Back to Search
Start Over
Radiomics signature: A potential biomarker for the prediction of MGMT promoter methylation in glioblastoma.
- Source :
-
Journal of magnetic resonance imaging : JMRI [J Magn Reson Imaging] 2018 May; Vol. 47 (5), pp. 1380-1387. Date of Electronic Publication: 2017 Sep 19. - Publication Year :
- 2018
-
Abstract
- Background: In glioblastoma (GBM), promoter methylation of the DNA repair gene O-methylguanine-DNA methyltransferase (MGMT) is associated with beneficial chemotherapy.<br />Purpose/hypothesis: To analyze radiomics features for utilizing the full potential of medical imaging as biomarkers of MGMT promoter methylation.<br />Study Type: Retrospective.<br />Population/subjects: In all, 98 GBM patients with known MGMT (48 methylated and 50 unmethylated tumors).<br />Field Strength/sequence: 3.0T magnetic resonance (MR) images, containing T <subscript>1</subscript> -weighted image (T <subscript>1</subscript> WI), T <subscript>2</subscript> -weighted image (T <subscript>2</subscript> WI), and enhanced T <subscript>1</subscript> WI.<br />Assessment: A region of interest (ROI) of the tumor was delineated. A total of 1665 radiomics features were extracted and quantized, and were reduced using least absolute shrinkage and selection operator (LASSO) regularization.<br />Statistical Testing: After the support vector machine construction, accuracy, sensitivity, and specificity were computed for different sequences. An independent validation cohort containing 20 GBM patients was utilized to further evaluate the radiomics model performance.<br />Results: Radiomics features of T <subscript>1</subscript> WI reached an accuracy of 67.54%. Enhanced T <subscript>1</subscript> WI features reached an accuracy of 82.01%, while T <subscript>2</subscript> WI reached an accuracy of 69.25%. The best classification system for predicting MGMT promoter methylation status originated from the combination of 36 T <subscript>1</subscript> WI, T <subscript>2</subscript> WI, and enhanced T <subscript>1</subscript> WI images features, with an accuracy of 86.59%. Further validation on the independent cohort of 20 patients produced similar results, with an accuracy of 80%.<br />Data Conclusion: Our results provide further evidence that radiomics MR features could predict MGMT methylation status in preoperative GBM. Multiple imaging modalities together can yield putative noninvasive biomarkers for the identification of MGMT.<br />Level of Evidence: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1380-1387.<br /> (© 2017 International Society for Magnetic Resonance in Medicine.)
- Subjects :
- Adolescent
Adult
Antineoplastic Agents pharmacology
Biomarkers, Tumor
Child
Child, Preschool
Female
Humans
Infant
Infant, Newborn
Male
Middle Aged
Reproducibility of Results
Retrospective Studies
Support Vector Machine
Young Adult
Brain Neoplasms genetics
DNA Methylation
DNA Modification Methylases genetics
DNA Repair Enzymes genetics
Glioblastoma genetics
Magnetic Resonance Imaging
Promoter Regions, Genetic
Tumor Suppressor Proteins genetics
Subjects
Details
- Language :
- English
- ISSN :
- 1522-2586
- Volume :
- 47
- Issue :
- 5
- Database :
- MEDLINE
- Journal :
- Journal of magnetic resonance imaging : JMRI
- Publication Type :
- Academic Journal
- Accession number :
- 28926163
- Full Text :
- https://doi.org/10.1002/jmri.25860