000908215 001__ 908215
000908215 005__ 20220622190124.0
000908215 037__ $$aFZJ-2022-02466
000908215 082__ $$a610
000908215 1001_ $$0P:(DE-Juel1)145110$$aLohmann, Philipp$$b0
000908215 245__ $$aNIMG-38. NON-INVASIVE PREDICTION OF MGMT PROMOTER METHYLATION USING COMBINED FET PET/MRI RADIOMICS
000908215 260__ $$c2020
000908215 3367_ $$2DataCite$$aText
000908215 3367_ $$0PUB:(DE-HGF)4$$2PUB:(DE-HGF)$$aCommunication$$bcomm$$mcomm$$s1655871122_6306
000908215 3367_ $$2BibTeX$$aMISC
000908215 3367_ $$2ORCID$$aOTHER
000908215 3367_ $$2DINI$$aOther
000908215 3367_ $$04$$2EndNote$$aPersonal Communication
000908215 520__ $$aBACKGROUNDRecently, the Response Assessment in Neuro-Oncology (RANO) Working Group emphasized the additional diagnostic value of amino acid PET in addition to MRI. However, the number of studies using amino acid PET/MRI radiomics is still low. We investigated the potential of combined O-(2-[18F]fluoroethyl)-L-tyrosine (FET) PET/MRI radiomics for the non-invasive prediction of the O6-methylguanine-DNA methyl-transferase (MGMT) promoter methylation status in glioma patients.METHODSSeventy-one patients with newly diagnosed glioma (predominantly WHO grade III and IV glioma, 82%) underwent a hybrid FET PET/MRI scan. Forty-six patients (65%) had a methylated MGMT promoter. The tumor and tumor subregions were manually segmented on conventional MRI. In total, 199 standardized features were obtained from FET PET, contrast-enhanced T1-weighted, T2-weighted, and fluid attenuated inversion recovery (FLAIR) MRI. After feature extraction and data normalization, patients were randomly assigned to a training and a test dataset for final model evaluation in a ratio of 70/30, with a balanced distribution of the MGMT promoter methylation status. Feature selection was performed by recursive feature elimination using random forest regressors. For the final model generation, the number of features was limited to seven to avoid data overfitting. Different algorithms for model generation were compared, and the model performance in the training data was assessed by 5-fold cross-validation. Finally, the best performing models were applied to the test dataset to evaluate the robustness of the models.RESULTSIn the test dataset, the best radiomics signatures obtained from MRI or FET PET alone achieved diagnostic accuracies for the prediction of the MGMT promoter methylation of 64% and 70%, respectively. In contrast, the highest diagnostic accuracy of 83% was obtained by combining FET PET and MRI features.CONCLUSIONCombined FET PET/MRI radiomics allows the non-invasive prediction of the MGMT promoter methylation status in patients with gliomas, providing more diagnostic information than either modality alone.
000908215 536__ $$0G:(DE-HGF)POF4-5253$$a5253 - Neuroimaging (POF4-525)$$cPOF4-525$$fPOF IV$$x0
000908215 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000908215 7001_ $$0P:(DE-HGF)0$$aMeissner, Anna-Katharina$$b1
000908215 7001_ $$0P:(DE-HGF)0$$aWerner, Jan-Michael$$b2
000908215 7001_ $$0P:(DE-Juel1)131627$$aStoffels, Gabriele$$b3
000908215 7001_ $$0P:(DE-Juel1)173675$$aKocher, Martin$$b4
000908215 7001_ $$0P:(DE-HGF)0$$aBauer, Elena$$b5
000908215 7001_ $$0P:(DE-Juel1)131720$$aFink, Gereon$$b6
000908215 7001_ $$0P:(DE-Juel1)131794$$aShah, Nadim$$b7
000908215 7001_ $$0P:(DE-Juel1)131777$$aLangen, Karl-Josef$$b8$$ufzj
000908215 7001_ $$0P:(DE-Juel1)143792$$aGalldiks, Norbert$$b9
000908215 909CO $$ooai:juser.fz-juelich.de:908215$$pVDB
000908215 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)145110$$aForschungszentrum Jülich$$b0$$kFZJ
000908215 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131627$$aForschungszentrum Jülich$$b3$$kFZJ
000908215 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)173675$$aForschungszentrum Jülich$$b4$$kFZJ
000908215 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131720$$aForschungszentrum Jülich$$b6$$kFZJ
000908215 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131794$$aForschungszentrum Jülich$$b7$$kFZJ
000908215 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131777$$aForschungszentrum Jülich$$b8$$kFZJ
000908215 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)143792$$aForschungszentrum Jülich$$b9$$kFZJ
000908215 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)POF4-5253$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
000908215 9201_ $$0I:(DE-Juel1)INM-11-20170113$$kINM-11$$lJara-Institut Quantum Information$$x0
000908215 9201_ $$0I:(DE-Juel1)INM-4-20090406$$kINM-4$$lPhysik der Medizinischen Bildgebung$$x1
000908215 9201_ $$0I:(DE-Juel1)VDB1046$$kJARA-BRAIN$$lJülich-Aachen Research Alliance - Translational Brain Medicine$$x2
000908215 9201_ $$0I:(DE-Juel1)INM-3-20090406$$kINM-3$$lKognitive Neurowissenschaften$$x3
000908215 980__ $$acomm
000908215 980__ $$aVDB
000908215 980__ $$aI:(DE-Juel1)INM-11-20170113
000908215 980__ $$aI:(DE-Juel1)INM-4-20090406
000908215 980__ $$aI:(DE-Juel1)VDB1046
000908215 980__ $$aI:(DE-Juel1)INM-3-20090406
000908215 980__ $$aUNRESTRICTED