[PDF] Development of Prediction Models to Detect the Presence of MGMT Promoter Methylation for Prognosis of Brain Tumor | Semantic Scholar (2024)

A compendium of brain MRI scans of GBM patients collected from the Cancer Imaging Archive combined with methylation data from The Cancer Genome Atlas are used to predict the methylation state of the MGMT regulatory regions in these patients, suggesting the existence of MRI features that may complement existing markers for GBM patient stratification and prognosis.

MGMT methylation status of gliomas may not be predictable with preoperative MR images even using deep learning, and prediction models developed using only small datasets without proper external validation achieved good diagnostic performance, however, the diagnostic performance was not reproducible when using a larger dataset in the RSNA-MICCAI Brain Tumor Radiogenomic Classification 2021 challenge.

The deep learning method using MRI radiomics has excellent diagnostic performance with a high accuracy in predicting MGMT promoter methylation in diffuse gliomas.

The combination of radiomics feature extraction and F-core feature selection significantly improved the performance of the XGBoost model, which may have implications for patient stratification and therapeutic strategy in GBM.

A deep learning network for determining MGMT promoter methylation status using T2 weighted Images (T2WI) only surpasses the sensitivity, specificity, and accuracy of histologic and molecular methods and represents an important milestone toward using MR imaging to predict prognosis and treatment response.

This meta-analysis demonstrated that machine learning is a promising, reliable and repeatable candidate method for predicting MGMT promoter methylation status in glioma and showed a higher performance than non-machine learning methods.

Several miRNAs were identified regulating MGMT expression, apart from promoter methylation, by degrading MGMT mRNA before protein translation, which could be a promising innovative treatment approach to enhance Temozolomide sensitivity in MGMT unmethylated patients and to increase progression-free survival as well as long-term survival.

A deep learning pipeline is designed for automatic prediction of MGMT status in 87 glioblastoma patients with contrast-enhanced T1W images and 66 with fluid-attenuated inversion recovery(FLAIR) images and achieves good prediction ofMGMT methylation status.

For The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas and relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human directed training.

...

...