A Learnable Prior Improves Inverse Tumor Growth Modeling
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 comp...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on medical imaging Jg. 44; H. 3; S. 1297 - 1307 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
IEEE
01.03.2025
|
| Schlagworte: | |
| ISSN: | 0278-0062, 1558-254X, 1558-254X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| 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%. |
|---|---|
| AbstractList | 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%.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%. 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%. |
| Author | Balcerak, Michal Kaltenbach, Sebastian Feiner, Leonhard Kofler, Florian Ezhov, Ivan Menze, Bjoern Litvinov, Sergey Lipkova, Jana Metz, Marie-Christin Latz, Jonas Wiestler, Benedikt Weidner, Jonas Lux, Laurin Rueckert, Daniel |
| Author_xml | – sequence: 1 givenname: Jonas orcidid: 0009-0003-6784-9738 surname: Weidner fullname: Weidner, Jonas email: j.weidner@tum.de organization: Department of Computer Science and the Center for Translational Cancer Research (TranslaTUM), Technical University of Munich, Munich, Germany – sequence: 2 givenname: Ivan orcidid: 0000-0002-0862-6513 surname: Ezhov fullname: Ezhov, Ivan email: ivan.ezhov@tum.de organization: Department of Computer Science and the Center for Translational Cancer Research (TranslaTUM), Technical University of Munich, Munich, Germany – sequence: 3 givenname: Michal surname: Balcerak fullname: Balcerak, Michal email: michal.balcerak@uzh.ch organization: Department of Quantitative Biomedicine, University of Zurich, Zürich, Switzerland – sequence: 4 givenname: Marie-Christin surname: Metz fullname: Metz, Marie-Christin email: marie.metz@tum.de organization: Department of Neuroradiology, School of Medicine and Health, Technical University of Munich, Munich, Germany – sequence: 5 givenname: Sergey surname: Litvinov fullname: Litvinov, Sergey email: slitvinov@seas.harvard.edu organization: School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA – sequence: 6 givenname: Sebastian orcidid: 0000-0002-4261-7282 surname: Kaltenbach fullname: Kaltenbach, Sebastian email: skaltenbach@seas.harvard.edu organization: School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA – sequence: 7 givenname: Leonhard surname: Feiner fullname: Feiner, Leonhard email: leo.feiner@tum.de organization: Department of Computer Science and the Center for Translational Cancer Research (TranslaTUM), Technical University of Munich, Munich, Germany – sequence: 8 givenname: Laurin orcidid: 0009-0003-7359-6212 surname: Lux fullname: Lux, Laurin email: laurin.lux@tum.de organization: Department of Computer Science and the Center for Translational Cancer Research (TranslaTUM), Technical University of Munich, Munich, Germany – sequence: 9 givenname: Florian surname: Kofler fullname: Kofler, Florian email: florian.kofler@helmholtz-munich.de organization: Helmholtz AI, Helmholtz Zentrum München, Oberschleißheim, Germany – sequence: 10 givenname: Jana surname: Lipkova fullname: Lipkova, Jana email: jlipkova@hs.uci.edu organization: Department of Pathology, The University of California at Irvine, Irvine, CA, USA – sequence: 11 givenname: Jonas orcidid: 0000-0002-4600-0247 surname: Latz fullname: Latz, Jonas email: jonas.latz@manchester.ac.uk organization: Department of Mathematics, The University of Manchester, Manchester, U.K – sequence: 12 givenname: Daniel orcidid: 0000-0002-5683-5889 surname: Rueckert fullname: Rueckert, Daniel