343 Machine Learning Using Multiparametric MRI Radiomic Feature Analysis to Predict Ki-67 in Meningiomas

Abstract

INTRODUCTION: Although WHO grade I meningiomas are considered ‘benign’ tumors, an elevated Ki-67 is one crucial factor that has been shown to influenceclinical outcomes. Machile learning using radiomic analysis can help predict tumor pathology and model outcomes. METHODS: A retrospective analysis was performed for a cohort of 306 patients that underwent surgical resection of WHO grade I meningiomas. MRI was used to perform radiomic feature extraction followed by machine learning using a support vector machine (SVM) through nested cross-validation on a discovery cohort (N = 230), to stratify tumors based on Ki-67. The final model was independently tested on a replication cohort (N = 76). RESULTS: The mean and median Ki-67 of tumor specimens were 4.84 ± 4.03% (range: 0.3 – 33.6) and 3.7% (Q1: 2.3%, Q3: 6%), respectively. Meningiomas with Ki-67=5% were larger in volume compared to tumors with Ki-67 < 5% (mean 38.65 ± 19.19 and 20.97 ± 35.57 cm3, respectively; p < 0.001), which held true in sub-group analysis of both skull base and non-skull base tumors. Similarly, meningiomas with Ki-67 = 5% had significantly larger peritumoral edema volumes compared to tumors with Ki67 < 5% (mean 22.11 ± 40.12 and 40.16 ± 42.34 cm3, respectively; p = 0.002). An area under the receiver operating curve (AUC) of 0.84 (95% CI: 0.78-0.90) with a sensitivity of 84.1% and specificity of 73.3% was achieved in the discovery cohort. When this model was applied to the replication cohort, a similar high performance was achieved, with an AUC of 0.83 (95% CI: 0.73-0.94), sensitivity and specificity of 82.6% and 85.5%, respectively. The model demonstrated similar efficacy when applied to skull base and non-skull base tumors. CONCLUSION: Our proposed radiomic feature analysis can be used to stratify meningiomas based on Ki-67 with excellent accuracy and can be applied to skull-base and non-skull base tumors.