Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach

<b>Background/Objectives</b>: Glioblastoma (GBM) is a highly aggressive primary central nervous system tumor with a median survival of 14 months. MGMT (O6-methylguanine-DNA methyltransferase) promoter methylation status is a key biomarker as a prognostic indicator and a predictor of chem...

Full description

Saved in:
Bibliographic Details
Main Authors: Erdal Tasci, Ying Zhuge, Longze Zhang, Holly Ning, Jason Y. Cheng, Robert W. Miller, Kevin Camphausen, Andra V. Krauze
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/10/1292
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327656084963328
author Erdal Tasci
Ying Zhuge
Longze Zhang
Holly Ning
Jason Y. Cheng
Robert W. Miller
Kevin Camphausen
Andra V. Krauze
author_facet Erdal Tasci
Ying Zhuge
Longze Zhang
Holly Ning
Jason Y. Cheng
Robert W. Miller
Kevin Camphausen
Andra V. Krauze
author_sort Erdal Tasci
collection DOAJ
description <b>Background/Objectives</b>: Glioblastoma (GBM) is a highly aggressive primary central nervous system tumor with a median survival of 14 months. MGMT (O6-methylguanine-DNA methyltransferase) promoter methylation status is a key biomarker as a prognostic indicator and a predictor of chemotherapy response in GBM. Patients with MGMT methylated disease progress later and survive longer (median survival rate 22 vs. 15 months, respectively) as compared to patients with MGMT unmethylated disease. Patients with GBM undergo an MRI of the brain prior to diagnosis and following surgical resection for radiation therapy planning and ongoing follow-up. There is currently no imaging biomarker for GBM. Studies have attempted to connect MGMT methylation status to MRI imaging appearance to determine if brain MRI can be leveraged to provide MGMT status information non-invasively and more expeditiously. <b>Methods</b>: Artificial intelligence (AI) can identify MRI features that are not distinguishable to the human eye and can be linked to MGMT status. We employed the UPenn-GBM dataset patients for whom methylation status was available (<i>n</i> = 146), employing a novel radiomic method grounded in hybrid feature selection and weighting to predict MGMT methylation status. <b>Results</b>: The best MGMT classification and feature selection result obtained resulted in a mean accuracy rate value of 81.6% utilizing 101 selected features and five-fold cross-validation. <b>Conclusions</b>: This compared favorably with similar studies in the literature. Validation with external datasets remains critical to enhance generalizability and propagate robust results while reducing bias. Future directions include multi-channel data integration with radiomic features and deep and ensemble learning methods to improve predictive performance.
format Article
id doaj-art-bef187dc2d8844ef87434d68b6be2180
institution Kabale University
issn 2075-4418
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-bef187dc2d8844ef87434d68b6be21802025-08-20T03:47:48ZengMDPI AGDiagnostics2075-44182025-05-011510129210.3390/diagnostics15101292Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting ApproachErdal Tasci0Ying Zhuge1Longze Zhang2Holly Ning3Jason Y. Cheng4Robert W. Miller5Kevin Camphausen6Andra V. Krauze7Radiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USA<b>Background/Objectives</b>: Glioblastoma (GBM) is a highly aggressive primary central nervous system tumor with a median survival of 14 months. MGMT (O6-methylguanine-DNA methyltransferase) promoter methylation status is a key biomarker as a prognostic indicator and a predictor of chemotherapy response in GBM. Patients with MGMT methylated disease progress later and survive longer (median survival rate 22 vs. 15 months, respectively) as compared to patients with MGMT unmethylated disease. Patients with GBM undergo an MRI of the brain prior to diagnosis and following surgical resection for radiation therapy planning and ongoing follow-up. There is currently no imaging biomarker for GBM. Studies have attempted to connect MGMT methylation status to MRI imaging appearance to determine if brain MRI can be leveraged to provide MGMT status information non-invasively and more expeditiously. <b>Methods</b>: Artificial intelligence (AI) can identify MRI features that are not distinguishable to the human eye and can be linked to MGMT status. We employed the UPenn-GBM dataset patients for whom methylation status was available (<i>n</i> = 146), employing a novel radiomic method grounded in hybrid feature selection and weighting to predict MGMT methylation status. <b>Results</b>: The best MGMT classification and feature selection result obtained resulted in a mean accuracy rate value of 81.6% utilizing 101 selected features and five-fold cross-validation. <b>Conclusions</b>: This compared favorably with similar studies in the literature. Validation with external datasets remains critical to enhance generalizability and propagate robust results while reducing bias. Future directions include multi-channel data integration with radiomic features and deep and ensemble learning methods to improve predictive performance.https://www.mdpi.com/2075-4418/15/10/1292MGMTradiomicsimage processingmachine learningfeature extractionfeature selection
spellingShingle Erdal Tasci
Ying Zhuge
Longze Zhang
Holly Ning
Jason Y. Cheng
Robert W. Miller
Kevin Camphausen
Andra V. Krauze
Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach
Diagnostics
MGMT
radiomics
image processing
machine learning
feature extraction
feature selection
title Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach
title_full Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach
title_fullStr Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach
title_full_unstemmed Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach
title_short Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach
title_sort radiomics and ai based prediction of mgmt methylation status in glioblastoma using multiparametric mri a hybrid feature weighting approach
topic MGMT
radiomics
image processing
machine learning
feature extraction
feature selection
url https://www.mdpi.com/2075-4418/15/10/1292
work_keys_str_mv AT erdaltasci radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach
AT yingzhuge radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach
AT longzezhang radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach
AT hollyning radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach
AT jasonycheng radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach
AT robertwmiller radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach
AT kevincamphausen radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach
AT andravkrauze radiomicsandaibasedpredictionofmgmtmethylationstatusinglioblastomausingmultiparametricmriahybridfeatureweightingapproach