A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme

Abstract

Traditional radiomics models mainly rely on explicitly-designed handcrafted features from medical images. This paper aimed to investigate if deep features extracted via transfer learning can generate radiomics signatures for prediction of overall survival (OS) in patients with Glioblastoma Multiforme (GBM). This study comprised a discovery data set of 75 patients and an independent validation data set of 37 patients. A total of 1403 handcrafted features and 98304 deep features were extracted from preoperative multi-modality MR images. After feature selection, a six-deep-feature signature was constructed by using the least absolute shrinkage and selection operator (LASSO) Cox regression model. A radiomics nomogram was further presented by combining the signature and clinical risk factors such as age and Karnofsky Performance Score. Compared with traditional risk factors, the proposed signature achieved better performance for prediction of OS (C-index = 0.710, 95% CI: 0.588, 0.932) and significant stratification of patients into prognostically distinct groups (P < 0.001, HR = 5.128, 95% CI: 2.029, 12.960). The combined model achieved improved predictive performance (C-index = 0.739). Our study demonstrates that transfer learning-based deep features are able to generate prognostic imaging signature for OS prediction and patient stratification for GBM, indicating the potential of deep imaging feature-based biomarker in preoperative care of GBM patients.

Figure 1

The workflow of radiomics analysis in this study.

Figure 2

Illustration of deep features extraction. LRN is short for Local Response Normalization. The details of the CNN_S framework can be found in Supplementary Table 2.

Figure 3

Illustration of Kaplan-Meier survival curve. The Kaplan-Meier survival curve show OS risk stratification for patients in Discovery data set (a) and Validation data set (b). Patients were classified as low risk and high risk according to radimics signature. The vertical dashed line is 95% confidence interval.

Figure 4

The heat map of selected radiomics feature. Each row of the heat map represents a radiomics feature and each column represents a patient. The Z-Score difference of each radiomics feature between high risk and low risk group can be seen from the heat map. At the same time, it can be observed directly from the heat map that there is a consistency of radiomics feature Z-Score between the discovery data set and the validation data set.

Figure 5

The nomogram (a) and calibration (b) curves. Radiomics signature and clinical data are associated with survival probability of 1, 2 and 3 years. The predictors are radiomics signature score, age of the patient (in years) and Karnofsky performance score (KPS). Draw a vertical line from each predictor to ‘Points’ to get the score of the predictor. Then summing up the scores of each predictor, the ‘Total Points’ correspond to the survival probability of 1, 2 and 3 years by drawing a vertical line from ‘Total Points’ to each survival probability axis. Calibration curves is used to assess the consistency between nomogram-predicted survival probability and actual fraction survival probability.