% IMPORTANT: The following is UTF-8 encoded. This means that in the presence % of non-ASCII characters, it will not work with BibTeX 0.99 or older. % Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or % “biber”. @ARTICLE{Kebir:885873, author = {Kebir, Sied and Schmidt, Teresa and Weber, Matthias and Lazaridis, Lazaros and Galldiks, Norbert and Langen, Karl-Josef and Kleinschnitz, Christoph and Hattingen, Elke and Herrlinger, Ulrich and Lohmann, Philipp and Glas, Martin}, title = {{A} {P}reliminary {S}tudy on {M}achine {L}earning-{B}ased {E}valuation of {S}tatic and {D}ynamic {FET}-{PET} for the {D}etection of {P}seudoprogression in {P}atients with {IDH}-{W}ildtype {G}lioblastoma}, journal = {Cancers}, volume = {12}, number = {11}, issn = {2072-6694}, address = {Basel}, publisher = {MDPI}, reportid = {FZJ-2020-04149}, pages = {3080 -}, year = {2020}, abstract = {Pseudoprogression (PSP) detection in glioblastoma remains challenging and has important clinical implications. We investigated the potential of machine learning (ML) in improving the performance of PET using O-(2-[18F]-fluoroethyl)-L-tyrosine (FET) for differentiation of tumor progression from PSP in IDH-wildtype glioblastoma. We retrospectively evaluated the PET data of patients with newly diagnosed IDH-wildtype glioblastoma following chemoradiation. Contrast-enhanced MRI suspected PSP/TP and all patients underwent subsequently an additional dynamic FET-PET scan. The modified Response Assessment in Neuro-Oncology (RANO) criteria served to diagnose PSP. We trained a Linear Discriminant Analysis (LDA)-based classifier using FET-PET derived features on a hold-out validation set. The results of the ML model were compared with a conventional FET-PET analysis using the receiver-operating-characteristic (ROC) curve. Of the 44 patients included in this preliminary study, 14 patients were diagnosed with PSP. The mean (TBRmean) and maximum tumor-to-brain ratios (TBRmax) were significantly higher in the TP group as compared to the PSP group (p = 0.014 and p = 0.033, respectively). The area under the ROC curve (AUC) for TBRmax and TBRmean was 0.68 and 0.74, respectively. Using the LDA-based algorithm, the AUC (0.93) was significantly higher than the AUC for TBRmax. This preliminary study shows that in IDH-wildtype glioblastoma, ML-based PSP detection leads to better diagnostic performance}, cin = {INM-4 / INM-3}, ddc = {610}, cid = {I:(DE-Juel1)INM-4-20090406 / I:(DE-Juel1)INM-3-20090406}, pnm = {573 - Neuroimaging (POF3-573)}, pid = {G:(DE-HGF)POF3-573}, typ = {PUB:(DE-HGF)16}, pubmed = {pmid:33105661}, UT = {WOS:000593665000001}, doi = {10.3390/cancers12113080}, url = {https://juser.fz-juelich.de/record/885873}, }