PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Weidner, J.* ; Ezhov, I.* ; Balcerak, M.* ; Metz, M.C.* ; Litvinov, S.* ; Kaltenbach, S.* ; Feiner, L.F.* ; Lux, L.* ; Kofler, F. ; Lipkova, J.* ; Latz, J.* ; Rueckert, D.* ; Menze, B.* ; Wiestler, B.*

A learnable prior improves inverse tumor growth modeling.

IEEE Trans. Med. Imaging 44, 1297-1307 (2024)
Publ. Version/Full Text Postprint DOI
Open Access Green
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%.
Impact Factor
Scopus SNIP
Altmetric
8.900
3.322
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Keywords Cma-es ; Evolutionary Sampling ; Individualized Brain Tumor Modeling ; Inverse Biophysics ; Learnable Prior ; Mri; Glioma Growth; Evolution; Adaptation; Invasion
Language english
Publication Year 2024
HGF-reported in Year 2024
ISSN (print) / ISBN 0278-0062
e-ISSN 1558-254X
Journal IEEE Transactions on Medical Imaging
Quellenangaben Volume: 44, Issue: 3, Pages: 1297-1307 Article Number: , Supplement: ,
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Publishing Place New York, NY [u.a.]
Reviewing status Peer reviewed
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-530001-001
Grants Helmut-Horten-Foundation
NIH
European High Performance Computing Joint Undertaking (EuroHPC)
Deutsche Forschungsgemeinschaft (DFG)
DOI 10.1109/TMI.2024.3494022
WOS ID 001447560800001
Scopus ID 85210182657
Erfassungsdatum 2024-12-02
[➜Report correction]