A Learnable Prior Improves Inverse Tumor Growth Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913572306550784 |
|---|---|
| author | Weidner, Jonas Ezhov, Ivan Balcerak, Michal Metz, Marie-Christin Litvinov, Sergey Kaltenbach, Sebastian Feiner, Leonhard Lux, Laurin Kofler, Florian Lipkova, Jana Latz, Jonas Rueckert, Daniel Menze, Bjoern Wiestler, Benedikt |
| author_facet | Weidner, Jonas Ezhov, Ivan Balcerak, Michal Metz, Marie-Christin Litvinov, Sergey Kaltenbach, Sebastian Feiner, Leonhard Lux, Laurin Kofler, Florian Lipkova, Jana Latz, Jonas Rueckert, Daniel Menze, Bjoern Wiestler, Benedikt |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04500 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Learnable Prior Improves Inverse Tumor Growth Modeling Weidner, Jonas Ezhov, Ivan Balcerak, Michal Metz, Marie-Christin Litvinov, Sergey Kaltenbach, Sebastian Feiner, Leonhard Lux, Laurin Kofler, Florian Lipkova, Jana Latz, Jonas Rueckert, Daniel Menze, Bjoern Wiestler, Benedikt Medical Physics Artificial Intelligence 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%. |
| title | A Learnable Prior Improves Inverse Tumor Growth Modeling |
| topic | Medical Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2403.04500 |