Learning MRI-based classification models for MGMT methylation status prediction in glioblastoma

•A noninvasive and reliable surrogate method of determining MGMT status could serve to complement brain tumor biopsy or as an alternative in those patients who have a contraindication to undergo an invasive procedure.•The significance of magnetic resonance 3D volumetrics and qualitative imaging feat...

Full description

Saved in:
Bibliographic Details
Published in:Computer methods and programs in biomedicine Vol. 140; pp. 249 - 257
Main Authors: Kanas, Vasileios G., Zacharaki, Evangelia I., Thomas, Ginu A., Zinn, Pascal O., Megalooikonomou, Vasileios, Colen, Rivka R.
Format: Journal Article
Language:English
Published: Ireland Elsevier B.V 01.03.2017
Elsevier
Subjects:
Adolescent
Adult
Aged
Aged, 80 and over
Brain Neoplasms - diagnostic imaging
Brain Neoplasms - genetics
Computer Science
DNA Methylation
DNA Modification Methylases - genetics
DNA Modification Methylases - metabolism
DNA Repair Enzymes - genetics
DNA Repair Enzymes - metabolism
Feature extraction
Female
Glioblastoma
Glioblastoma - diagnostic imaging
Glioblastoma - genetics
Humans
Internal Medicine
Machine Learning
Magnetic Resonance Imaging
Male
Medical Imaging
MGMT promoter methylation
Middle Aged
Multivariate analysis
Other
Prediction model
Promoter Regions, Genetic
Tumor Suppressor Proteins - genetics
Tumor Suppressor Proteins - metabolism
Young Adult
Feature extraction
MGMT promoter methylation
Multivariate analysis
Glioblastoma
Prediction model
glioblastoma
prediction model
feature extraction
multivariate analysis
ISSN:0169-2607, 1872-7565, 1872-7565
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A noninvasive and reliable surrogate method of determining MGMT status could serve to complement brain tumor biopsy or as an alternative in those patients who have a contraindication to undergo an invasive procedure.•The significance of magnetic resonance 3D volumetrics and qualitative imaging features for predicting MGMT methylation status in glioblastoma was evaluated (73.6% accuracy achieved).•Our analysis showed that the edema/necrosis volume ratio, tumor/necrosis volume ratio, edema volume, and tumor location and enhancement characteristics were associated with the status of MGMT promoter methylation in glioblastoma.•The results of our study provide further evidence of an association between standard preoperative MRI features and MGMT methylation status in glioblastoma. The O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation has been shown to be associated with improved outcomes in patients with glioblastoma (GBM) and may be a predictive marker of sensitivity to chemotherapy. However, determination of the MGMT promoter methylation status requires tissue obtained via surgical resection or biopsy. The aim of this study was to assess the ability of quantitative and qualitative imaging variables in predicting MGMT methylation status noninvasively. A retrospective analysis of MR images from GBM patients was conducted. Multivariate prediction models were obtained by machine-learning methods and tested on data from The Cancer Genome Atlas (TCGA) database. The status of MGMT promoter methylation was predicted with an accuracy of up to 73.6%. Experimental analysis showed that the edema/necrosis volume ratio, tumor/necrosis volume ratio, edema volume, and tumor location and enhancement characteristics were the most significant variables in respect to the status of MGMT promoter methylation in GBM. The obtained results provide further evidence of an association between standard preoperative MRI variables and MGMT methylation status in GBM.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0169-2607
1872-7565
1872-7565
DOI:10.1016/j.cmpb.2016.12.018