| Autor: |
Weidner J, Ezhov I, Balcerak M, Metz MC, Litvinov S, Kaltenbach S, Feiner L, Lux L, Kofler F, Lipkova J, Latz J, Rueckert D, Menze B, Wiestler B |
| Jazyk: |
angličtina |
| Zdroj: |
ArXiv [ArXiv] 2024 Mar 07. Date of Electronic Publication: 2024 Mar 07. |
| Abstrakt: |
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. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
