% 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”.
@MISC{Lohmann:908211,
author = {Lohmann, P. and Elahmadawy, M. A. and Werner, J. and Rapp,
M. and Ceccon, G. and Fink, G. R. and Shah, N. J. and
Langen, K. and Galldiks, N.},
title = {{OS}9.6 {D}iagnosis of pseudoprogression using {FET} {PET}
radiomics},
issn = {1523-5866},
reportid = {FZJ-2022-02462},
year = {2019},
abstract = {AbstractBACKGROUNDRadiomics derived from different imaging
modalities is gaining increasing interest in the field of
neuro-oncology. Besides MRI, amino acid PET radiomics may
also improve the to date challenging, clinically relevant
diagnostic problem of differentiating pseudoprogression
(PsP) from tumor progression (TP). To this end, we here
explored the potential of O-(2-[18F]fluoroethyl)-L-tyrosine
(FET) PET radiomics to discriminate between PsP and
TP.MATERIAL AND METHODSThirty-five newly diagnosed
IDH-wildtype glioblastoma patients with MRI findings
suspicious for TP within 12 weeks after completion of
chemoradiation with temozolomide underwent an additional
dynamic FET PET scan. FET PET tumor volumes were segmented
using a tumor-to-brain ratio (TBR) ≥ 1.6. The static PET
parameters TBRmax and TBRmean, as well as the dynamic
parameter time-to-peak (TTP), were calculated. For radiomics
analysis, the number of datasets for model generation was
increased using data augmentation techniques. Subsequently,
70 datasets were available for model generation. Prior to
further processing, patients were randomly assigned to a
discovery and a validation dataset in a ratio of 70/30, with
balanced distribution of PsP and TP diagnoses. Forty-two
radiomics features (4 shape-based, 6 first- and 32
second-order features) were obtained using the software
LifeX (lifexsoft.org). Afterwards, a z-score transformation
was performed for data normalization. For feature selection,
recursive feature elimination using random forest regressors
was performed. For the final model generation, the number of
parameters was limited to three to avoid data overfitting.
Different algorithms for model calculation were compared,
and the diagnostic accuracy was assessed using leave-one-out
cross-validation. Finally, the resulting models were applied
to the validation dataset to evaluate model
robustness.RESULTSEighteen patients were diagnosed with TP,
and 17 patients had PsP. Diagnoses were based on a
neuropathological confirmation or clinicoradiological
follow-up $(26\%$ and $74\%,$ respectively). The diagnostic
accuracy of the best single FET PET parameter was $75\%$
(TBRmax). Combining TBRmax and TTP increased the diagnostic
accuracy to $83\%.$ Other combinations of static and dynamic
FET PET parameters, however, did not further increase the
accuracy. The highest diagnostic accuracy of $92\%$ was
achieved by a three-parameter model combining the FET PET
parameter TTP with two radiomics features. The model
demonstrated its robustness in the validation dataset with a
diagnostic accuracy of $86\%.CONCLUSIONThe$ results suggest
that FET PET radiomics improves the diagnostic accuracy for
discerning PsP and TP considerably. Given the clinical
significance of differentiating PSP and TP, prospective
multicenter studies are warranted.FUNDINGWilhelm-Sander
Stiftung and the DAAD GERSS Program, Germany},
cin = {INM-4 / INM-11 / JARA-BRAIN},
ddc = {610},
cid = {I:(DE-Juel1)INM-4-20090406 / I:(DE-Juel1)INM-11-20170113 /
I:(DE-Juel1)VDB1046},
pnm = {5253 - Neuroimaging (POF4-525)},
pid = {G:(DE-HGF)POF4-5253},
typ = {PUB:(DE-HGF)4},
UT = {WOS:000493085900066},
doi = {10.1093/neuonc/noz126.064},
url = {https://juser.fz-juelich.de/record/908211},
}