AUTHOR=He Yongqi , Duan Ling , Dong Gehong , Chen Feng , Li Wenbin 

TITLE=Computational pathology-based weakly supervised prediction model for MGMT promoter methylation status in glioblastoma

JOURNAL=Frontiers in Neurology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2024.1345687

DOI=10.3389/fneur.2024.1345687

ISSN=1664-2295

ABSTRACT=The methylation status of oxygen 6-methylguanine-DNA methyltransferase (MGMT) is closely related to the treatment and prognosis of glioblastoma. However, there are currently some challenges in detecting the methylation status for MGMT promoter. The Hematoxylin and Eosin (H&E) stained histopathological slides have always been the gold standard for tumor diagnosis. In this study, we constructed a weakly supervised prediction model for MGMT promoter methylation status of glioblastoma based on H&E-stained whole slide images (WSI) from the TCGA database and our hospital. The accuracy scores of this model in the TCGA dataset and our independent dataset were 0.79 (AUC = 0.86) and 0.76 (AUC= 0.83) respectively. The model demonstrates effective prediction of MGMT promoter methylation status in glioblastoma and exhibits some degree of generalization capability.