The Value Of MRI Radiomics In Predicting IDH-1 Genotype In Gliomas

Objectives:To explore the value of multi-sequence MRI image-based radiomics in preoperative assessment of the isocitrate dehydrogenase-1(IDH-1)genotype in patients with glioma.Materials and Methods:A retrospective analysis was performed on 102 patients with gliomas confirmed by postoperative pathology in our hospital from 2017 to 2021,who had preoperative multi-sequence MRI images,including 74 patients with wild-type of IDH-1(12 patients with WHO grade 2,15 patients with grade 3,47 patients with grade 4),28 patients with an IDH-1 mutation(15 patients with WHO 2 grade,10 patients with grade 3,3 patients with grade 4).All patients were randomly assigned to training group and validation group according to a ratio of 7:3,using 3D-slicer software to extract radiological features from T2WI and enhanced T1WI sequences respectively.Lasso was finally conducted to obtain 7 optimized subset of the feature to build five radiomics model,and the model was then tested with cross-validation.The area under the curve(AUC)of the receiver operating characteristic was performed to evaluate the performance of the model.Results:Among the single-sequence models,the enhanced T1WI radiomics model、T2WI model and the clinic model have the seem predictive performance.The prediction performance of the two-sequence combined M model is better than that of the single-sequence model,and the difference is statistically significant compared with the T2 model,P<0.05.The combined model with clinical characteristics(C model)has the best performance witch compared with the clinic model,the difference was statistically significant(P<0.05),and the AUC of the training group and the validation group are respectively 0.924(95%CI:0.86-0.98)、0.821(95%CI:0.66-0.98),the sensitivity are 0.92、0.95,the specificity are 0.68、0.56,and the accuracy are 0.86、0.84.Conclusion:The MRI radiomic model based on T2WI and enhanced T1WI sequence can effectively predict the IDH-1 genotype of glioma and had the potential ability in predicting the IDH-1 genotype in gliomas preoperatively,which provides a non-invasive,risk-free and complication-free examination method for early intervention and prognosis assessment.