Identifying a radiomics imaging signature for prediction of overall survival in glioblastoma multiforme

Abstract

This paper identifies a MR imaging radiomics signature for prediction of overall survival (OS) in patients with glioblastoma multiforme (GBM). A fully-automatic radiomics model is presented, including automatic tumor segmentation, high-throughput features extraction, features selection, and multi-feature signature identification. The automatic GBM segmentation method employs a random forest classifier with a CRF spatial regulation where the importances of the multi-modality features are considered. After feature selection, a 4-feature radiomics signature is identified based on training data and further confirmed on independent validation data. The proposed signature succeeds to stratify patients into prognostically high-risk and low-risk groups, indicating the potential to facilitate the preoperative patient care of GBM patients.