Predicting MGMT Methylation Status of Glioblastomas from MRI Texture

Authors:
Ilya Levner;Sylvia Drabycz;Gloria Roldan;Paula Robles;J. Gregory Cairncross;Ross Mitchell
Affiliations:
Department of Radiology, University of Calgary, Alberta, Canada and Southern Alberta Cancer Research Institute, University of Calgary, Alberta, Canada and Alberta Ingenuity Center for Machine Lear ...;Department of Electrical and Computer Engineering, University of Calgary, Alberta, Canada;Department of Oncology, Tom Baker Cancer Centre, Alberta Cancer Board, Canada and Hotchkiss Brain Institute, Calgary, Canada and Department of Clinical Neurosciences, University of Calgary, Albert ...;Department of Oncology, Tom Baker Cancer Centre, Alberta Cancer Board, Canada and Hotchkiss Brain Institute, Calgary, Canada and Department of Clinical Neurosciences, University of Calgary, Albert ...;Department of Oncology, Tom Baker Cancer Centre, Alberta Cancer Board, Canada and Hotchkiss Brain Institute, Calgary, Canada and Department of Clinical Neurosciences, University of Calgary, Albert ...;Department of Radiology, University of Calgary, Alberta, Canada and Southern Alberta Cancer Research Institute, University of Calgary, Alberta, Canada and Alberta Ingenuity Center for Machine Lear ...
Venue:
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Year:
2009

Citing 4
Cited 0

Bayesian regularization and pruning using a Laplace prior

Neural Computation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Medical Image Processing, Analysis & Visualization in Clinical Research

CBMS '01 Proceedings of the Fourteenth IEEE Symposium on Computer-Based Medical Systems
A novel MRI texture analysis of demyelination and inflammation in relapsing-remitting experimental allergic encephalomyelitis

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I

Quantified Score

Hi-index	0.01

Visualization

Abstract

In glioblastoma (GBM), promoter methylation of the DNA repair gene MGMT is associated with benefit from chemotherapy. Because MGMT promoter methylation status can not be determined in all cases, a surrogate for the methylation status would be a useful clinical tool. Correlation between methylation status and magnetic resonance imaging features has been reported suggesting that non-invasive MGMT promoter methylation status detection is possible. In this work, a retrospective analysis of T2, FLAIR and T1-post contrast MR images in patients with newly diagnosed GBM is performed using L1-regularized neural networks. Tumor texture, assessed quantitatively was utilized for predicting the MGMT promoter methylation status of a GBM in 59 patients. The texture features were extracted using a space-frequency texture analysis based on the S-transform and utilized by a neural network to predict the methylation status of a GBM. Blinded classification of MGMT promoter methylation status reached an average accuracy of 87.7%, indicating that the proposed technique is accurate enough for clinical use.