This issue, Kebir and colleagues present their pilot trial: "Hybrid 11C-MET PET/MRI Combined With "Machine Learning" in Glioma Diagnosis According to the Revised Glioma WHO Classification 2016".
The revised WHO classification from 2016 included molecular features exemplified by isocitrate dehydrogenase (IDH) mutation for glioma subtyping. 11C-methionine (MET) PET/MRI was used to classify gliomas according to the revised WHO classification using a machine learning model. Patients with newly diagnosed WHO grade II–IV gliomas underwent preoperative MET-PET/MRI. Participants were divided into four groups: IDH wild-type glioblastoma (GBM), IDH wild-type grade II/III glioma (GII/III-IDHwt), and IDH mutant grade II/III glioma with codeletion of 1p19q (GII/III-IDHmut1p19qcod) or without 1p19q-codeletion (GII/III-IDHmut1p19qnc). Within each group, the maximum tumor-to-brain-ratio (TBRmax) of MET-uptake was calculated. To establish generalizable implications from this data, a machine learning algorithm based on a development cohort and validation sub-cohort was fit to a support vector machine model was fit to the development cohort. ROC analysis served as metric to assess model performance.
Of 259 patients, 39 patients met inclusion criteria. TBRmax was highest in the GBM cohort (TBRmax 3.83 ± 1.30) and significantly higher (P = 0.004) compared to GII/III-IDHmut1p19qnc group, where TBRmax was lowest (TBRmax 2.05 ± 0.94). ROC analysis showed poor AUC for glioma subtyping (AUC 0.62) and high AUC of 0.79 for predicting IDH status. In the GII/III-IDHmut1p19qcod group, TBR values were slightly higher than in the IDHmut1p19qnc group.
MET-PET/MRI was successful in pre-operatively classifying glioma IDH status.