FET PET radiomics for the diagnosis of pseudoprogression in patients with glioblastoma

Ziel/Aim Radiomics 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-[F-18]fluoroethyl)-L-tyrosine (FET) PET radiomics to discriminate between PsP and TP.

Methodik/Methods Thirty-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 conventional FET PET parameters TBR_max, TBR_mean and time-to-peak (TTP) were calculated. For radiomics analysis, the number of datasets was increased using data augmentation techniques. Prior to further processing, patients were randomly assigned to a discovery and a validation dataset. Forty-two radiomics features were calculated. After z-score normalization, feature selection was performed and the number of parameters was limited to three to avoid data overfitting. Diagnostic accuracy was assessed using cross-validation. Finally, the best performing model was applied to the holdout dataset to evaluate model robustness.

Ergebnisse/Results Eighteen patients were diagnosed with TP, and 17 patients had PsP. Using conventional FET PET parameters, a diagnostic accuracy of 83% was achieved by combining TBR_max and TTP. The highest diagnostic accuracy of 92% was achieved by a three-parameter model combining TTP with two radiomics features. The model demonstrated its robustness in the validation dataset with a diagnostic accuracy of 86%.

Schlussfolgerungen/Conclusions The 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.