Radiomic study on preoperative multi‐modal magnetic resonance images identifies IDH‐mutant TERT promoter‐mutant gliomas

Abstract

Objectives Gliomas with comutations of isocitrate dehydrogenase (IDH) genes and telomerase reverse transcriptase (TERT) gene promoter (IDHmut pTERTmut) show distinct biological features and respond to first‐line treatment differently in comparison with other gliomas. This study aimed to characterize the IDHmut pTERTmut gliomas in multimodal MRI using the radiomic method and establish a precise diagnostic model identifying this group of gliomas. Methods A total of 140 patients with untreated primary gliomas were admitted between 2016 and 2020 to West China Hospital as a discovery cohort, including 22 IDHmut pTERTmut patients. Thirty‐four additional cases from a different hospital were included in the study as an independent validation cohort. A total of 3654 radiomic features were extracted from the preoperative multimodal MRI images (T1c, FLAIR, and ADC maps) and filtered in a data‐driven approach. The discovery cohort was split into training and test sets by a 4:1 ratio. A diagnostic model (multilayer perceptron classifier) for detecting the IDHmut pTERTmut gliomas was trained using an automatic machine‐learning algorithm named tree‐based pipeline optimization tool (TPOT). The most critical radiomic features in the model were identified and visualized. Results The model achieved an area under the receiver‐operating curve (AUROC) of 0.971 (95% CI, 0.902–1.000), the sensitivity of 0.833 (95% CI, 0.333–1.000), and the specificity of 0.966 (95% CI, 0.931–1.000) in the test set. The area under the precision‐recall curve (AUCPR) was 0.754 (95% CI, 0.572–0.833) and the F1 score was 0.833 (95% CI, 0.500–1.000). In the independent validation set, the model reached 0.952 AUROC, 0.714 sensitivity, 0.963 specificity, 0.841 AUCPR, and 0.769 F1 score. MR radiomic features of the IDHmut pTERTmut gliomas represented homogenous low‐complexity texture in three modalities. Conclusions An accurate diagnostic model was constructed for detecting IDHmut pTERTmut gliomas using multimodal radiomic features. The most important features were associated with the homogenous simple texture of IDHmut pTERTmut gliomas in MRI images transformed using Laplacian of Gaussian and wavelet filters.

Deep Learning Radiomics for the Assessment of Telomerase Reverse Transcriptase Promoter Mutation Status in Patients With Glioblastoma Using Multiparametric MRI

“…Previous studies have only focused on a single radiomics approach to predict TERT promoter mutation status in patients with gliomas 17,28–30 . Few studies have explored whether the stacking fusion method combining radiomics and DL signatures can improve the prediction of TERT promoter mutation status.…”

“…27 Previous studies have only focused on a single radiomics approach to predict TERT promoter mutation status in patients with gliomas. 17,[28][29][30] Few studies have explored whether the stacking fusion method combining radiomics and DL signatures can improve the prediction of TERT promoter mutation status. In a study on glioma grading, Ning et al 19 found that, regardless of whether single-or multimodality MRI was used, the combination of radiomics and DL had better performance than that of radiomics or DL alone, which is consistent with the results of the present study.…”

“…Radiomics analysis, which converts manually delineated regions of interest in medical images into mineable high‐throughput quantitative features, and convolutional neural networks (CNNs), wherein a computer learns to recognize image features on its own, are usually based on a set of labeled training examples 15,16 . Previous studies have established several radiomics models to predict TERT promoter mutation status in patients with gliomas 17,18 . However, the clinical utility of these models is limited by their small sample size and lack of independent validation.…”

“…15,16 Previous studies have established several radiomics models to predict TERT promoter mutation status in patients with gliomas. 17,18 However, the clinical utility of these models is limited by their small sample size and lack of independent validation. Meanwhile, relevant quantitative features extracted by deep learning (DL) techniques have shown promising results in many medical applications.…”

A radiomics‐based nomogram may be useful for predicting telomerase reverse transcriptase promoter mutation status in adult glioblastoma

“…Previous reports have demonstrated that specific radiomic features, including tumor shape, texture, and enhancement patterns, can provide valuable insights for predicting TERT promoter mutations and survival outcomes (Fang et al., 2020 ; Ivanidze et al., 2019 ). More recently, several researchers have employed multi‐parameter MRI radiomics analysis to effectively differentiate TERT mutant gliomas from wild‐type counterparts with promising results (He et al., 2022 ; Park, Han et al., 2021 ; Tian et al., 2020 ; Wang et al., 2023 ). However, these studies have predominantly focused on grade 2–4 gliomas, and there is a limited amount of literature regarding the utilization of radiomics analysis to differentiate TERT promoter status in patients with GBM.…”