Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach
Abstract We 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 w...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87803-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585815054614528 |
|---|---|
| author | İlker Özgür Koska Çağan Koska |
| author_facet | İlker Özgür Koska Çağan Koska |
| author_sort | İlker Özgür Koska |
| collection | DOAJ |
| description | Abstract We 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. |
| format | Article |
| id | doaj-art-eaa1e9d2787942098e2b053f617e64e1 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-eaa1e9d2787942098e2b053f617e64e12025-01-26T12:32:17ZengNature PortfolioScientific Reports2045-23222025-01-0115111410.1038/s41598-025-87803-0Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approachİlker Özgür Koska0Çağan Koska1Department of Radiology, Behçet Uz Children’s HospitalDepartment of Electrical Electronical Engineering, Yaşar UniversityAbstract We 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.https://doi.org/10.1038/s41598-025-87803-0MGMT methylationGlioblastomaArtificial intelligenceDeep learningModel explanation |
| spellingShingle | İlker Özgür Koska Çağan Koska Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach Scientific Reports MGMT methylation Glioblastoma Artificial intelligence Deep learning Model explanation |
| title | Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach |
| title_full | Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach |
| title_fullStr | Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach |
| title_full_unstemmed | Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach |
| title_short | Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach |
| title_sort | deep learning classification of mgmt status of glioblastomas using multiparametric mri with a novel domain knowledge augmented mask fusion approach |
| topic | MGMT methylation Glioblastoma Artificial intelligence Deep learning Model explanation |
| url | https://doi.org/10.1038/s41598-025-87803-0 |
| work_keys_str_mv | AT ilkerozgurkoska deeplearningclassificationofmgmtstatusofglioblastomasusingmultiparametricmriwithanoveldomainknowledgeaugmentedmaskfusionapproach AT cagankoska deeplearningclassificationofmgmtstatusofglioblastomasusingmultiparametricmriwithanoveldomainknowledgeaugmentedmaskfusionapproach |