Purpose To develop and validate an integrated model for discriminating tumor recurrence from radiation necrosis in glioma patients. Methods Data from 160 pathologically confirmed glioma patients were analyzed. The diagnostic model was developed in a primary cohort (n = 112). Textural features were extracted from postoperative 18 F-fluorodeoxyglucose (18 F-FDG) positron emission tomography (PET), 11 C-methionine (11 C-MET) PET, and magnetic resonance images. The least absolute shrinkage and selection operator regression model was used for feature selection and radiomics signature building. Multivariable logistic regression analysis was used to develop a model for predicting tumor recurrence. The radiomics signature, quantitative PET parameters, and clinical risk factors were incorporated in the model. The clinical value of the model was then assessed in an independent validation cohort using the remaining 48 glioma patients. Results The integrated model consisting of 15 selected features was significantly associated with postoperative tumor recurrence (p < 0.001 for both primary and validation cohorts). Predictors contained in the individualized diagnosis model included the radiomics signature, the mean of tumor-background ratio (TBR) of 18 F-FDG, maximum of TBR of 11 C-MET PET, and patient age. The integrated model demonstrated good discrimination, with an area under the curve (AUC) of 0.988, with a 95% confidence interval (CI) of 0.975-1.000. Application in the validation cohort showed good differentiation (AUC of 0.914 and 95% CI of 0.881-0.945). Decision curve analysis showed that the integrated diagnosis model was clinically useful. Conclusions Our developed model could be used to assist the postoperative individualized diagnosis of tumor recurrence in patients with gliomas.

BACKGROUND AND PURPOSE: Both 11 C-methionine PET/CT and DSC-PWI could be used to differentiate radiation injury from recurrent brain tumors. Our aim was to assess the performance of MET PET/CT and DSC-PWI for differentiation of recurrence and radiation injury in patients with high-grade gliomas and to quantitatively analyze the diagnostic values of PET and PWI parameters. MATERIALS AND METHODS: Forty-two patients with high-grade gliomas were enrolled in this study. The final diagnosis was determined by histopathologic analysis or clinical follow-up. PWI and PET parameters were recorded and compared between patients with recurrence and those with radiation injury using Student t tests. Receiver operating characteristic and logistic regression analyses were used to determine the diagnostic performance of each parameter. RESULTS: The final diagnosis was recurrence in 33 patients and radiation injury in 9. PET/CT showed a patient-based sensitivity and specificity of 0.909 and 0.556, respectively, while PWI showed values of 0.667 and 0.778, respectively. The maximum standardized uptake value, mean standardized uptake value, tumor-to-background maximum standardized uptake value, and mean relative CBV were significantly higher for patients with recurrence than for patients with radiation injury. All these parameters showed a high discriminative power in receiver operating characteristic analysis. The optimal cutoff values for the tumor-to-background maximum standardized uptake value and mean relative CBV were 1.85 and 1.83, respectively, and corresponding sensitivities and specificities for the diagnosis of recurrence were 0.97 and 0.667 and 0.788 and 0.88, respectively. Areas under the curve for the tumor-to-background maximum standardized uptake value and mean relative CBV were 0.847 Ϯ 0.077 and 0.845 Ϯ 0.078, respectively. Combined assessment of the tumor-to-background maximum standardized uptake value and mean relative CBV showed the largest area under the curve (0.953 Ϯ 0.031), with corresponding sensitivity and specificity of 0.848 and 1.0, respectively. CONCLUSIONS: Both 11 C-methionine PET/CT and PWI are equally accurate in the differentiation of recurrence from radiation injury in patients with high-grade gliomas, and a combination of the 2 modalities could result in increased diagnostic accuracy. ABBREVIATIONS: AUC ϭ area under the curve; MET ϭ 11 C-methionine; HGG ϭ high-grade glioma; max ϭ maximum; rCBV ϭ relative CBV; SUV ϭ standardized uptake value; TBR ϭ tumor-to-background G liomas are the most common primary brain tumors. Tumor resection followed by postoperative chemotherapy and radiation therapy is the primary treatment for gliomas. However, radiation therapy may damage normal brain tissue and result in adverse effects involving the brain. Classically, radiation injury can be classified into acute and delayed reactions. Radiation-induced necrosis is the most severe form of radiation injury and usually occurs 3-12 months after radiation therapy, though it can also occur years after treatment. The incid...