Development and validation of clinical-radiomics analysis for preoperative prediction of IDH mutation status and WHO grade in diffuse gliomas: a consecutive l -[methyl-11C] methionine cohort study with two PET scanners

Purpose Determination of isocitrate dehydrogenase ( IDH ) genotype is crucial in the stratification of diagnosis and prognostication in diffuse gliomas. We sought to build and validate radiomics models and clinical features incorporated nomogram for preoperative prediction of IDH mutation status and WHO grade of diffuse gliomas with l -[methyl-11C] methionine ([ 11 C]MET) PET/CT imaging according to the 2016 WHO classification of tumors of the central nervous system. Methods Consecutive 178 preoperative [ 11 C]MET PET/CT images were retrospectively studied for radiomics analysis. One hundred six patients from PET scanner 1 were used as training dataset, and 72 patients from PET scanner 2 were used for validation dataset. [ 11 C]MET PET and integrated CT radiomics features were extracted, respectively; three independent predictive models were built based on PET features, CT features, and combined PET/CT features, respectively. The SelectKBest method, Spearman correlation analysis, Least Absolute Shrinkage and Selection Operator (LASSO) regression, and machine learning algorithms were applied for feature selection and model building. After filtering the satisfactory predictive model, key clinical features were incorporated for the nomogram establishment. Results The combined [ 11 C]MET PET/CT radiomics model, which consisted of four PET features and eight integrated CT features, was significantly associated with IDH genotype ( p < 0.0001 for both training and validation datasets). Nomogram based on the [ 11 C]MET PET/CT radiomics score, patients’ age, and dichotomous tumor location status showed satisfactory discrimination capacity, and the AUC was 0.880 (95% CI, 0.726–0.998) in the training dataset and 0.866 (95% CI, 0.777–0.956) in the validation dataset. In IDH stratified WHO grade prediction, the final radiomics model consists of four PET features and two CT features had reasonable and stable differential efficacy of WHO grade II and III patients from grade IV patients in IDH -wildtype patients, and the AUC was 0.820 (95% CI, 0.541–1.000) in the training dataset and 0.766 (95% CI, 0.612–0.921) in the validation dataset. Conclusion [ 11 C]MET PET radiomics features could benefit non-invasive IDH genotype prediction, and integrated CT radiomics features could enhance the efficacy. Radiomics and clinical features incorporation could establish satisfactory nomogram for clinical application. This non-invasive predictive investigation based on our consecutive cohort from two PET scanners could provide the perspective to observe the differential efficacy and the stability of radiomics-based investigation in untreated diffuse gliomas.