Abstract
Glioblastoma is recognized as World Health Organization (WHO) grade IV glioma with an aggressive growth pattern. The current clinical practice in diagnosis and prognosis of Glioblastoma using MRI involves multiple steps including manual tumor sizing. Accurate identification and segmentation of multiple abnormal tissues within tumor volume in MRI is essential for precise survival prediction. Manual tumor and abnormal tissue detection and sizing are tedious, and subject to inter-observer variability. Consequently, this work proposes a fully automated MRI-based glioblastoma and abnormal tissue segmentation, and survival prediction framework. The framework includes radiomics feature-guided deep neural network methods for tumor tissue segmentation; followed by survival regression and classification using these abnormal tumor tissue segments and other relevant clinical features. The proposed multiple abnormal tumor tissue segmentation step effectively fuses feature-based and feature-guided deep radiomics information in structural MRI. The survival prediction step includes two representative survival prediction pipelines that combine different feature selection and regression approaches. The framework is evaluated using two recent widely used benchmark datasets from Brain Tumor Segmentation (BraTS) global challenges in 2017 and 2018. The best overall survival pipeline in the proposed framework achieves leave-one-out cross-validation (LOOCV) accuracy of 0.73 for training datasets and 0.68 for validation datasets, respectively. These training and validation accuracies for tumor patient survival prediction are among the highest reported in literature. Finally, a critical analysis of radiomics features and efficacy of these features in segmentation and survival prediction performance is presented as lessons learned.
Highlights
The World Health Organization (WHO) identifies Glioblastoma as a highly aggressive grade IV glioma
Our results suggest that the proposed framework achieves better tumor segmentation and survival prediction performance compared to the state-of-the-art methods
BraTS17 validation dataset consists of 33 cases while that for BraTS18 consists of 28 cases for overall survival prediction purposes
Summary
The World Health Organization (WHO) identifies Glioblastoma as a highly aggressive grade IV glioma. Feature-Guided Segmentation and Survival Prediction methods (Brown et al, 2008; Itakura et al, 2015; Yang et al, 2015). Different studies (Vartanian et al, 2014; Hu et al, 2015; Liu et al, 2017) discussed Glioblastoma heterogeneity and its implication on the clinical outcome. Quantitative radiomic imaging features (radiomics) computed from MRI can be utilized for clinical outcome prediction (Lacroix et al, 2001; Lao et al, 2017; Shboul et al, 2017) and molecular classifications (Gutman et al, 2013; Jain et al, 2013). An accurate detection and segmentation of different abnormal tumor tissues is essential in planning treatment therapy, diagnosis, grading, and survival prediction
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have