MRI影像组学对无强化弥漫性胶质瘤术后5年复发的预测价值OA

Objective To investigate the value of the MRI-based radiomics model in predicting the recurrence of non-enhan-cing diffuse gliomas within 5 years after surgery.Methods A retrospective analysis was conducted on 116 patients with pathologically confirmed non-enhanced diffuse gliomas treated at Beijing Tiantan Hospital Affiliated to Capital Medical University from June 2016 to June 2020.Clinical pathological data,MRI images,and follow-up information were collected.Radiomics features and tumor location features were extracted using Python pyradiomics and Atlasquery tools.The LASSO algorithm was applied for feature dimensionality re-duction and selection.Five predictive models were constructed as follows:Model-1(Sex and Age),Model-2(Tumor Location),Mod-el-3(Radiomics),Model-4(Tumor Location+Radiomics),and Model-5(Sex+Age+Tumor Location+Radiomics).Receiver operat-ing characteristic(ROC)curves and decision curve analysis(DCA)were plotted to evaluate the predictive performance of the models.Results The areas under the ROC curve(AUC)for predicting postoperative recurrence were 0.529(Model-1),0.680(Model-2),0.912(Model-3),0.911(Model-4),and 0.917(Model-5),respectively.Model-5 demonstrated the best performance,achieving a sensitivity of 0.837,specificity of 0.866,and accuracy of 0.863,respectively in the test set.Conclusions The MRI radiomics-based model has high clinical value in predicting recurrence of non-enhancing diffuse gliomas within 5 years after surgery.