000888137 001__ 888137
000888137 005__ 20210130010824.0
000888137 037__ $$aFZJ-2020-04711
000888137 1001_ $$0P:(DE-Juel1)145110$$aLohmann, Philipp$$b0$$eCorresponding author$$ufzj
000888137 1112_ $$aJahrestagung der Society for Neuro-Oncology (SNO)$$cvirtual$$d2020-11-19 - 2020-11-21$$wvirtual
000888137 245__ $$aNIMG-38. NON-INVASIVE PREDICTION OF MGMT PROMOTER METHYLATION USING COMBINED FET PET/MRI RADIOMICS
000888137 260__ $$c2020
000888137 3367_ $$033$$2EndNote$$aConference Paper
000888137 3367_ $$2BibTeX$$aINPROCEEDINGS
000888137 3367_ $$2DRIVER$$aconferenceObject
000888137 3367_ $$2ORCID$$aCONFERENCE_POSTER
000888137 3367_ $$2DataCite$$aOutput Types/Conference Poster
000888137 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1606141511_27391$$xInvited
000888137 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.
000888137 536__ $$0G:(DE-HGF)POF3-573$$a573 - Neuroimaging (POF3-573)$$cPOF3-573$$fPOF III$$x0
000888137 7001_ $$0P:(DE-HGF)0$$aAnna-Katharina Meissner, $$b1
000888137 7001_ $$0P:(DE-HGF)0$$aJan-Michael Werner, $$b2
000888137 7001_ $$0P:(DE-Juel1)131627$$aStoffels, Gabriele$$b3$$ufzj
000888137 7001_ $$0P:(DE-Juel1)173675$$aKocher, Martin$$b4$$ufzj
000888137 7001_ $$0P:(DE-HGF)0$$aBauer, Elena$$b5
000888137 7001_ $$0P:(DE-Juel1)131720$$aFink, Gereon Rudolf$$b6$$ufzj
000888137 7001_ $$0P:(DE-Juel1)131794$$aShah, N. J.$$b7$$ufzj
000888137 7001_ $$0P:(DE-Juel1)131777$$aLangen, Karl-Josef$$b8$$ufzj
000888137 7001_ $$0P:(DE-Juel1)143792$$aGalldiks, Norbert$$b9$$ufzj
000888137 909CO $$ooai:juser.fz-juelich.de:888137$$pVDB
000888137 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)145110$$aForschungszentrum Jülich$$b0$$kFZJ
000888137 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131627$$aForschungszentrum Jülich$$b3$$kFZJ
000888137 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)173675$$aForschungszentrum Jülich$$b4$$kFZJ
000888137 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131720$$aForschungszentrum Jülich$$b6$$kFZJ
000888137 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131794$$aForschungszentrum Jülich$$b7$$kFZJ
000888137 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131777$$aForschungszentrum Jülich$$b8$$kFZJ
000888137 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)143792$$aForschungszentrum Jülich$$b9$$kFZJ
000888137 9131_ $$0G:(DE-HGF)POF3-573$$1G:(DE-HGF)POF3-570$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lDecoding the Human Brain$$vNeuroimaging$$x0
000888137 9141_ $$y2020
000888137 9201_ $$0I:(DE-Juel1)INM-4-20090406$$kINM-4$$lPhysik der Medizinischen Bildgebung$$x0
000888137 9201_ $$0I:(DE-Juel1)INM-11-20170113$$kINM-11$$lJara-Institut Quantum Information$$x1
000888137 9201_ $$0I:(DE-Juel1)VDB1046$$kJARA-BRAIN$$lJülich-Aachen Research Alliance - Translational Brain Medicine$$x2
000888137 980__ $$aposter
000888137 980__ $$aVDB
000888137 980__ $$aI:(DE-Juel1)INM-4-20090406
000888137 980__ $$aI:(DE-Juel1)INM-11-20170113
000888137 980__ $$aI:(DE-Juel1)VDB1046
000888137 980__ $$aUNRESTRICTED