Preprocessing techniques for brain mri scans: a comparative analysis for radiogenomics applications

TitlePreprocessing techniques for brain mri scans: a comparative analysis for radiogenomics applications
Publication TypeJournal Article
Year of Publication2023
AuthorsMiteva M, Nisheva-Pavlova M
JournalAnnuaire de l’Université de Sofia “St. Kliment Ohridski”. Faculté de Mathématiques et Informatique
Volume110
Start Page111
Pagination111-125
ISSN1313-9215 (Print) 2603-5529 (Online)
Keywordsdeep learning, glioblastoma, machine learning, medical imaging, MGMT promoter, MRI scans, radiogenomics
Abstract

In this study, we aim to investigate the use of preprocessing techniques on brain magnetic resonance imaging (MRI) scans for the prediction of Methylguanine-DNA methyltransferase methylation (MGMT) status in glioma patients. MGMT methylation is a biomarker that has been linked to treatment response and prognosis in glioma. We review several studies that have applied preprocessing techniques to brain MRI scans, along with molecular genetic information, for this purpose. The preprocessing techniques include but are not limited to image registration, normalization, brain extraction, and tumor segmentation. We compare the effectiveness of the techniques used in these studies and evaluate the performance of each technique in terms of accuracy, computational efficiency and other parameters. Our goal is to identify the most effective preprocessing techniques for radiogenomics applications and to determine the potential of these techniques for improving the accuracy of predictions in brain MRI scans by combining different types of data. The results of this study have the potential to serve as a basis for the development of more accurate and efficient imaging-based diagnostic tools for glioma patients, and to improve the understanding of the relationship between imaging and genomics in glioma.

DOI10.60063/GSU.FMI.110.111-125
AttachmentSize
PDF icon 110-111-125.pdf432.47 KB