Purpose: This study aims to evaluate qualitative and quantitative imaging metrics along with clinical features affecting overall survival in glioblastomas and to classify them into high survival and low survival groups based on 12, 19, and 24 months thresholds using machine learning.
Methods: The cohort consisted of 98 adult glioblastomas. A standard brain tumor magnetic resonance (MR) imaging protocol, was performed on a 3T MR scanner. Visually Accessible REMBRANDT Images (VASARI) features were assessed. A Kaplan-Meier survival analysis followed by a log-rank test and multivariate Cox regression analysis were used to investigate the effects of VASARI features along with the age, gender, the extent of resection, pre- and post-KPS, ki67 and P53 mutation status on overall survival. Supervised machine learning algorithms were employed to predict the survival of glioblastoma patients based on 12, 19, and 24 months thresholds.
Results: Tumor location (p<0.001), the proportion of non-enhancing component (p=0.0482), and proportion of necrosis (p=0.02) were significantly associated with overall survival based on Kaplan-Meier analysis. Multivariate Cox regression analysis revealed that increases in proportion of non-enhancing component (p=0.040) and proportion of necrosis (p=0.039) were significantly associated with overall survival. Machine-learning models were successful in differentiating patients living longer than 12 months with 96.40% accuracy (sensitivity=97.22%, specificity=95.55%). The classification accuracies based on 19 and 24 months survival thresholds were 70.87% (sensitivity=83.02%, specificity=60.11%) and 74.66% (sensitivity=67.58%, specificity=82.08%), respectively.
Conclusion: Employing clinical and VASARI features together resulted in a successful classification of glioblastomas that would have a longer overall survival.
Keywords: Glioblastoma; Machine learning; Magnetic resonance imaging; Survival analysis; VASARI.
Copyright © 2022 Elsevier Inc. All rights reserved.