email: daniel.rueckert@tum.de organization: Department of Computing, Biomedical Image Analysis Group, Imperial College London, London, U.K – sequence: 13 givenname: Bjoern orcidid: 0000-0003-4136-5690 surname: Menze fullname: Menze, Bjoern email: bjoern.menze@uzh.ch organization: Department of Quantitative Biomedicine, University of Zurich, Zürich, Switzerland – sequence: 14 givenname: Benedikt orcidid: 0000-0002-2963-7772 surname: Wiestler fullname: Wiestler, Benedikt email: b.wiestler@tum.de organization: Department of Neuroradiology, School of Medicine and Health, Technical University of Munich, Munich, Germany |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/39514352$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kM1Lw0AQxRep2A-9exDJ0Uvq7FeaPRbRGmjRQwVvYZNMdCUfdTep-N-7pVXEg6eB4ffem3ljMmjaBgk5pzClFNT1epVMGTAx5UIJYOyIjKiUccikeB6QEbBZHAJEbEjGzr0BUCFBnZAhV5IKLtmIxPNgido2OqsweLSmtUFSb2y7RRckzRatw2Dd1369sO1H9xqs2gIr07yckuNSVw7PDnNCnu5u1zf34fJhkdzMl2HOGXShZowjUM5UXpSohECFWUZZrJWMNJMKkeYSPKs5FlBqFmGGlOYZ5hKl5hNytff1R7336Lq0Ni7HqtINtr1LuffiPsRnTMjlAe2zGot0Y02t7Wf6_a0HYA_ktnXOYvmDUEh3haa-0HRXaHoo1EuiP5LcdLozbdNZbar_hBd7oUHEXzkzEQuI-Bd9HIE6 |
| CODEN | ITMID4 |
| CitedBy_id | crossref_primary_10_1016_j_ejmp_2024_104881 crossref_primary_10_1038_s41467_025_60366_4 |
| Cites_doi | 10.1007/s00259-018-4180-3 10.1109/TMI.2014.2377694 10.1158/0008-5472.CAN-05-3166 10.1109/TMI.2019.2902044 10.1109/TMI.2022.3221913 10.1007/978-3-319-24571-3_51 10.7759/cureus.6914 10.1016/j.media.2024.103423 10.1093/imamat/hxae011 10.3892/ijo.2016.3595 10.1016/S0140-6736(23)01054-1 10.1093/noajnl/vdad171 10.1098/rsos.221444 10.1109/CVPR.2016.90 10.2307/1932409.JSTOR1932409 10.1038/s41571-020-00447-z 10.1142/S0219525902000572 10.1137/22S1472814 10.2307/2682801 10.1016/j.media.2022.102672 10.1162/106365603321828970 10.3390/cancers12030728 10.1016/j.cma.2017.08.009 10.1016/j.bulm.2004.08.001 10.1007/978-3-030-72084-1_15 10.1080/02664763.2018.1441383 10.1093/neuonc/noaa200 10.1007/978-3-030-87199-4_8 10.1093/imammb/dqq011 10.1016/j.neuroimage.2024.120583 10.1097/nen.0b013e31802d9000 10.1109/TMI.2023.3298637 10.1145/2330784.2330919 10.1016/j.jtbi.2013.01.014 10.1016/j.radonc.2023.109663 10.1098/rsif.2021.0922 10.3389/fnins.2020.00125 10.1162/106365601750190398 10.1007/s00285-015-0888-x 10.1007/978-3-030-59713-9_53 10.1056/NEJMicm1704713 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1109/TMI.2024.3494022 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Engineering |
| EISSN | 1558-254X |
| EndPage | 1307 |
| ExternalDocumentID | 39514352 10_1109_TMI_2024_3494022 10748406 |
| Genre | orig-research Journal Article Research Support, N.I.H., Extramural |
| GrantInformation_xml | – fundername: European High Performance Computing Joint Undertaking (EuroHPC) grantid: DCoMEX 956201-H2020-JTI-EuroHPC-2019-1 – fundername: Helmut Horten Stiftung; Helmut-Horten-Foundation funderid: 10.13039/501100013850 – fundername: Deutsche Forschungsgemeinschaft (DFG) grantid: 504320104 funderid: 10.13039/501100001659 – fundername: NIH grantid: R01CA269948 – fundername: NCI NIH HHS grantid: R01 CA269948 |
| GroupedDBID | --- -DZ -~X .GJ 0R~ 29I 4.4 53G 5GY 5RE 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ACPRK AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7X8 |
| ID | FETCH-LOGICAL-c320t-a223e01329cdfe944e9ebb128a956a259ee1c50320a3ed0fa26ebe11cbec5e5a3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001447560800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0278-0062 1558-254X |
