Identification of glioblastoma molecular subtype and prognosis based on deep MRI features

Magnetic resonance imaging (MRI) has become an important tool to study the correlation between the imaging phenotypes and the molecular profiles of Glioblastoma multiforme (GBM), the most frequent and lethal brain tumor. This type of study is named Radiogenomics. Currently, many radiogenomics studies segmented the tumors manually and then extracted hand-crafted MRI features for analysis. Automated segmentation approach as well as automatically learned features are urgently needed to release the burden of manual operation. In this study, we developed a predictive model, named DeepRA, based on deep imaging features and machine learning technologies to identify MRI signatures that enable accurate prediction of GBM molecular subtype and patient overall survival. We here for the first time used state-of-the-art deep imaging features to predict both molecular subtype and overall survival. We converted the high-dimensional deep feature representations to interpretable feature vector, selected the most distinguishing features and conducted the prediction. Experiments validated on The Cancer Genome Atlas (TCGA) data have shown that the DeepRA outperformed the traditional hand-crafted method. Also, compared with the regular convolutional neural networks used to segment tumors, the DeepRA presents a better performance, which shows the features extracted from DeepRA are more predictive. The implementation of the proposed method is available at https: //github.com/RanSuLab/GBM-subtype-survival. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

A predictive model named DeepRA was developed to accurately predict the molecular subtype and patient overall survival of GBM using deep imaging features and machine learning technologies. Experiments showed that DeepRA outperformed traditional hand-crafted methods and regular convolutional neural networks.