Meningioma MRI radiomics and machine learning: systematic review, quality score assessment, and meta-analysis

Purpose To systematically review and evaluate the methodological quality of studies using radiomics for diagnostic and predictive purposes in patients with intracranial meningioma. To perform a meta-analysis of machine learning studies for the prediction of intracranial meningioma grading from pre-operative brain MRI. Methods Articles published from the year 2000 on radiomics and machine learning applications in brain imaging of meningioma patients were included. Their methodological quality was assessed by three readers with the radiomics quality score, using the intra-class correlation coefficient (ICC) to evaluate inter-reader reproducibility. A meta-analysis of machine learning studies for the preoperative evaluation of meningioma grading was performed and their risk of bias was assessed with the Quality Assessment of Diagnostic Accuracy Studies tool. Results In all, 23 studies were included in the systematic review, 8 of which were suitable for the meta-analysis. Total (possible range, -8 to 36) and percentage radiomics quality scores were respectively 6.96 +/- 4.86 and 19 +/- 13% with a moderate to good inter-reader reproducibility (ICC = 0.75, 95% confidence intervals, 95%CI = 0.54-0.88). The meta-analysis showed an overall AUC of 0.88 (95%CI = 0.84-0.93) with a standard error of 0.02. Conclusions Machine learning and radiomics have been proposed for multiple applications in the imaging of meningiomas, with promising results for preoperative lesion grading. However, future studies with adequate standardization and higher methodological quality are required prior to their introduction in clinical practice.

Automated summary

This study systematically reviewed studies using radiomics and machine learning in patients with intracranial meningioma for diagnostic and predictive purposes. Promising results were found for preoperative meningioma grading using machine learning, but more high-quality studies are needed before clinical implementation.