Machine learning assisted DSC-MRI radiomics as a tool for glioma classification by grade and mutation status

Abstract

Background: Machine learning assisted MRI radiomics, which combines MRI techniques with machine learning methodology, is rapidly gaining attention as a promising method for staging of brain gliomas. Our study assess the diagnostic value of such machine learning for DSC-MRI radiomics in classifying treatment-naive gliomas from a multi-center patient pool into WHO grades II-IV and across their isocitrate dehydrogenase (IDH) mutation status. Methods: 333 patients from 6 tertiary centres, diagnosed histologically and molecularly with primary gliomas (IDH-mutant=151 or IDH-wildtype=182) were retrospectively identified. Raw DSC-MRI data was post-processed for normalised leakage-corrected relative cerebral blood volume (rCBV) maps. Shape, intensity distribution (histogram) and rotational invariant Haralick texture features over the tumour mask were extracted. Differences in extracted features between IDH-wildtype and IDH-mutant gliomas and across three glioma grades were tested using the Wilcoxon two-sample test. A random forest algorithm was employed (2-fold cross-validation, 250 repeats) to predict grades or mutation status using the extracted features. Results: Features from all types (shape, distribution, texture) showed significant differences across mutation status. WHO grade II-III differentiation was mostly driven by shape features while texture and intensity feature were more relevant for the III-IV separation. Increased number of features became significant when differentiating grades further apart from one another. Gliomas were correctly stratified by IDH mutation status in 71% of the cases and by grade in 53% of the cases. In addition, 87% of the gliomas grades predicted with an error distance up to 1. Conclusion: Despite large heterogeneity in the multi-center dataset, machine learning assisted DSC-MRI radiomics hold potential to address the inherent variability and presents a promising approach for non-invasive glioma molecular subtyping and grading. Keywords: diagnostic machine learning, glioma stratification, Isocitrate dehydrogenase; MRI imaging