Clinical Characteristics and Magnetic Resonance Imaging-Based Prediction of the KLF4K409Q Mutation in Meningioma

Radiomics-Based Prediction of TERT Promotor Mutations in Intracranial High-Grade Meningiomas

PURPOSE

In meningiomas, TERT promotor mutations are rare but qualify the diagnosis of anaplasia, directly impacting adjuvant therapy. Effective screening for patients at risk for promotor mutations could enable more targeted molecular analyses and improve diagnosis and treatment.

METHODS

Semiautomatic segmentation of intracranial grade 2/3 meningiomas was performed on preoperative magnetic resonance imaging. Discriminatory power to predict TERT promoter mutations was analyzed using a random forest algorithm with an increasing number of radiomic features. Two final models with five and eight features with both fixed and differing radiomics features were developed and adjusted to eliminate random effects and to avoid overfitting.

RESULTS

A total of 117 image sets including training (N = 94) and test data (N = 23) were analyzed. To eliminate random effects and demonstrate the robustness of our approach, data partitioning and subsequent model development and testing were repeated a total of 100 times (each time with repartitioned training and independent test data). The established five- and eight-feature models with both fixed and different radiomics features enabled the prediction of TERT with similar but excellent performance. The five-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 91.8%/94.3%, mean accuracy of 85.5%/88.9%, mean sensitivity of 88.6%/91.4%, mean specificity of 83.2%/87.0%, and a mean Cohen's Kappa of 71.0%/77.7%. The eight-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 92.7%/94.6%, mean accuracy of 87.3%/88.9%, mean sensitivity of 89.6%/90.6%, mean specificity of 85.5%/87.5%, and a mean Cohen's Kappa of 74.4%/77.6%. Of note, the addition of further features of up to N = 8 only slightly increased the performance.

CONCLUSIONS

Radiomics-based machine learning enables prediction of TERT promotor mutation status in meningiomas with excellent discriminatory performance. Future analyses in larger cohorts should include grade 1 lesions as well as additional molecular alterations.

Clinicopathologic Characteristics of Grade 2/3 Meningiomas: A Perspective on the Role of Next-Generation Sequencing

Background

Grade 2/3 meningiomas have locally aggressive behaviors often requiring additional treatment plans after surgical resection. Herein, we explored the clinical significance of next-generation sequencing (NGS) in characterizing the molecular profiles of high-grade meningiomas.

Methods

Patients with intracranial meningioma who underwent surgical resection in a single institution were retrospectively reviewed. Clinicopathologic relevance was evaluated using recurrence-free survival (RFS) as an outcome measure. NGS for the targeted gene regions was performed in 40 participants.

Results

Among the 713 individuals in the study population, 143 cases (20.1%) were identified as having grade 2 or 3 meningiomas with a significantly lower female predominance. While the difference in RFS between grade 2 and 3 meningiomas was insignificant, a few conventional grade 2 cases, but with TERT promoter hotspot mutation, were highly progressive and refractory to the treatment. From the NGS study, recurrent mutations in TRAF and AKT1 were identified with a higher prevalence (17.5% and 12.5%, respectively) compared with grade 2/3 meningiomas reported in previous literature. However, their relations to other histopathologic properties or clinical factors were rarely observed.

Conclusions

Grade 2/3 meningiomas show a broad spectrum of molecular profiles, as they have heterogeneous histologic characteristics.