Abstract
PurposeConstruction of radiomics models for the individualized estimation of multiple survival stratification in glioblastoma (GBM) patients using the multiregional information extracted from multiparametric MRI that could facilitate clinical decision-making for GBM patients.Materials and MethodsA total of 134 eligible GBM patients were selected from The Cancer Genome Atlas. These patients were separated into the long-term and short-term survival groups according to the median of individual survival indicators: overall survival (OS), progression-free survival (PFS), and disease-specific survival (DSS). Then, the patients were divided into a training set and a validation set in a ratio of 2:1. Radiomics features (n = 5,152) were extracted from multiple regions of the GBM using multiparametric MRI. Then, radiomics signatures that are related to the three survival indicators were respectively constructed using the analysis of variance (ANOVA) and the least absolute shrinkage and selection operator (LASSO) regression for each patient in the training set. Based on a Cox proportional hazards model, the radiomics model was further constructed by combining the signature and clinical risk factors.ResultsThe constructed radiomics model showed a promising discrimination ability to differentiate in the training set and validation set of GBM patients with survival indicators of OS, PFS, and DSS. Both the four MRI modalities and five tumor subregions have different effects on the three survival indicators of GBM. The favorable calibration and decision curve analysis indicated the clinical decision value of the radiomics model. The performance of models of the three survival indicators was different but excellent; the best model achieved C indexes of 0.725, 0.677, and 0.724, respectively, in the validation set.ConclusionOur results show that the proposed radiomics models have favorable predictive accuracy on three survival indicators and can provide individualized probabilities of survival stratification for GBM patients by using multiparametric and multiregional MRI features.
Highlights
Glioblastoma (GBM) is the most common primary malignant neoplasm in adults and is nearly uniformly fatal [1], with a median survival time about 12–14 months [2]
The heterogeneity of GBM is reflected in the fact that it usually contains different heterogeneous subregions; this inherent heterogeneity is reflected in its imaging phenotype because its subregions are described by different intensity distributions of multimodal magnetic resonance imaging (MRI) scanning, reflecting the differences in tumor biology, which all contribute to prognosis prediction [8, 9, 14]
To determine the optimal regulation weight l for the least absolute shrinkage and selection operator (LASSO) algorithm, features with non-zero coefficients for survival stratification were selected by 10-fold cross-validation from the 5,152 radiomics features
Summary
Glioblastoma (GBM) is the most common primary malignant neoplasm in adults and is nearly uniformly fatal [1], with a median survival time about 12–14 months [2]. It is necessary to establish a survival prediction model that is helpful to the treatment decision-making and disease management for GBM patients [3]. MRI techniques have great potential for predicting the survival of GBM patients [6, 8, 9]. The field of radiomics has been introduced to extract high-throughput quantitative imaging features from MRI, transform the features into minable data, and establish a prediction or prognosis model connecting image features and tumor phenotype [10, 11]. Previous studies have explored the survival time of GBM patients, most of them focus on OS, and the research on the heterogeneity within the tumor is insufficient. It is necessary and feasible that a multiparametric MRI- and multiregion-based radiomics approach may improve the performance of the multi-survival stratification in GBM patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
