NIMG-36. VISUALIZATION OF TUMOR HETEROGENEITY AND PREDICTION OF ISOCITRATE DEHYDROGENASE MUTATION STATUS FOR HUMAN GLIOMAS BY USING MULTIPARAMETRIC PHYSIOLOGIC AND METABOLIC MRI

Preoperative prediction of isocitrate dehydrogenase mutation status is clinically meaningful, but remains challenging. This study aimed to predict the isocitrate dehydrogenase (IDH) status of gliomas by using the machine learning voxel-wise clustering method of multiparametric physiologic and metabolic magnetic resonance imaging (MRI) and to show the association of the created cluster labels with the glucose metabolism status of the tumors. Sixty-nine patients with diffuse glioma were scanned by pH-sensitive MRI, diffusion-weighted imaging, fluid-attenuated inversion recovery, and contrast-enhanced T1-weighted imaging at 3 T. An unsupervised two-level clustering approach, including the generation of a self-organizing map followed by the K-means clustering, was used for voxel-wise feature extraction from the acquired images. The logarithmic ratio of the labels in each class within tumor regions was applied to a support vector machine to differentiate IDH mutation status. Bootstrapping and leave-one-out cross-validation were used to calculate the area under the curve (AUC) of receiver operating characteristic curves, accuracy, sensitivity, and specificity for evaluating performance. Targeted biopsies were performed for 14 patients to explore the relationship between clustered labels and the expression of key glycolytic proteins determined using immunohistochemistry. The highest prediction performance to differentiate IDH status was found for 10-class clustering, with a mean AUC, accuracy, sensitivity, and specificity of 0.94, 0.91, 0.90, and 0.91, respectively. The tissues with labels 7 + 8 + 9 + 10 showed high expression levels of hypoxia-inducible factor 1-alpha, glucose transporter 3, and hexokinase 2, which are typical of IDH wild-type glioma, whereas those with labels 1 showed low expression of these proteins. Our machine learning model successfully predicted the IDH mutation status of gliomas, and the resulting clusters properly reflected the metabolic status of the tumors.

IMG-21. PROSPECTIVE PREOPERATIVE DETERMINATION OF ISOCITRATE DEHYDROGENASE MUTATION IN GLIOMAS USING SPECTRAL EDITING MAGNETIC RESONANCE SPECTROSCOPY

BACKGROUND Gliomas are the most common malignant brain tumors in children and adults. A subset of these tumors harbour mutations in the enzyme isocitrate dehydrogenase (IDH) which produces the novel oncometabolite 2-hydroxyglutarate (2HG). In general, patients with an IDH mutant glioma have a longer survival—often necessitating more re-treatment sessions over the span of a patient’s life and surveillance monitoring for tumor recurrence. The need to non-invasively detect early evidence of tumor recurrence is therefore heightened in this unique subset of patients with extended survival. As magnetic resonance spectroscopy (MRS) has been demonstrated to measure biochemical components of intracranial tumors using MRI, we conducted a study in 58 pre-operative adult patients to determine if a diagnosis of IDH mutant glioma could be made confidently using imaging data. METHODS Patients underwent neuroimaging for diagnosis or preoperative planning on a 3 tesla MR scanner. A MEGA-PRESS spectral editing technique was employed. Imaging findings were directly compared to post-operative histopathologic diagnosis. RESUTLS: For all patients with gliomas from grade II to IV, detection of 2-HG with MEGA-PRESS sequence had a sensitivity between 48% and 81%, specificity between 60% and 100%, PPV between 53% and 100% and NPV between 77% and 85% depending on the CRLB threshold. Among the different metabolite ratios, a 2-HG/NAA ratio >0.034 had the highest sensitivity and specificity, 86% and 73% respectively. DISCUSSION Magnetic resonance spectroscopy (MRS) is an underused advanced MR technique that deserves consideration in pediatric neuro-oncology given its utility in non-invasively detecting malignant gliomas.