Machine Learning-based Multiparametric Magnetic Resonance Imaging Radiomics Model For Distinguishing Central Neurocytoma From Glioma Of Lateral Ventricle

BackgroundPreoperative,noninvasive differentiation of central neurocytomas(CNs)from gliomas of lateral ventricle is important because it influences the treatment strategy.Recently,machine learning-based radiomics models have attracted wide attention in the neuro-oncology community and has produced promising results.PurposeTo develop a radiomics model based on multiparametric magnetic resonance imaging(MRI)for preoperative discrimination between CNs and gliomas of lateral ventricles.Materials and Methods:In this retrospective study,our radiomics model was developed with contrast-enhanced T1-weighted and T2-weighted images of 104 participants(50 CNs,54 gliomas,histopathologically proven)from medical center A using a support vector machine.The model was validated with an external cohort(n=28,13 CNs and 15 gliomas)from medical center B.Performance was evaluated using the sensitivity,specificity and area under the receiver operating characteristic curve(AUC).The model’s performance was also compared with those of three radiologists.ResultsThe radiomics model achieved an AUC of 0.986 in the training cohort,0.933 in the internal validation cohort,and 0.903 in the external validation cohort.In the three cohorts,the AUC values were 0.657,0.786 and 0.708 for radiologist 1;0.838,0.799 and 0.790 for radiologist 2;and 0.827,0.871 and 0.862 for radiologist 3.When assisted by the radiomics model,two radiologists improved their performance in the training cohort(P<0.05)but not in the internal or external validation cohorts.ConclusionThe machine learning radiomics model based on multiparametric MRI showed better performance for distinguishing CNs from lateral ventricular gliomas than did experienced radiologists,and it showed the potential to improve radiologist performance.