Combining mri and histologic imaging features for predicting overall survival in patients with glioma

Abstract

Purpose: To test the hypothesis that combined features from MR and digital histopathologic images more accurately predict overall survival (OS) in patients with glioma compared with MRI or histopathologic features alone. Materials and Methods: Multiparametric MR and histopathologic images in patients with a diagnosis of glioma (high-or low-grade glioma [HGG or LGG]) were obtained from The Cancer Imaging Archive (original images acquired 1983–2008). An extensive set of engineered features such as intensity, histogram, and texture were extracted from delineated tumor regions in MR and histopathologic images. Cox proportional hazard regression and support vector machine classification (SVC) models were applied to (a) MRI features only (MRIcox/svc ), histopathologic features only (HistoPathcox/svc ), and (c) combined MRI and histopathologic features (MRI+HistoPathcox/svc ) and evaluated in a split train-test configuration. Results: A total of 171 patients (mean age, 51 years 6 15; 91 men) were included with HGG (n = 75) and LGG (n = 96). Median OS was 467 days (range, 3–4752 days) for all patients, 350 days (range, 15–1561 days) for HGG, and 595 days (range, 3–4752 days) for LGG. The MRI+HistoPathcox model demonstrated higher concordance index (C-index) compared with MRIcox and HistoPathcox models on all patients (C-index, 0.79 vs 0.70 [P = .02; MRIcox ] and 0.67 [P = .01; HistoPathcox ]), patients with HGG (C-index, 0.78 vs 0.68 [P = .03; MRIcox ] and 0.64 [P = .01; HistoPathcox ]), and patients with LGG (C-index, 0.88 vs 0.62 [P = .008; MRIcox ] and 0.62 [P = .006; HistoPathcox ]). In binary classification, the MRI+HistoPathsvc model (area under the receiver operating characteristic curve [AUC], 0.86 [95% CI: 0.80, 0.95]) had higher performance than the MRIsvc model (AUC, 0.68 [95% CI: 0.50, 0.81]; P = .01) and the HistoPathsvc model (AUC, 0.72 [95% CI: 0.60, 0.85]; P = .04). Conclusion: The model combining features from MR and histopathologic images had higher accuracy in predicting OS compared with the models with MR or histopathologic images alone.