Ilker Ozgur KoskaCagan Koska2025-10-062025204523222045-232210.1038/s41598-025-87803-0https://www.scopus.com/inward/record.uri?eid=2-s2.0-85216996610&doi=10.1038%2Fs41598-025-87803-0&partnerID=40&md5=c7aac31150acdd4472034267ae57651bhttps://gcris.yasar.edu.tr/handle/123456789/7959We aimed to build a robust classifier for the MGMT methylation status of glioblastoma in multiparametric MRI. We focused on multi-habitat deep image descriptors as our basic focus. A subset of the BRATS 2021 MGMT methylation dataset containing both MGMT class labels and segmentation masks was used. A comprehensive mask fusion approach was developed to select relevant image crops of diseased tissue. These fusion masks which were guided by multiple sequences helped collect information from the regions that seem disease-free to radiologists in standard MRI sequences while harboring pathology. Integrating the information in different MRI sequences and leveraging the high entropic capacity of deep neural networks we built a 3D ROI-based custom CNN classifier for the automatic prediction of MGMT methylation status of glioblastoma in multi-parametric MRI. Single sequence-based classifiers reached intermediate predictive performance with 0.65 0.71 0.77 and 0.82 accuracy for T1W T2W T1 contrast-enhanced and FLAIR sequences respectively. The multiparametric classifier using T1 contrast-enhanced and FLAIR images reached 0.88 accuracy. The accuracy of the four-input model that used all sequences was 0.81. The best model reached 0.90 ROC AUC value. Integrating human knowledge in the form of relevant target selection was a useful approach in MGMT methylation status prediction in MRI. Exploration of means to integrate radiology knowledge into the models and achieve human-machine collaboration may help to develop better models. MGMT methylation status of glioblastoma is an important prognostic marker and is also important for treatment decisions. The preoperative non-invasive predictive ability and the explanation tools of the developed model may help clinicians to better understand imaging phenotypes of MGMT methylation status of glial tumors. © 2025 Elsevier B.V. All rights reserved.EnglishArtificial Intelligence, Deep Learning, Glioblastoma, Mgmt Methylation, Model Explanation, Dna Ligase, Dna Methyltransferase, Dna Modification Methylases, Dna Repair Enzymes, Mgmt Protein Human, Tumor Suppressor Proteins, Dna Ligase, Dna Methyltransferase, Mgmt Protein Human, Tumor Suppressor Protein, Brain Tumor, Deep Learning, Diagnostic Imaging, Dna Methylation, Genetics, Glioblastoma, Human, Metabolism, Multiparametric Magnetic Resonance Imaging, Nuclear Magnetic Resonance Imaging, Pathology, Procedures, Brain Neoplasms, Deep Learning, Dna Methylation, Dna Modification Methylases, Dna Repair Enzymes, Glioblastoma, Humans, Magnetic Resonance Imaging, Multiparametric Magnetic Resonance Imaging, Tumor Suppressor ProteinsDNA ligase, DNA methyltransferase, MGMT protein human, tumor suppressor protein, brain tumor, deep learning, diagnostic imaging, DNA methylation, genetics, glioblastoma, human, metabolism, multiparametric magnetic resonance imaging, nuclear magnetic resonance imaging, pathology, procedures, Brain Neoplasms, Deep Learning, DNA Methylation, DNA Modification Methylases, DNA Repair Enzymes, Glioblastoma, Humans, Magnetic Resonance Imaging, Multiparametric Magnetic Resonance Imaging, Tumor Suppressor ProteinsArticle