Deep radiomic features from MRI scans predict survival outcome of recurrent glioblastoma

TL;DR

This study demonstrates that deep radiomic features extracted from CNNs significantly improve the prediction of survival outcomes in recurrent glioblastoma patients compared to standard radiomic features.

Contribution

The paper introduces the use of deep radiomic features from CNNs for prognostic modeling in recurrent glioblastoma, showing enhanced predictive accuracy over traditional features.

Findings

DRFs achieve an AUC of 89.15% in survival prediction.

DRFs outperform standard radiomic features with an AUC of 78.07%.

Deep features are effective prognostic markers for rGBM.

Abstract

This paper proposes to use deep radiomic features (DRFs) from a convolutional neural network (CNN) to model fine-grained texture signatures in the radiomic analysis of recurrent glioblastoma (rGBM). We use DRFs to predict survival of rGBM patients with preoperative T1-weighted post-contrast MR images (n=100). DRFs are extracted from regions of interest labelled by a radiation oncologist and used to compare between short-term and long-term survival patient groups. Random forest (RF) classification is employed to predict survival outcome (i.e., short or long survival), as well as to identify highly group-informative descriptors. Classification using DRFs results in an area under the ROC curve (AUC) of 89.15% (p<0.01) in predicting rGBM patient survival, compared to 78.07% (p<0.01) when using standard radiomic features (SRF). These results indicate the potential of DRFs as a prognostic marker for patients with rGBM.