IS DYNAMIC SUSCEPTIBILITY CONTRAST PERFUSION- WEIGHTED MRI RELIABLE IN THE ESTIMATION OF IDH MUTATION IN GLIOMAS?

Abstract

BACKROUND &PURPOSE: The presence of mutation in the encoding gene of isocitrate-dehydrogenase (IDH) enzyme has been defined as a molecular biomarker by World Health Organisation (WHO) in 2016 in the diagnosis and differentiation of gliomas. MRI techniques have been widely used in the radiological evaluation of gliomas. Among advanced MRI techniques, Dynamic Susceptibility Contrast Perfusion- Weighted Imaging (DSC - PWI) appears as a recently established technique for histopathological WHO grading of gliomas. In this study, we aimed to investigate whether DSC - PWI, enhanced by texture analysis and machine learning, can stratify gliomas according to their IDH mutation status. MATERIAL &METHODS: 208 patients (F/ M: 84 /119, median age: 47 [range: 21-81 year]) from a multicenter setting, who have been immunohistopathologically diagnosed with gliomas (IDH positive / negative: 98 /105) were prospectively included in our study. The raw data from DSC -PWI was processed on a dedicated workstation to create leakage-corrected relative cerebral blood volume (rCBV) maps. Tumours were manually segmented and registered to rCBV maps. rCBV maps were used to generate distribution and rotational invariant Haralick texture features over the tumour mask. The predictive power of the extracted features in differentiating between IDH status was assessed in a 2-fold cross-validation setting of 1000 iterations using support vector machine and multinomial ordinal regression, respectively. RESULTS: In the differentiation of IDH-mutant tumours from wild-type ones, overall sensitivity and specificity rates for the rCBV values were 68% and 81%, respectively. Nine of the ten classical histogram statistics and twelve texture features appeared significantly different across mutation status (p< 0.05) when using a non parametric Wilcoxon test. CONCLUSION: Preliminary results are promising in the differentiation of gliomas with DSC- PWI on the basis of IDH mutation status, especially regarding the high specificity rates obtained using features from rCBV data.