A Learnable Prior Improves Inverse Tumor Growth Modeling
Abstract
Biophysical modeling, particularly involving partial differential equations (PDEs), offers significant potential for tailoring disease treatment protocols to individual patients. However, the inverse problem-solving aspect of these models presents a substantial challenge, either due to the high computational requirements of model-based approaches or the limited robustness of deep learning (DL) methods. We propose a novel framework that leverages the unique strengths of both approaches in a synergistic manner. Our method incorporates a DL ensemble for initial parameter estimation, facilitating efficient downstream evolutionary sampling initialized with this DL-based prior. We showcase the effectiveness of integrating a rapid deep-learning algorithm with a high-precision evolution strategy in estimating brain tumor cell concentrations from magnetic resonance images. The DL-Prior plays a pivotal role, significantly constraining the effective sampling-parameter space. This reduction results in a fivefold convergence acceleration and a Dice-score of 95%.
Cite
@article{arxiv.2403.04500,
title = {A Learnable Prior Improves Inverse Tumor Growth Modeling},
author = {Jonas Weidner and Ivan Ezhov and Michal Balcerak and Marie-Christin Metz and Sergey Litvinov and Sebastian Kaltenbach and Leonhard Feiner and Laurin Lux and Florian Kofler and Jana Lipkova and Jonas Latz and Daniel Rueckert and Bjoern Menze and Benedikt Wiestler},
journal= {arXiv preprint arXiv:2403.04500},
year = {2024}
}