Scholarlink

The research work aims to predict the genetic subtype of glioblastoma, a malignant brain tumour, using MRI scans and specifically targeting the presence of MGMT promoter methylation. This biomarker has been proved as a favorable prognostic factor and a best predictor of chemotherapy responsiveness in glioblastoma patients. By utilizing MRI scans, the proposed model is trained and tested to detect the presence of MGMT promoter methylation, providing a less invasive and customized diagnosis and treatment approach for brain cancer patients. In this research work the ResNet50 CNN model is employed to predict the genetic subtype of glioblastoma based on MRI scans. The experimental results demonstrate promising outcomes, with an accuracy of 0.73. This accuracy surpasses the performance of the latest solution posted in an online challenge platform, which achieved an accuracy of 0.62. The proposed method can be employed to increase the survival and management of the patients with brain cancer through accurately predicting the genetic subtype of glioblastoma using MRI scans Customized treatment strategies can be introduced before surgery, leading to more effective and tailored approaches in the diagnosis and treatment of glioblastoma.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting Methylation Status in Glioblastoma Patients Using MRI Images

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Puneet Pandit,
  • Karthik Patil,
  • Rohan Reddy,
  • Sainath Kulkarni,
  • Uday A. Nuli,
  • Nirmala Patil,
  • Shrinivas D. Desai

摘要

The research work aims to predict the genetic subtype of glioblastoma, a malignant brain tumour, using MRI scans and specifically targeting the presence of MGMT promoter methylation. This biomarker has been proved as a favorable prognostic factor and a best predictor of chemotherapy responsiveness in glioblastoma patients. By utilizing MRI scans, the proposed model is trained and tested to detect the presence of MGMT promoter methylation, providing a less invasive and customized diagnosis and treatment approach for brain cancer patients. In this research work the ResNet50 CNN model is employed to predict the genetic subtype of glioblastoma based on MRI scans. The experimental results demonstrate promising outcomes, with an accuracy of 0.73. This accuracy surpasses the performance of the latest solution posted in an online challenge platform, which achieved an accuracy of 0.62. The proposed method can be employed to increase the survival and management of the patients with brain cancer through accurately predicting the genetic subtype of glioblastoma using MRI scans Customized treatment strategies can be introduced before surgery, leading to more effective and tailored approaches in the diagnosis and treatment of glioblastoma.