| IngestDate | Sun Nov 09 14:27:57 EST 2025 Wed Jul 30 01:47:48 EDT 2025 Tue Nov 18 22:12:49 EST 2025 Sat Nov 29 08:06:21 EST 2025 Wed Aug 27 01:45:47 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c320t-a223e01329cdfe944e9ebb128a956a259ee1c50320a3ed0fa26ebe11cbec5e5a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-0862-6513 0000-0003-4136-5690 0000-0002-2963-7772 0000-0002-5683-5889 0000-0002-4600-0247 0009-0003-7359-6212 0009-0003-6784-9738 0000-0002-4261-7282 |
| PMID | 39514352 |
| PQID | 3128322301 |
| PQPubID | 23479 |
| PageCount | 11 |
| ParticipantIDs | pubmed_primary_39514352 crossref_primary_10_1109_TMI_2024_3494022 crossref_citationtrail_10_1109_TMI_2024_3494022 proquest_miscellaneous_3128322301 ieee_primary_10748406 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-03-01 |
| PublicationDateYYYYMMDD | 2025-03-01 |
| PublicationDate_xml | – month: 03 year: 2025 text: 2025-03-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on medical imaging |
| PublicationTitleAbbrev | TMI |
| PublicationTitleAlternate | IEEE Trans Med Imaging |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref18 Pabisz (ref10) 2024 ref24 Jin (ref22); 36 ref23 ref45 ref26 ref25 ref20 ref42 ref41 ref44 ref43 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 Zhao (ref21) 2022 Balcerak (ref19) 2023 38495563 - ArXiv. 2024 Nov 6:arXiv:2403.04500v2. |
| References_xml | – volume: 36 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref22 article-title: PETAL: Physics emulation through averaged linearizations for solving inverse problems – ident: ref44 doi: 10.1007/s00259-018-4180-3 – ident: ref25 doi: 10.1109/TMI.2014.2377694 – ident: ref36 doi: 10.1158/0008-5472.CAN-05-3166 – ident: ref12 doi: 10.1109/TMI.2019.2902044 – ident: ref5 doi: 10.1109/TMI.2022.3221913 – ident: ref11 doi: 10.1007/978-3-319-24571-3_51 – ident: ref38 doi: 10.7759/cureus.6914 – ident: ref15 doi: 10.1016/j.media.2024.103423 – ident: ref18 doi: 10.1093/imamat/hxae011 – ident: ref40 doi: 10.3892/ijo.2016.3595 – ident: ref1 doi: 10.1016/S0140-6736(23)01054-1 – ident: ref45 doi: 10.1093/noajnl/vdad171 – ident: ref6 doi: 10.1098/rsos.221444 – year: 2023 ident: ref19 article-title: Individualizing glioma radiotherapy planning by optimization of data and physics-informed discrete loss publication-title: arXiv:2312.05063 – ident: ref26 doi: 10.1109/CVPR.2016.90 – ident: ref30 doi: 10.2307/1932409.JSTOR1932409 – ident: ref3 doi: 10.1038/s41571-020-00447-z – ident: ref8 doi: 10.1142/S0219525902000572 – ident: ref16 doi: 10.1137/22S1472814 – ident: ref29 doi: 10.2307/2682801 – ident: ref14 doi: 10.1016/j.media.2022.102672 – ident: ref28 doi: 10.1162/106365603321828970 – ident: ref43 doi: 10.3390/cancers12030728 – year: 2022 ident: ref21 article-title: Learning to solve PDE-constrained inverse problems with graph networks publication-title: arXiv:2206.00711 – ident: ref9 doi: 10.1016/j.cma.2017.08.009 – ident: ref37 doi: 10.1016/j.bulm.2004.08.001 – ident: ref13 doi: 10.1007/978-3-030-72084-1_15 – ident: ref33 doi: 10.1080/02664763.2018.1441383 – ident: ref2 doi: 10.1093/neuonc/noaa200 – ident: ref17 doi: 10.1007/978-3-030-87199-4_8 – ident: ref7 doi: 10.1093/imammb/dqq011 – ident: ref20 doi: 10.1016/j.neuroimage.2024.120583 – ident: ref24 doi: 10.1097/nen.0b013e31802d9000 – ident: ref42 doi: 10.1109/TMI.2023.3298637 – ident: ref32 doi: 10.1145/2330784.2330919 – ident: ref41 doi: 10.1016/j.jtbi.2013.01.014 – ident: ref4 doi: 10.1016/j.radonc.2023.109663 – ident: ref34 doi: 10.1098/rsif.2021.0922 – ident: ref23 doi: 10.3389/fnins.2020.00125 – year: 2024 ident: ref10 article-title: Augmenting MRI scan data with real-time predictions of glioblastoma brain tumor evolution using faster exponential time integrators publication-title: arXiv:2402.02273 – ident: ref27 doi: 10.1162/106365601750190398 – ident: ref31 doi: 10.1007/s00285-015-0888-x – ident: ref35 doi: 10.1007/978-3-030-59713-9_53 – ident: ref39 doi: 10.1056/NEJMicm1704713 – reference: 38495563 - ArXiv. 2024 Nov 6:arXiv:2403.04500v2. |
