Reproducible and Interpretable Machine Learning-Based Radiomic Analysis for Overall Survival Prediction in Glioblastoma Multiforme

Simple Summary This study aimed to develop and validate a radiomic model for predicting overall survival (OS) in glioblastoma multiforme (GBM) patients using pre-treatment MRI images. A retrospective dataset of 289 patients from multiple institutions was used to extract 660 radiomic features (RFs) from each patient's tumor volume. The initial model was enhanced by incorporating clinical variables and validated through repeated three-fold cross-validation. The final clinical-radiomic model utilized primary gross tumor volume (GTV) and T2-FLAIR MRI modality and includes the age variable and two robust RFs. The model achieved a moderately good discriminatory performance (C-Index: 0.69) and significant patient stratification (p = 7 x 10-5) on the validation cohort. Notably, the trained model exhibited the highest integrated area under curve (iAUC) at 11 months (0.81) in the literature. The study concluded that the validated clinical-radiomic model can effectively stratify GBM patients into low and high-risk groups based on OS. Future work will focus on integrating deep learning-based features and standardized convolutional filters to improve OS predictions.Abstract Purpose: To develop and validate an MRI-based radiomic model for predicting overall survival (OS) in patients diagnosed with glioblastoma multiforme (GBM), utilizing a retrospective dataset from multiple institutions. Materials and Methods: Pre-treatment MRI images of 289 GBM patients were collected. From each patient's tumor volume, 660 radiomic features (RFs) were extracted and subjected to robustness analysis. The initial prognostic model with minimum RFs was subsequently enhanced by including clinical variables. The final clinical-radiomic model was derived through repeated three-fold cross-validation on the training dataset. Performance evaluation included assessment of concordance index (C-Index), integrated area under curve (iAUC) alongside patient stratification into low and high-risk groups for overall survival (OS). Results: The final prognostic model, which has the highest level of interpretability, utilized primary gross tumor volume (GTV) and one MRI modality (T2-FLAIR) as a predictor and integrated the age variable with two independent, robust RFs, achieving moderately good discriminatory performance (C-Index [95% confidence interval]: 0.69 [0.62-0.75]) with significant patient stratification (p = 7 x 10-5) on the validation cohort. Furthermore, the trained model exhibited the highest iAUC at 11 months (0.81) in the literature. Conclusion: We identified and validated a clinical-radiomic model for stratification of patients into low and high-risk groups based on OS in patients with GBM using a multicenter retrospective dataset. Future work will focus on the use of deep learning-based features, with recently standardized convolutional filters on OS tasks.