Magnetic resonance imaging-based deep learning for predicting subtypes of glioma
PurposeTo explore the value of deep learning based on magnetic resonance imaging (MRI) in the classification of glioma subtypes.MethodsThis study retrospectively included 747 adult patients with surgically pathologically confirmed gliomas from a public database and 64 patients from our hospital. Pat...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2025.1518815/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582934728540160 |
|---|---|
| author | Zhen Yang Zhen Yang Peng Zhang Yi Ding Liyi Deng Tong Zhang Yong Liu |
| author_facet | Zhen Yang Zhen Yang Peng Zhang Yi Ding Liyi Deng Tong Zhang Yong Liu |
| author_sort | Zhen Yang |
| collection | DOAJ |
| description | PurposeTo explore the value of deep learning based on magnetic resonance imaging (MRI) in the classification of glioma subtypes.MethodsThis study retrospectively included 747 adult patients with surgically pathologically confirmed gliomas from a public database and 64 patients from our hospital. Patients were classified into IDH-wildtype (IDHwt) (490 cases), IDH-mutant/1p19q-noncodeleted (IDHmut-intact) (105 cases), and IDH-mutant/1p19q-codeleted (IDHmut-codel) (216 cases) based on their pathological findings, with the public database of patients were divided into training and validation sets, and patients from our hospital were used as an independent test set. The models were developed based on five categories of preoperative T1-weighted, T1-weighted gadolinium contrast-enhanced, T2-weighted and T2-weighted fluid-attenuated inversion recovery (T1w, T1c, T2w and FLAIR) magnetic resonance imaging (MRI) of four sequences and mixed imaging of the four sequences, respectively. The receiver operating characteristic curve (ROC), area under the curve (AUC) of the ROC were generated in the jupyter notebook tool using python language to evaluate the accuracy of the models in classification and comparing the predictive value of different MRI sequences.ResultsIDHwt, IDHmut-intact and IDHmut-codel were the best classified in the model containing only FLAIR sequences, with test set AUCs of 0.790, 0.737 and 0.820, respectively; and the worst classified in the model containing only T1w sequences, with test set AUCs of 0.621, 0.537 and 0.760, respectively.ConclusionWe have developed a set of models that can effectively classify glioma subtypes and that work best when only the FLAIR sequence model is included. |
| format | Article |
| id | doaj-art-2b905661852241829c9c861d53e93d2c |
| institution | Kabale University |
| issn | 1664-2295 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj-art-2b905661852241829c9c861d53e93d2c2025-01-29T05:21:09ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-01-011610.3389/fneur.2025.15188151518815Magnetic resonance imaging-based deep learning for predicting subtypes of gliomaZhen Yang0Zhen Yang1Peng Zhang2Yi Ding3Liyi Deng4Tong Zhang5Yong Liu6Department of Neurosurgery, The Second People’s Hospital of Hefei, Hefei Hospital Affiliated to Anhui Medical University, Hefei, ChinaDepartment of Neurosurgery, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, ChinaDepartment of Neurosurgery, The Second People’s Hospital of Hefei, Hefei Hospital Affiliated to Anhui Medical University, Hefei, ChinaDepartment of Neurosurgery, The Second People’s Hospital of Hefei, Hefei Hospital Affiliated to Anhui Medical University, Hefei, ChinaDepartment of Neurosurgery, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, ChinaDepartment of Neurosurgery, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, ChinaDepartment of Neurosurgery, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, ChinaPurposeTo explore the value of deep learning based on magnetic resonance imaging (MRI) in the classification of glioma subtypes.MethodsThis study retrospectively included 747 adult patients with surgically pathologically confirmed gliomas from a public database and 64 patients from our hospital. Patients were classified into IDH-wildtype (IDHwt) (490 cases), IDH-mutant/1p19q-noncodeleted (IDHmut-intact) (105 cases), and IDH-mutant/1p19q-codeleted (IDHmut-codel) (216 cases) based on their pathological findings, with the public database of patients were divided into training and validation sets, and patients from our hospital were used as an independent test set. The models were developed based on five categories of preoperative T1-weighted, T1-weighted gadolinium contrast-enhanced, T2-weighted and T2-weighted fluid-attenuated inversion recovery (T1w, T1c, T2w and FLAIR) magnetic resonance imaging (MRI) of four sequences and mixed imaging of the four sequences, respectively. The receiver operating characteristic curve (ROC), area under the curve (AUC) of the ROC were generated in the jupyter notebook tool using python language to evaluate the accuracy of the models in classification and comparing the predictive value of different MRI sequences.ResultsIDHwt, IDHmut-intact and IDHmut-codel were the best classified in the model containing only FLAIR sequences, with test set AUCs of 0.790, 0.737 and 0.820, respectively; and the worst classified in the model containing only T1w sequences, with test set AUCs of 0.621, 0.537 and 0.760, respectively.ConclusionWe have developed a set of models that can effectively classify glioma subtypes and that work best when only the FLAIR sequence model is included.https://www.frontiersin.org/articles/10.3389/fneur.2025.1518815/fulldeep learningIDHglioma1p/19qMRI |
| spellingShingle | Zhen Yang Zhen Yang Peng Zhang Yi Ding Liyi Deng Tong Zhang Yong Liu Magnetic resonance imaging-based deep learning for predicting subtypes of glioma Frontiers in Neurology deep learning IDH glioma 1p/19q MRI |
| title | Magnetic resonance imaging-based deep learning for predicting subtypes of glioma |
| title_full | Magnetic resonance imaging-based deep learning for predicting subtypes of glioma |
| title_fullStr | Magnetic resonance imaging-based deep learning for predicting subtypes of glioma |
| title_full_unstemmed | Magnetic resonance imaging-based deep learning for predicting subtypes of glioma |
| title_short | Magnetic resonance imaging-based deep learning for predicting subtypes of glioma |
| title_sort | magnetic resonance imaging based deep learning for predicting subtypes of glioma |
| topic | deep learning IDH glioma 1p/19q MRI |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2025.1518815/full |
| work_keys_str_mv | AT zhenyang magneticresonanceimagingbaseddeeplearningforpredictingsubtypesofglioma AT zhenyang magneticresonanceimagingbaseddeeplearningforpredictingsubtypesofglioma AT pengzhang magneticresonanceimagingbaseddeeplearningforpredictingsubtypesofglioma AT yiding magneticresonanceimagingbaseddeeplearningforpredictingsubtypesofglioma AT liyideng magneticresonanceimagingbaseddeeplearningforpredictingsubtypesofglioma AT tongzhang magneticresonanceimagingbaseddeeplearningforpredictingsubtypesofglioma AT yongliu magneticresonanceimagingbaseddeeplearningforpredictingsubtypesofglioma |