| SSID | ssj0014509 |
| Score | 2.474066 |
| Snippet | Biophysical modeling, particularly involving partial differential equations (PDEs), offers significant potential for tailoring disease treatment protocols to... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1297 |
| SubjectTerms | Algorithms Biological system modeling Brain - diagnostic imaging Brain modeling Brain Neoplasms - diagnostic imaging Brain Neoplasms - pathology CMA-ES Computational modeling Deep Learning evolutionary sampling Humans Image Processing, Computer-Assisted - methods Image segmentation Individualized brain tumor modeling inverse biophysics learnable prior Magnetic Resonance Imaging - methods Mathematical models Models, Biological MRI Predictive models Radiation therapy Robustness Training Tumors |
| Title | A Learnable Prior Improves Inverse Tumor Growth Modeling |
| URI | https://ieeexplore.ieee.org/document/10748406 https://www.ncbi.nlm.nih.gov/pubmed/39514352 https://www.proquest.com/docview/3128322301 |
| Volume | 44 |
| WOSCitedRecordID | wos001447560800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 1558-254X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014509 issn: 0278-0062 databaseCode: RIE dateStart: 19820101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5skaIHn1Xro0Tw4iFtNrtpskcRqx4qPVToLWySCRa0lbT19zuzSUs9KHgLYTeE-WaZmZ3HB3ATqizASBhXJXSalETPNQkBIhI_zMNQijzKLdlE-PISjcd6WDWr214YRLTFZ9jhR5vLz2bpkq_Kulw8SAFJrwa1MOyVzVrrlIEKynoOn0fGej1_lZP0dHc0eKZI0FcdnsVCRmsHGlJbT8H_YY4sv8rvrqY1Of39f_7sAexVvqVzVyrDIWzh9Ah2NyYOHkFjUOXSjyG6c-xwVe6dcobFZFY45Q0Dzh2evlHM0RktP-j1I4XqizeHadO4eb0Jr_2H0f2TW_EouKn0vYVryAVAzqnoNMtRK4Uak4QMk6HgyFD8gyjSgJnUjcTMy43fI2iFSAnfAAMjT6A-nU3xDJxckpQzoTi5pmSoaJn2PJNkJhAmjXQLuitxxmk1ZJy5Lt5jG2x4OiYsYsYirrBowe16x2c5YOOPtU2W88a6UsQtuF5BFtPp4JSHmeJsOY-lYComCrNEC05LLNe7Vypw_stXL2DHZ7JfW3B2CfVFscQr2E6_FpN50SYVHEdtq4Lfar_S0A |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB584ePg-1GfEbx4SJvNbprssYgvbEsPFXoLm2SCgraStv5-ZzZp0YOCtxB2Q5hvlpnZeXwAV6HKAoyEcVVCp0lJ9FyTECAi8cM8DKXIo9ySTYTdbjQY6F7VrG57YRDRFp9hnR9tLj8bpVO-Kmtw8SAFJM1FWGbqrKpda540UEFZ0eHz0Fiv6c-ykp5u9DuPFAv6qs7TWMhsrcOq1NZX8H8YJMuw8ruzaY3O3dY_f3cbNivv0mmV6rADCzjchY1vMwd3YbVTZdP3IGo5drwqd085veJ1VDjlHQOOHZ6_UYzR6U_f6fU9BeuTF4eJ07h9fR-e7277Nw9uxaTgptL3Jq4hJwA5q6LTLEetFGpMEjJNhsIjQxEQokgD5lI3EjMvN36TwBUiJYQDDIw8gKXhaIhH4OSSpJwJxek1JUNFy7TnmSQzgTBppGvQmIkzTqsx48x28RbbcMPTMWERMxZxhUUNruc7PsoRG3-s3Wc5f1tXirgGlzPIYjofnPQwQxxNx7EUTMZEgZaowWGJ5Xz3TAWOf_nqBaw99DvtuP3YfTqBdZ-pf2352SksTYopnsFK-jl5HRfnVhG_AJus1TE |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Learnable+Prior+Improves+Inverse+Tumor+Growth+Modeling&rft.jtitle=IEEE+transactions+on+medical+imaging&rft.au=Weidner%2C+Jonas&rft.au=Ezhov%2C+Ivan&rft.au=Balcerak%2C+Michal&rft.au=Metz%2C+Marie-Christin&rft.date=2025-03-01&rft.eissn=1558-254X&rft.volume=44&rft.issue=3&rft.spage=1297&rft_id=info:doi/10.1109%2FTMI.2024.3494022&rft_id=info%3Apmid%2F39514352&rft.externalDocID=39514352 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0278-0062&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0278-0062&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0278-0062&client=summon |