Addition of MR imaging features and genetic biomarkers strengthens glioblastoma survival prediction in TCGA patients

on behalf of the TCGA Glioma Phenotype Research Group

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

Purpose: The purpose of our study was to assess whether a model combining clinical factors, MR imaging features, and genomics would better predict overall survival of patients with glioblastoma (GBM) than either individual data type. Methods: The study was conducted leveraging The Cancer Genome Atlas (TCGA) effort supported by the National Institutes of Health. Six neuroradiologists reviewed MRI images from The Cancer Imaging Archive (http://cancerimagingarchive.net) of 102 GBM patients using the VASARI scoring system. The patients' clinical and genetic data were obtained from the TCGA website (http://www.cancergenome.nih.gov/). Patient outcome was measured in terms of overall survival time. The association between different categories of biomarkers and survival was evaluated using Cox analysis. Results: The features that were significantly associated with survival were: (1) clinical factors: chemotherapy; (2) imaging: proportion of tumor contrast enhancement on MRI; and (3) genomics: HRAS copy number variation. The combination of these three biomarkers resulted in an incremental increase in the strength of prediction of survival, with the model that included clinical, imaging, and genetic variables having the highest predictive accuracy (area under the curve 0.679 ± 0.068, Akaike's information criterion 566.7, P< 0.001). Conclusion: A combination of clinical factors, imaging features, and HRAS copy number variation best predicts survival of patients with GBM.

Original languageEnglish (US)
Pages (from-to)212-221
Number of pages10
JournalJournal of Neuroradiology
Volume42
Issue number4
DOIs
StatePublished - Jul 1 2015

Fingerprint

Atlases
Glioblastoma
Biomarkers
Genome
Survival
Neoplasms
Genomics
National Institutes of Health (U.S.)
Area Under Curve
Drug Therapy

Keywords

  • Genetics
  • Glioblastoma
  • Magnetic resonance imaging
  • Prognosis
  • Survival

ASJC Scopus subject areas

  • Clinical Neurology
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Addition of MR imaging features and genetic biomarkers strengthens glioblastoma survival prediction in TCGA patients. / on behalf of the TCGA Glioma Phenotype Research Group.

In: Journal of Neuroradiology, Vol. 42, No. 4, 01.07.2015, p. 212-221.

Research output: Contribution to journalArticle

on behalf of the TCGA Glioma Phenotype Research Group. / Addition of MR imaging features and genetic biomarkers strengthens glioblastoma survival prediction in TCGA patients. In: Journal of Neuroradiology. 2015 ; Vol. 42, No. 4. pp. 212-221.
@article{7f67de04624d44d791de395227c94520,
title = "Addition of MR imaging features and genetic biomarkers strengthens glioblastoma survival prediction in TCGA patients",
abstract = "Purpose: The purpose of our study was to assess whether a model combining clinical factors, MR imaging features, and genomics would better predict overall survival of patients with glioblastoma (GBM) than either individual data type. Methods: The study was conducted leveraging The Cancer Genome Atlas (TCGA) effort supported by the National Institutes of Health. Six neuroradiologists reviewed MRI images from The Cancer Imaging Archive (http://cancerimagingarchive.net) of 102 GBM patients using the VASARI scoring system. The patients' clinical and genetic data were obtained from the TCGA website (http://www.cancergenome.nih.gov/). Patient outcome was measured in terms of overall survival time. The association between different categories of biomarkers and survival was evaluated using Cox analysis. Results: The features that were significantly associated with survival were: (1) clinical factors: chemotherapy; (2) imaging: proportion of tumor contrast enhancement on MRI; and (3) genomics: HRAS copy number variation. The combination of these three biomarkers resulted in an incremental increase in the strength of prediction of survival, with the model that included clinical, imaging, and genetic variables having the highest predictive accuracy (area under the curve 0.679 ± 0.068, Akaike's information criterion 566.7, P< 0.001). Conclusion: A combination of clinical factors, imaging features, and HRAS copy number variation best predicts survival of patients with GBM.",
keywords = "Genetics, Glioblastoma, Magnetic resonance imaging, Prognosis, Survival",
author = "{on behalf of the TCGA Glioma Phenotype Research Group} and Manal Nicolasjilwan and Ying Hu and Chunhua Yan and Daoud Meerzaman and Holder, {Chad A.} and David Gutman and Rajan Jain and Rivka Colen and Rubin, {Daniel L.} and Zinn, {Pascal O.} and Hwang, {Scott N.} and Prashant Raghavan and Hammoud, {Dima A.} and Scarpace, {Lisa M.} and Tom Mikkelsen and James Chen and Olivier Gevaert and Kenneth Buetow and John Freymann and Justin Kirby and Flanders, {Adam E.} and Max Wintermark",
year = "2015",
month = "7",
day = "1",
doi = "10.1016/j.neurad.2014.02.006",
language = "English (US)",
volume = "42",
pages = "212--221",
journal = "Journal of Neuroradiology",
issn = "0150-9861",
publisher = "Elsevier Masson",
number = "4",

