P04.53 Multiregional radiomics profiling from multiparametric MRI: identifying an imaging predictor of IDH1 mutation status in glioblastoma multiforme

Abstract

Background

Glioblastoma Multiforme (GBM) patients with isocitrate dehydrogenase 1 (IDH1) mutations have significantly improved prognosis than those without such mutations. We aimed to preoperatively predict IDH1 mutation status in GBM using multiregional radiomics features from multiparametric magnetic resonance imaging (MRI).

Material and Methods

In total 225 patients were recruited in this retrospective multicenter study. 1614 quantitative features were extracted from multiple tumor subregions (including enhancement area, non-enhancement area, necrosis and edema) in multiparametric MRI. After intensitynormalization, tumor subregion segmentation, resampling-based data balancing and relevant feature selection, a multiregional radiomics model was built using a machine-learning method for prediction of IDH1 mutation from a primary cohort (118 patients) and tested on an independent validation cohort (107 patients). Four single-region radiomics models with features from each tumor subregion, and a model combining multiregional features with clinical factors (age, sex, and Karnofsky performance status) were also built and tested.

Results

Among four single-region radiomics models, the model built from edema region achieved the best accuracy of 96% and the best F1-score of 0.75 in the independent validation cohort. The 8-feature multiregional radiomics model achieved an improved overall performance of an accuracy 96%, an AUC 0.90 and an F1-score 0.78 in the validation cohort, which significantly outperformed the single-region models. Among all predictive models, the model combining multiregional imaging features with patient age achieved the best performance of an accuracy 97%, an AUC 0.96 and an F1-score 0.84 in the validation cohort.

Conclusion

The radiomics-based model built with a minimal set of multiregional features from multiparametric MRI has the potential to preoperatively detect the IDH1 mutation status in GBM patients. The proposed predictor may serve as a potential noninvasive biomarker to guide preoperative GBM patient care.