001010196 001__ 1010196
001010196 005__ 20230929112543.0
001010196 0247_ $$2doi$$a10.1007/s11060-023-04367-7
001010196 0247_ $$2ISSN$$a0167-594x
001010196 0247_ $$2ISSN$$a0167-594X
001010196 0247_ $$2ISSN$$a1573-7373
001010196 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-03007
001010196 0247_ $$2pmid$$a37382806
001010196 0247_ $$2WOS$$aWOS:001022079900002
001010196 037__ $$aFZJ-2023-03007
001010196 082__ $$a610
001010196 1001_ $$00000-0003-4150-7265$$aMeißner, Anna-Katharina$$b0$$eCorresponding author
001010196 245__ $$aRadiomics for the non-invasive prediction of PD-L1 expression in patients with brain metastases secondary to non-small cell lung cancer
001010196 260__ $$aDordrecht [u.a.]$$bSpringer Science + Business Media B.V$$c2023
001010196 3367_ $$2DRIVER$$aarticle
001010196 3367_ $$2DataCite$$aOutput Types/Journal article
001010196 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1694755908_17124
001010196 3367_ $$2BibTeX$$aARTICLE
001010196 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001010196 3367_ $$00$$2EndNote$$aJournal Article
001010196 500__ $$a„Open access publication funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – 491111487“
001010196 520__ $$aBackgroundThe expression level of the programmed cell death ligand 1 (PD-L1) appears to be a predictor for response to immunotherapy using checkpoint inhibitors in patients with non-small cell lung cancer (NSCLC). As differences in terms of PD-L1 expression levels in the extracranial primary tumor and the brain metastases may occur, a reliable method for the non-invasive assessment of the intracranial PD-L1 expression is, therefore of clinical value. Here, we evaluated the potential of radiomics for a non-invasive prediction of PD-L1 expression in patients with brain metastases secondary to NSCLC.Patients and methodsFifty-three NSCLC patients with brain metastases from two academic neuro-oncological centers (group 1, n = 36 patients; group 2, n = 17 patients) underwent tumor resection with a subsequent immunohistochemical evaluation of the PD-L1 expression. Brain metastases were manually segmented on preoperative T1-weighted contrast-enhanced MRI. Group 1 was used for model training and validation, group 2 for model testing. After image pre-processing and radiomics feature extraction, a test-retest analysis was performed to identify robust features prior to feature selection. The radiomics model was trained and validated using random stratified cross-validation. Finally, the best-performing radiomics model was applied to the test data. Diagnostic performance was evaluated using receiver operating characteristic (ROC) analyses.ResultsAn intracranial PD-L1 expression (i.e., staining of at least 1% or more of tumor cells) was present in 18 of 36 patients (50%) in group 1, and 7 of 17 patients (41%) in group 2. Univariate analysis identified the contrast-enhancing tumor volume as a significant predictor for PD-L1 expression (area under the ROC curve (AUC), 0.77). A random forest classifier using a four-parameter radiomics signature, including tumor volume, yielded an AUC of 0.83 ± 0.18 in the training data (group 1), and an AUC of 0.84 in the external test data (group 2).ConclusionThe developed radiomics classifiers allows for a non-invasive assessment of the intracranial PD-L1 expression in patients with brain metastases secondary to NSCLC with high accuracy.
001010196 536__ $$0G:(DE-HGF)POF4-5252$$a5252 - Brain Dysfunction and Plasticity (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001010196 536__ $$0G:(GEPRIS)491111487$$aDFG project 491111487 - Open-Access-Publikationskosten / 2022 - 2024 / Forschungszentrum Jülich (OAPKFZJ) (491111487)$$c491111487$$x1
001010196 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001010196 7001_ $$0P:(DE-Juel1)181076$$aGutsche, Robin$$b1$$ufzj
001010196 7001_ $$0P:(DE-Juel1)143792$$aGalldiks, Norbert$$b2$$ufzj
001010196 7001_ $$0P:(DE-Juel1)173675$$aKocher, Martin$$b3$$ufzj
001010196 7001_ $$0P:(DE-HGF)0$$aJünger, Stephanie T.$$b4
001010196 7001_ $$0P:(DE-HGF)0$$aEich, Marie-Lisa$$b5
001010196 7001_ $$0P:(DE-HGF)0$$aNogova, Lucia$$b6
001010196 7001_ $$0P:(DE-HGF)0$$aAraceli, Tommaso$$b7
001010196 7001_ $$0P:(DE-HGF)0$$aSchmidt, Nils Ole$$b8
001010196 7001_ $$0P:(DE-HGF)0$$aRuge, Maximilian I.$$b9
001010196 7001_ $$0P:(DE-HGF)0$$aGoldbrunner, Roland$$b10
001010196 7001_ $$0P:(DE-HGF)0$$aProescholdt, Martin$$b11
001010196 7001_ $$0P:(DE-HGF)0$$aGrau, Stefan$$b12
001010196 7001_ $$0P:(DE-Juel1)145110$$aLohmann, Philipp$$b13$$ufzj
001010196 773__ $$0PERI:(DE-600)2007293-4$$a10.1007/s11060-023-04367-7$$gVol. 163, no. 3, p. 597 - 605$$n3$$p597 - 605$$tJournal of neuro-oncology$$v163$$x0167-594x$$y2023
001010196 8564_ $$uhttps://juser.fz-juelich.de/record/1010196/files/PDF.pdf$$yOpenAccess
001010196 909CO $$ooai:juser.fz-juelich.de:1010196$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001010196 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)181076$$aForschungszentrum Jülich$$b1$$kFZJ
001010196 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)143792$$aForschungszentrum Jülich$$b2$$kFZJ
001010196 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)173675$$aForschungszentrum Jülich$$b3$$kFZJ
001010196 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)145110$$aForschungszentrum Jülich$$b13$$kFZJ
001010196 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5252$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001010196 9141_ $$y2023
001010196 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-08
001010196 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001010196 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-08
001010196 915__ $$0StatID:(DE-HGF)3002$$2StatID$$aDEAL Springer$$d2022-11-08$$wger
001010196 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001010196 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2023-08-20$$wger
001010196 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bJ NEURO-ONCOL : 2022$$d2023-08-20
001010196 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-08-20
001010196 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-08-20
001010196 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-08-20
001010196 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-08-20
001010196 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2023-08-20
001010196 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2023-08-20
001010196 920__ $$lyes
001010196 9201_ $$0I:(DE-Juel1)INM-3-20090406$$kINM-3$$lKognitive Neurowissenschaften$$x0
001010196 9201_ $$0I:(DE-Juel1)INM-4-20090406$$kINM-4$$lPhysik der Medizinischen Bildgebung$$x1
001010196 980__ $$ajournal
001010196 980__ $$aVDB
001010196 980__ $$aI:(DE-Juel1)INM-3-20090406
001010196 980__ $$aI:(DE-Juel1)INM-4-20090406
001010196 980__ $$aUNRESTRICTED
001010196 9801_ $$aFullTexts