neuro-oncology.