Multiregional radiomics profiling from multiparametric MRI: Identifying an imaging predictor of IDH1 mutation status in glioblastoma

Abstract

Purpose: Isocitrate dehydrogenase 1 (IDH1) has been proven as a prognostic and predictive marker in glioblastoma (GBM) patients. The purpose was to preoperatively predict IDH mutation status in GBM using multiregional radiomics features from multiparametric magnetic resonance imaging (MRI).

Methods: In this retrospective multicenter study, 225 patients were included. A total of 1614 multiregional features were extracted from enhancement area, non-enhancement area, necrosis, edema, tumor core, and whole tumor in multiparametric MRI. Three multiregional radiomics models were built from tumor core, whole tumor, and all regions using an all-relevant feature selection and a random forest classification for predicting IDH1. Four single-region models and a model combining all-region features with clinical factors (age, sex, and Karnofsky performance status) were also built. All models were built from a training cohort (118 patients) and tested on an independent validation cohort (107 patients).

Results: Among the four single-region radiomics models, the edema model achieved the best accuracy of 96% and the best F1-score of 0.75 while the non-enhancement model achieved the best area under the receiver operating characteristic curve (AUC) of 0.88 in the validation cohort. The overall performance of the tumor-core model (accuracy 0.96, AUC 0.86 and F1-score 0.75) and the whole-tumor model (accuracy 0.96, AUC 0.88 and F1-score 0.75) was slightly better than the single-regional models. The 8-feature all-region radiomics model achieved an improved overall performance of an accuracy 96%, an AUC 0.90, and an F1-score 0.78. Among all models, the model combining all-region imaging features with age achieved the best performance of an accuracy 97%, an AUC 0.96, and an F1-score 0.84.

Conclusions: The radiomics model built with multiregional features from multiparametric MRI has the potential to preoperatively detect the IDH1 mutation status in GBM patients. The multiregional model built with all-region features performed better than the single-region models, while combining age with all-region features achieved the best performance.

Keywords: IDH1 mutation; glioblastoma; magnetic resonance imaging; radiomics.

Figure 1

Multiregional segmentation result. The enhancement area, non‐enhancement area, necrosis, and edema were shown in green, yellow, purple, and blue, respectively

Figure 2

Receiver operating characteristic (ROC) curves of the multiregional and single‐region radiomics models in the independent validation cohort, where the area under the receiver operating characteristic curve (AUC) for each model was displayed

Figure 3

Precision‐recall curves (PRC) of the multiregional and single‐region radiomics models in the independent validation cohort, where the F1 score for each model was displayed

Figure 4

Feature maps of the eight all‐region features for an isocitrate dehydrogenase 1 (IDH1)‐mutated patient (top) and an IDH1‐wild‐type patient (bottom). The feature maps illustrated how the selected features radiologically quantified the multiregional variations. Specifically, the features f ₁ measured the quadratic mean of the intensity within the enhancement area; f ₂ measured the amount of local variations present in the enhancement area; f ₃ indicated the spatial distribution of low‐level intensity within core area; f ₄ characterized the joint distribution of both low‐level intensity and short run length within edema; f ₅ quantified the nonuniformity of gray‐level within edema; f ₆ described the distribution of both high‐level intensity and large area size within the enhancement area; f ₇ described the variance of the size of area with the same gray‐level in the whole tumor region; f ₈ described the spatial rate of intensity change within the non‐enhancement area