TY - JOUR
T1 - Radiomic subtyping improves disease stratification beyond key molecular, clinical, and standard imaging characteristics in patients with glioblastoma
AU - Kickingereder, Philipp
AU - Neuberger, Ulf
AU - Bonekamp, David
AU - Piechotta, Paula L.
AU - Götz, Michael
AU - Wick, Antje
AU - Sill, Martin
AU - Kratz, Annekathrin
AU - Shinohara, Russell T.
AU - Jones, David T.W.
AU - Radbruch, Alexander
AU - Muschelli, John
AU - Unterberg, Andreas
AU - Debus, Jürgen
AU - Schlemmer, Heinz Peter
AU - Herold-Mende, Christel
AU - Pfister, Stefan
AU - Von Deimling, Andreas
AU - Wick, Wolfgang
AU - Capper, David
AU - Maier-Hein, Klaus H.
AU - Bendszus, Martin
N1 - Funding Information:
P.K. is supported by the Medical Faculty Heidelberg Postdoc-Program and the Else-Kröner Memorial Scholarship of the Else Kröner-Fresenius Foundation. DNA methylation analysis was performed as part of the National Center for Tumor Diseases (NCT) Precision Oncology Program of the Heidelberg Center for Personalized Oncology (German Cancer Research Center–HIPO). We would further like to thank the Genomics and Proteomics Core Facility of the German Cancer Research Center (DKFZ) for excellent technical assistance.
Funding Information:
R.T.S. is funded partially by the National Institutes of Health under award numbers R01NS085211 and U24CA189523. The content is solely the responsibility of the authors and does not necessarily represent the official views of the funding agency.
Publisher Copyright:
© The Author(s) 2017. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved.
PY - 2018/5/18
Y1 - 2018/5/18
N2 - Background The purpose of this study was to analyze the potential of radiomics for disease stratification beyond key molecular, clinical, and standard imaging features in patients with glioblastoma. Methods Quantitative imaging features (n = 1043) were extracted from the multiparametric MRI of 181 patients with newly diagnosed glioblastoma prior to standard-of-care treatment (allocated to a discovery and a validation set, 2:1 ratio). A subset of 386/1043 features were identified as reproducible (in an independent MRI test-retest cohort) and selected for analysis. A penalized Cox model with 10-fold cross-validation (Coxnet) was fitted on the discovery set to construct a radiomic signature for predicting progression-free and overall survival (PFS and OS). The incremental value of a radiomic signature beyond molecular (O 6 -methylguanine-DNA methyltransferase [MGMT] promoter methylation, DNA methylation subgroups), clinical (patient's age, KPS, extent of resection, adjuvant treatment), and standard imaging parameters (tumor volumes) for stratifying PFS and OS was assessed with multivariate Cox models (performance quantified with prediction error curves). Results The radiomic signature (constructed from 8/386 features identified through Coxnet) increased the prediction accuracy for PFS and OS (in both discovery and validation sets) beyond the assessed molecular, clinical, and standard imaging parameters (P ≤ 0.01). Prediction errors decreased by 36% for PFS and 37% for OS when adding the radiomic signature (compared with 29% and 27%, respectively, with molecular + clinical features alone). The radiomic signature was - along with MGMT status - the only parameter with independent significance on multivariate analysis (P ≤ 0.01). Conclusions Our study stresses the role of integrating radiomics into a multilayer decision framework with key molecular and clinical features to improve disease stratification and to potentially advance personalized treatment of patients with glioblastoma.
AB - Background The purpose of this study was to analyze the potential of radiomics for disease stratification beyond key molecular, clinical, and standard imaging features in patients with glioblastoma. Methods Quantitative imaging features (n = 1043) were extracted from the multiparametric MRI of 181 patients with newly diagnosed glioblastoma prior to standard-of-care treatment (allocated to a discovery and a validation set, 2:1 ratio). A subset of 386/1043 features were identified as reproducible (in an independent MRI test-retest cohort) and selected for analysis. A penalized Cox model with 10-fold cross-validation (Coxnet) was fitted on the discovery set to construct a radiomic signature for predicting progression-free and overall survival (PFS and OS). The incremental value of a radiomic signature beyond molecular (O 6 -methylguanine-DNA methyltransferase [MGMT] promoter methylation, DNA methylation subgroups), clinical (patient's age, KPS, extent of resection, adjuvant treatment), and standard imaging parameters (tumor volumes) for stratifying PFS and OS was assessed with multivariate Cox models (performance quantified with prediction error curves). Results The radiomic signature (constructed from 8/386 features identified through Coxnet) increased the prediction accuracy for PFS and OS (in both discovery and validation sets) beyond the assessed molecular, clinical, and standard imaging parameters (P ≤ 0.01). Prediction errors decreased by 36% for PFS and 37% for OS when adding the radiomic signature (compared with 29% and 27%, respectively, with molecular + clinical features alone). The radiomic signature was - along with MGMT status - the only parameter with independent significance on multivariate analysis (P ≤ 0.01). Conclusions Our study stresses the role of integrating radiomics into a multilayer decision framework with key molecular and clinical features to improve disease stratification and to potentially advance personalized treatment of patients with glioblastoma.
KW - MGMT
KW - glioblastoma
KW - radiomics
UR - http://www.scopus.com/inward/record.url?scp=85047750078&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047750078&partnerID=8YFLogxK
U2 - 10.1093/neuonc/nox188
DO - 10.1093/neuonc/nox188
M3 - Article
C2 - 29036412
AN - SCOPUS:85047750078
SN - 1522-8517
VL - 20
SP - 848
EP - 857
JO - Neuro-oncology
JF - Neuro-oncology
IS - 6
ER -