WITHDRAWN: The value of T2WI-based intratumoral and peritumoral edema radiomics in predicting IDH-1 genotype in gliomas

Abstract

Objective: To explore the preoperative prediction value of isocitrate dehydrogenase-1 (IDH-1) genotype in gliomas using T2WI peritumoral edema radiomics. Methods: Preoperative T2WI images of 164 patients with glioma (WHO grade 2–4) confirmed by pathology were retrospectively analyzed, including wild-type IDH-1 (n = 106) and mutant IDH-1 (n = 58). All patients were randomly divided into training and validation cohorts in the ratio of 7:3. Radiomics features were extracted from tumor and peritumoral edema using 3D-slicer software. The least absolute shrinkage and selection operator (Lasso) method was used for feature selection and regularization. After obtaining the optimized radiomics features, multiple regression models of clinical model (A), intratumoral-only radiomics model (T), peritumoral edema–only radiomics model (E), intratumoral and peritumoral edema radiomics model (H), and clinical combined radiomics model (C) were established and cross-validated. The predictive performance of the model was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). Result: Model E had a better prediction efficiency than model T, and model H had a better prediction performance than the single-region model, although without significant difference among the three groups (P > 0.05). Model C had the best prediction performance, with an AUC of 0.927 (95% CI: 0.88–0.97) and 0.870 (95% CI: 0.77–0.97), the sensitivity of 0.73 and 0.93, the specificity of 0.83 and 0.81, and the accuracy of 0.86 and 0.82 in the training and validation cohort, respectively. The difference between model C and model A was statistically significant (P< 0.05). Conclusion: Radiomic models based on T2WI intratumoral and peritumoral edema can effectively predict the IDH-1 genotype of gliomas preoperatively.