چاپ صفحه |  صفحه نخست سامانه |  نویسندگان |  اطلاعات تفضیلی |  دانلود مقاله | دانشگاه علوم پزشکی تبریز |
| نویسنده | نفر چندم مقاله |
|---|---|
| یونس سلیمانی کیچی قلعه سی | اول |
| داود خضرلو | دوم |
| صمد حسنی آغوزی | سوم |
| عنوان | متن |
|---|---|
| خلاصه مقاله | Introduction: Glioblastoma multiform (GBM) is the most common malignant brain tumor which carries a poor prognosis due to its intratumor genetic heterogeneity. Oxygen 6- methylguanine- DNA methyltransferase (MGMT) promotor methylation is a favorable prognostic factor in GBM patients, and patients with GBM and MGMT are more sensitive to temozolomide and radiotherapy. The analysis based on surgical specimens is the standard method for assessing the MGMT status. This method has technical shortcomings such as incomplete biopsy sampling due to the high spatial heterogeneity of GBM tumors and the expensive process of the method that makes it practically impossible in some hospitals. Magnetic resonance imaging (MRI)- based radiomics analysis is a powerful diagnostic tool for GBM tumors management and opens up the possibility of having a preoperative and noninvasive prediction of MGMT methylation status. Radiomics is a newly emerging machine learning-based technology that could resolve the problem of subjective judgments by radiologists that are vulnerable to inter-observer variability by converting encrypted medical images into usable data and extracting high-throughput imaging features and relating features data to clinical outcomes. The purpose of this review study was to investigate the relationship between radiomics features extracted from MRI images and MGMT methylation status in order to evaluate the prediction power of radiomics based machine learning models. Materials and methods: The keywords of 'GBM', 'MGMT methylation status', 'Radiomics' and “MRI” were entered in the scientific databases of Google scholar, Scopus, PubMed, and Elsevier. About 10 fully relevant articles were extracted and reviewed. Then the correlation between MRI-based radiomics and MGMT methylation status were obtained and assessed. Results: All papers indicated that T1-weighted, T2-weighted, and enhanced T1-weighted MRI images were suitable for MGMT methylation status prediction. Among morphological, gray scale and textural based features, the texture features had highest correlation with MGMT methylation status. Studies showed an area under the receiver operative characteristic (ROC) curve (AUC) of 0.88-0.92 and an accuracy of 80%-87% for prediction of MGMT promotor. Also, the results of all studies showed that the combination of T1-weighted, T2-weighted, and enhanced T1-weighted images features had the best classification system for predicting MGMT promoter methylation status. Conclusions: The results of our study showed that radiomics-based quantitative analysis of MR images, can significantly help to prediction of MGMT promoter methylation status. |
| کلمات کلیدی | Keywords: 'GBM', 'MGMT methylation status', 'Radiomics', “MRI” |
| نام فایل | تاریخ درج فایل | اندازه فایل | دانلود |
|---|---|---|---|
| Abstract Book 2020 - 06.pdf | 1399/11/20 | 9487377 | دانلود |
| MRI radiomics.pdf | 1399/11/20 | 125893 | دانلود |
| first page.pdf | 1399/11/20 | 476864 | دانلود |
