T2-FLAIR mismatch sign and machine learning-based multiparametric MRI radiomics in predicting IDH mutant 1p/19q non-co-deleted diffuse lower-grade gliomas

AIM To investigate the application of the T2-weighted (T2)-fluid-attenuated inversion recovery (FLAIR) mismatch sign and machine learning-based multiparametric magnetic resonance imaging (MRI) radiomics in predicting 1p/19q non-co-deletion of lower-grade gliomas (LGGs). MATERIALS AND METHODS One hundred and forty-six patients, who had pathologically confirmed isocitrate dehydrogenase (IDH) mutant LGGs were assigned randomly to the training cohort (n=102) and the testing cohort (n=44) at a ratio of 7:3. The T2-FLAIR mismatch sign and conventional MRI features were evaluated. Radiomics features extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), FLAIR, apparent diffusion coefficient (ADC), and contrast-enhanced T1WI images (CE-T1WI). The models that displayed the best performance of each sequence were selected, and their predicted values as well as the T2-FLAIR mismatch sign data were collected to establish a final stacking model. Receiver operating characteristic curve (ROC) analyses and area under the curve (AUC) values were applied to evaluate and compare the performance of the models. RESULTS The T2-FLAIR mismatch sign was more common in the IDH mutant 1p/19q non-co-deleted group (p<0.05) and the area under the curve (AUC) value was 0.692 with sensitivity 0.397, specificity 0.987, and accuracy 0.712, respectively. The stacking model showed a favourable performance with an AUC of 0.925 and accuracy of 0.882 in the training cohort and an AUC of 0.886 and accuracy of 0.864 in the testing cohort. CONCLUSION The stacking model based on multiparametric MRI can serve as a supplementary tool for pathological diagnosis, offering valuable guidance for clinical practice.