Multimodal MRI radiomics based on habitat subregions of the tumor microenvironment for predicting risk stratification in glioblastoma.

in PloS one by Han Wang

TLDR

  • This study developed and validated an integrated clinical-radiomics model to predict overall survival and disease progression in patients with glioblastoma, achieving good risk stratification and survival prediction.

Abstract

Accurate prediction of glioblastoma (GBM) progression is essential for improving therapeutic interventions and outcomes. This study aimed to develop and validate an integrated clinical-radiomics model to predict overall survival (OS) and evaluate the risk of disease progression in patients with isocitrate dehydrogenase-wildtype GBM (IDH-wildtype GBM). The data of 423 IDH-wildtype GBM patients were retrospectively analyzed. Radiomic features were extracted from preoperatively acquired MR images. Least absolute shrinkage and selection operator-Cox proportional hazards (LASSO-Cox) regression was used to identify radiomic features significantly associated with OS and calculate a risk score and construct a radiomic signature for each patient. Kaplan‒Meier survival analysis and the log-rank test were used to compare survival between the high-risk and low-risk groups. A clinical‒radiomic model and a nomogram were developed on the basis of the results of multivariable Cox proportional hazards regression and were evaluated with the concordance index (C-index). Radiomics models were developed on the basis of feature extracted from the three sub-regions individually, and a multiregional radiomics model was established by aggregating 16 features selected from these subregions. Kaplan-Meier survival analysis indicated that the high-risk group exhibited significantly worse outcomes than the low-risk group did (p < 0.05). The C-index of the multiregional radiomics model was the highest. Univariable Cox regression analysis revealed that the risk score, age, and extent of gross total resection (GTR) were significant prognostic factors for OS in GBM patients. According to the C-index, the combined clinical‒radiomic model outperformed the standalone radiomic and clinical models. The multifactor nomogram showed high accuracy in predicting the OS rates of preclinical GBM patients at 3 months, 6 months, 1 year, and 3 years in both the training and test cohorts. The integrated model combining clinicopathological data with a radiomic signature achieves good risk stratification and survival prediction in GBM and thus could be an important tool in clinical practice.

Overview

  • This study aimed to develop and validate an integrated clinical-radiomics model to predict overall survival (OS) and evaluate the risk of disease progression in patients with isocitrate dehydrogenase-wildtype glioblastoma (GBM).
  • The study included 423 IDH-wildtype GBM patients, and radiomic features were extracted from preoperatively acquired MR images using the least absolute shrinkage and selection operator-Cox proportional hazards (LASSO-Cox) regression method.
  • The primary objective of the study was to develop a predictive model that could identify patients at high risk of disease progression and improve therapeutic interventions and outcomes.

Comparative Analysis & Findings

  • The study found that the high-risk group exhibited significantly worse outcomes than the low-risk group (p < 0.05) according to Kaplan-Meier survival analysis.
  • The C-index of the multiregional radiomics model was the highest among the different models, indicating its superiority in predicting overall survival (OS).
  • The multifactor nomogram showed high accuracy in predicting the OS rates of preclinical GBM patients at different time points (3 months, 6 months, 1 year, and 3 years) in both the training and test cohorts.

Implications and Future Directions

  • The integrated clinical-radiomic model could be a valuable tool in clinical practice for risk stratification and survival prediction in GBM patients.
  • Future research directions include exploring the use of this model in combination with other clinical and imaging biomarkers to improve its accuracy and generalizability.
  • Additionally, the model could be validated in larger, prospective studies to further establish its predictive value in clinical decision-making.
Read Full Article