}

TY - JOUR

T1 - Addition of MR imaging features and genetic biomarkers strengthens glioblastoma survival prediction in TCGA patients

AU - on behalf of the TCGA Glioma Phenotype Research Group

AU - Nicolasjilwan, Manal

AU - Hu, Ying

AU - Yan, Chunhua

AU - Meerzaman, Daoud

AU - Holder, Chad A.

AU - Gutman, David

AU - Jain, Rajan

AU - Colen, Rivka

AU - Rubin, Daniel L.

AU - Zinn, Pascal O.

AU - Hwang, Scott N.

AU - Raghavan, Prashant

AU - Hammoud, Dima A.

AU - Scarpace, Lisa M.

AU - Mikkelsen, Tom

AU - Chen, James

AU - Gevaert, Olivier

AU - Buetow, Kenneth

AU - Freymann, John

AU - Kirby, Justin

AU - Flanders, Adam E.

AU - Wintermark, Max

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Purpose: The purpose of our study was to assess whether a model combining clinical factors, MR imaging features, and genomics would better predict overall survival of patients with glioblastoma (GBM) than either individual data type. Methods: The study was conducted leveraging The Cancer Genome Atlas (TCGA) effort supported by the National Institutes of Health. Six neuroradiologists reviewed MRI images from The Cancer Imaging Archive (http://cancerimagingarchive.net) of 102 GBM patients using the VASARI scoring system. The patients' clinical and genetic data were obtained from the TCGA website (http://www.cancergenome.nih.gov/). Patient outcome was measured in terms of overall survival time. The association between different categories of biomarkers and survival was evaluated using Cox analysis. Results: The features that were significantly associated with survival were: (1) clinical factors: chemotherapy; (2) imaging: proportion of tumor contrast enhancement on MRI; and (3) genomics: HRAS copy number variation. The combination of these three biomarkers resulted in an incremental increase in the strength of prediction of survival, with the model that included clinical, imaging, and genetic variables having the highest predictive accuracy (area under the curve 0.679 ± 0.068, Akaike's information criterion 566.7, P< 0.001). Conclusion: A combination of clinical factors, imaging features, and HRAS copy number variation best predicts survival of patients with GBM.

AB - Purpose: The purpose of our study was to assess whether a model combining clinical factors, MR imaging features, and genomics would better predict overall survival of patients with glioblastoma (GBM) than either individual data type. Methods: The study was conducted leveraging The Cancer Genome Atlas (TCGA) effort supported by the National Institutes of Health. Six neuroradiologists reviewed MRI images from The Cancer Imaging Archive (http://cancerimagingarchive.net) of 102 GBM patients using the VASARI scoring system. The patients' clinical and genetic data were obtained from the TCGA website (http://www.cancergenome.nih.gov/). Patient outcome was measured in terms of overall survival time. The association between different categories of biomarkers and survival was evaluated using Cox analysis. Results: The features that were significantly associated with survival were: (1) clinical factors: chemotherapy; (2) imaging: proportion of tumor contrast enhancement on MRI; and (3) genomics: HRAS copy number variation. The combination of these three biomarkers resulted in an incremental increase in the strength of prediction of survival, with the model that included clinical, imaging, and genetic variables having the highest predictive accuracy (area under the curve 0.679 ± 0.068, Akaike's information criterion 566.7, P< 0.001). Conclusion: A combination of clinical factors, imaging features, and HRAS copy number variation best predicts survival of patients with GBM.

KW - Genetics

KW - Glioblastoma

KW - Magnetic resonance imaging

KW - Prognosis

KW - Survival

UR - http://www.scopus.com/inward/record.url?scp=84937640437&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937640437&partnerID=8YFLogxK

U2 - 10.1016/j.neurad.2014.02.006

DO - 10.1016/j.neurad.2014.02.006

M3 - Article

C2 - 24997477

AN - SCOPUS:84937640437

VL - 42

SP - 212

EP - 221

JO - Journal of Neuroradiology

JF - Journal of Neuroradiology

SN - 0150-9861

IS - 4

ER -