000302814 001__ 302814
000302814 005__ 20250720021401.0
000302814 0247_ $$2doi$$a10.1016/j.radonc.2025.111031
000302814 0247_ $$2pmid$$apmid:40618900
000302814 0247_ $$2ISSN$$a0167-8140
000302814 0247_ $$2ISSN$$a1879-0887
000302814 0247_ $$2altmetric$$aaltmetric:179096850
000302814 037__ $$aDKFZ-2025-01354
000302814 041__ $$aEnglish
000302814 082__ $$a610
000302814 1001_ $$aErdur, Ayhan Can$$b0
000302814 245__ $$aImproving risk assessment of local failure in brain metastases patients using vision transformers - A multicentric development and validation study.
000302814 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2025
000302814 3367_ $$2DRIVER$$aarticle
000302814 3367_ $$2DataCite$$aOutput Types/Journal article
000302814 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1752657850_10334
000302814 3367_ $$2BibTeX$$aARTICLE
000302814 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000302814 3367_ $$00$$2EndNote$$aJournal Article
000302814 520__ $$aThis study investigates the use of Vision Transformers (ViTs) to predict Freedom from Local Failure (FFLF) in patients with brain metastases using pre-operative MRI scans. The goal is to develop a model that enhances risk stratification and informs personalized treatment strategies.Within the AURORA retrospective trial, patients (n = 352) who received surgical resection followed by post-operative stereotactic radiotherapy (SRT) were collected from seven hospitals. We trained our ViT for the direct image-to-risk task on T1-CE and FLAIR sequences and combined clinical features along the way. We employed segmentation-guided image modifications, model adaptations, and specialized patient sampling strategies during training. The model was evaluated with five-fold cross-validation and ensemble learning across all validation runs. An external, international test cohort (n = 99) within the dataset was used to assess the generalization capabilities of the model, and saliency maps were generated for explainability analysis.We achieved a competent C-Index score of 0.7982 on the test cohort, surpassing all clinical, CNN-based, and hybrid baselines. Kaplan-Meier analysis showed significant FFLF risk stratification. Saliency maps focusing on the BM core confirmed that model explanations aligned with expert observations.Our ViT-based model offers a potential for personalized treatment strategies and follow-up regimens in patients with brain metastases. It provides an alternative to radiomics as a robust, automated tool for clinical workflows, capable of improving patient outcomes through effective risk assessment and stratification.
000302814 536__ $$0G:(DE-HGF)POF4-899$$a899 - ohne Topic (POF4-899)$$cPOF4-899$$fPOF IV$$x0
000302814 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000302814 650_7 $$2Other$$aArtificial Intelligence
000302814 650_7 $$2Other$$aBrain metastases
000302814 650_7 $$2Other$$aStereotactic radiotherapy
000302814 650_7 $$2Other$$aVision Transformers
000302814 7001_ $$aScholz, Daniel$$b1
000302814 7001_ $$aNguyen, Q Mai$$b2
000302814 7001_ $$aBuchner, Josef A$$b3
000302814 7001_ $$aMayinger, Michael$$b4
000302814 7001_ $$aChrist, Sebastian M$$b5
000302814 7001_ $$aBrunner, Thomas B$$b6
000302814 7001_ $$aWittig, Andrea$$b7
000302814 7001_ $$aZimmer, Claus$$b8
000302814 7001_ $$aMeyer, Bernhard$$b9
000302814 7001_ $$aGuckenberger, Matthias$$b10
000302814 7001_ $$aAndratschke, Nicolaus$$b11
000302814 7001_ $$aEl Shafie, Rami A$$b12
000302814 7001_ $$aDebus, J Urgen$$b13
000302814 7001_ $$aRogers, Susanne$$b14
000302814 7001_ $$aRiesterer, Oliver$$b15
000302814 7001_ $$aSchulze, Katrin$$b16
000302814 7001_ $$aFeldmann, Horst J$$b17
000302814 7001_ $$aBlanck, Oliver$$b18
000302814 7001_ $$0P:(DE-HGF)0$$aZamboglou, Constantinos$$b19
000302814 7001_ $$0P:(DE-HGF)0$$aBilger-Z, Angelika$$b20
000302814 7001_ $$0P:(DE-HGF)0$$aGrosu, Anca L$$b21
000302814 7001_ $$aWolff, Robert$$b22
000302814 7001_ $$0P:(DE-HGF)0$$aEitz, Kerstin A$$b23
000302814 7001_ $$0P:(DE-HGF)0$$aCombs, Stephanie E$$b24
000302814 7001_ $$0P:(DE-HGF)0$$aBernhardt, Denise$$b25
000302814 7001_ $$aWiestler, Benedikt$$b26
000302814 7001_ $$aRueckert, Daniel$$b27
000302814 7001_ $$0P:(DE-HGF)0$$aPeeken, Jan C$$b28
000302814 773__ $$0PERI:(DE-600)1500707-8$$a10.1016/j.radonc.2025.111031$$gVol. 210, p. 111031 -$$p111031$$tRadiotherapy and oncology$$v210$$x0167-8140$$y2025
000302814 909CO $$ooai:inrepo02.dkfz.de:302814$$pVDB
000302814 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b19$$kDKFZ
000302814 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b20$$kDKFZ
000302814 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b21$$kDKFZ
000302814 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b23$$kDKFZ
000302814 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b24$$kDKFZ
000302814 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b25$$kDKFZ
000302814 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b28$$kDKFZ
000302814 9131_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000302814 9141_ $$y2025
000302814 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2025-01-07$$wger
000302814 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bRADIOTHER ONCOL : 2022$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2025-01-07
000302814 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bRADIOTHER ONCOL : 2022$$d2025-01-07
000302814 9201_ $$0I:(DE-He78)FR01-20160331$$kFR01$$lDKTK Koordinierungsstelle Freiburg$$x0
000302814 9201_ $$0I:(DE-He78)MU01-20160331$$kMU01$$lDKTK Koordinierungsstelle München$$x1
000302814 980__ $$ajournal
000302814 980__ $$aVDB
000302814 980__ $$aI:(DE-He78)FR01-20160331
000302814 980__ $$aI:(DE-He78)MU01-20160331
000302814 980__ $$aUNRESTRICTED