Incorporating multiple magnetic resonance diffusion models to differentiate low- and high-grade adult gliomas: a machine learning approach

BACKGROUND: Accurate grading of gliomas is a challenge in imaging diagnosis. This study aimed to evaluate the performance of a machine learning (ML) approach based on multiparametric diffusion-weighted imaging (DWI) in differentiating low- and high-grade adult gliomas. METHODS: A model was developed from an initial cohort containing 74 patients with pathology-confirmed gliomas, who underwent 3 tesla (3T) diffusion magnetic resonance imaging (MRI) with 21 b values. In all, 112 histogram features were extracted from 16 parameters derived from seven diffusion models [monoexponential, intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), fractional order calculus (FROC), continuous-time random walk (CTRW), stretched-exponential, and statistical]. Feature selection and model training were performed using five randomly permuted five-fold cross-validations. An internal test set (15 cases of the primary dataset) and an external cohort (n=55) imaged on a different scanner were used to validate the model. The diagnostic performance of the model was compared with that of a single DWI model and DWI radiomics using accuracy, sensitivity, specificity, and the area under the curve (AUC). RESULTS: Seven significant multiparametric DWI features (two from the stretched-exponential and FROC models, and three from the CTRW model) were selected to construct the model. The multiparametric DWI model achieved the highest AUC (0.84, versus 0.71 for the single DWI model, P<0.05), an accuracy of 0.80 in the internal test, and both AUC and accuracy of 0.76 in the external test. CONCLUSIONS: Our multiparametric DWI model differentiated low- (LGG) from high-grade glioma (HGG) with better generalization performance than the established single DWI model. This result suggests that the application of an ML approach with multiple DWI models is feasible for the preoperative grading of gliomas.