MRI-based habitat imaging predicts high-risk molecular subtypes and early risk assessment of lower-grade gliomas.

Abstract

Background: In lower-grade gliomas (LrGGs, histological grades 2-3), there exist a minority of high-risk molecular subtypes with malignant transformation potential, associated with unfavorable clinical outcomes and shorter survival prognosis. Identifying high-risk molecular subtypes early in LrGGs and conducting preoperative prognostic evaluations are crucial for precise clinical diagnosis and treatment.

Materials and methods: We retrospectively collected data from 345 patients with LrGGs and comprehensively screened key high-risk molecular markers. Based on preoperative MRI sequences (CE-T1WI/T2-FLAIR), we employed seven classifiers to construct models based on habitat, radiomics, and combined. Eventually, we identified Extra Trees based on habitat features as the optimal predictive model for identifying high-risk molecular subtypes of LrGGs. Moreover, we developed a prognostic prediction model based on radiomics score (Radscore) to assess the survival outlook of patients with LrGGs. We utilized Kaplan-Meier (KM) survival analysis alongside the log-rank test to discern variations in survival probabilities among high-risk and low-risk cohorts. The concordance index was employed to gauge the efficacy of habitat, clinical, and amalgamated prognosis models. Calibration curves were utilized to appraise the congruence between the anticipated survival probability and the actual survival probability projected by the models.

Results: The habitat model for predicting high-risk molecular subtypes of LrGGs, achieved AUCs of 0.802, 0.771, and 0.768 in the training set, internal test set, and external test set, respectively. Comparison among habitat, clinical, combined prognostic models revealed that the combined prognostic model exhibited the highest performance (C-index = 0.781 in the training set, C-index = 0.778 in the internal test set, C-index = 0.743 in the external test set), followed by the habitat prognostic model (C-index = 0.749 in the training set, C-index = 0.716 in the internal test set, C-index = 0.707 in the external test set), while the clinical prognostic model performed the worst (C-index = 0.717 in the training set, C-index = 0.687 in the internal test set, C-index = 0.649 in the external test set). Furthermore, the calibration curves of the combined model exhibited satisfactory alignment when forecasting the 1-year, 2-year, and 3-year survival probabilities of patients with LrGGs.

Conclusion: The MRI-based habitat model simultaneously achieves the objectives of non-invasive prediction of high-risk molecular subtypes of LrGGs and assessment of survival prognosis. This has incremental value for early non-invasive warning of malignant transformation in LrGGs and risk-stratified management.