A deep ensemble learning framework for glioma segmentation and grading prediction
Abstract The segmentation and risk grade prediction of gliomas based on preoperative multimodal magnetic resonance imaging (MRI) are crucial tasks in computer-aided diagnosis. Due to the significant heterogeneity between and within tumors, existing methods mainly rely on single-task approaches, over...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87127-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862348883951616 |
|---|---|
| author | Liang Wen Hui Sun Guobiao Liang Yue Yu |
| author_facet | Liang Wen Hui Sun Guobiao Liang Yue Yu |
| author_sort | Liang Wen |
| collection | DOAJ |
| description | Abstract The segmentation and risk grade prediction of gliomas based on preoperative multimodal magnetic resonance imaging (MRI) are crucial tasks in computer-aided diagnosis. Due to the significant heterogeneity between and within tumors, existing methods mainly rely on single-task approaches, overlooking the inherent correlation between segmentation and grading tasks. Furthermore, the limited availability of glioma grading data presents further challenges. To address these issues, we propose a deep-ensemble learning framework based on multimodal MRI and the U-Net model, which simultaneously performs glioma segmentation and risk grade prediction. We introduce asymmetric convolution and dual-domain attention in the encoder, fully integrating effective information from different modalities, enhancing the extraction of features from critical regions, and constructing a dual-branch decoder that combines spatial features and global semantic information for both segmentation and grading. In addition, we propose a weighted composite adaptive loss function to balance the optimization objectives of the two tasks. Our experimental results on the BraTS dataset demonstrate that our method outperforms state-of-the-art methods, yielding superior segmentation accuracy and precise risk grade prediction. |
| format | Article |
| id | doaj-art-e02543e795ea470e987a46f3185f1df8 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e02543e795ea470e987a46f3185f1df82025-02-09T12:34:06ZengNature PortfolioScientific Reports2045-23222025-02-0115111510.1038/s41598-025-87127-zA deep ensemble learning framework for glioma segmentation and grading predictionLiang Wen0Hui Sun1Guobiao Liang2Yue Yu3General Hospital of Northern Theater CommandCollege of Information Science and Engineering, Northeastern UniversityGeneral Hospital of Northern Theater CommandCollege of Information Science and Engineering, Northeastern UniversityAbstract The segmentation and risk grade prediction of gliomas based on preoperative multimodal magnetic resonance imaging (MRI) are crucial tasks in computer-aided diagnosis. Due to the significant heterogeneity between and within tumors, existing methods mainly rely on single-task approaches, overlooking the inherent correlation between segmentation and grading tasks. Furthermore, the limited availability of glioma grading data presents further challenges. To address these issues, we propose a deep-ensemble learning framework based on multimodal MRI and the U-Net model, which simultaneously performs glioma segmentation and risk grade prediction. We introduce asymmetric convolution and dual-domain attention in the encoder, fully integrating effective information from different modalities, enhancing the extraction of features from critical regions, and constructing a dual-branch decoder that combines spatial features and global semantic information for both segmentation and grading. In addition, we propose a weighted composite adaptive loss function to balance the optimization objectives of the two tasks. Our experimental results on the BraTS dataset demonstrate that our method outperforms state-of-the-art methods, yielding superior segmentation accuracy and precise risk grade prediction.https://doi.org/10.1038/s41598-025-87127-zGliomaDeep learningSegmentation and grading predictionAttention mechanismDeep-ensemble framework |
| spellingShingle | Liang Wen Hui Sun Guobiao Liang Yue Yu A deep ensemble learning framework for glioma segmentation and grading prediction Scientific Reports Glioma Deep learning Segmentation and grading prediction Attention mechanism Deep-ensemble framework |
| title | A deep ensemble learning framework for glioma segmentation and grading prediction |
| title_full | A deep ensemble learning framework for glioma segmentation and grading prediction |
| title_fullStr | A deep ensemble learning framework for glioma segmentation and grading prediction |
| title_full_unstemmed | A deep ensemble learning framework for glioma segmentation and grading prediction |
| title_short | A deep ensemble learning framework for glioma segmentation and grading prediction |
| title_sort | deep ensemble learning framework for glioma segmentation and grading prediction |
| topic | Glioma Deep learning Segmentation and grading prediction Attention mechanism Deep-ensemble framework |
| url | https://doi.org/10.1038/s41598-025-87127-z |
| work_keys_str_mv | AT liangwen adeepensemblelearningframeworkforgliomasegmentationandgradingprediction AT huisun adeepensemblelearningframeworkforgliomasegmentationandgradingprediction AT guobiaoliang adeepensemblelearningframeworkforgliomasegmentationandgradingprediction AT yueyu adeepensemblelearningframeworkforgliomasegmentationandgradingprediction AT liangwen deepensemblelearningframeworkforgliomasegmentationandgradingprediction AT huisun deepensemblelearningframeworkforgliomasegmentationandgradingprediction AT guobiaoliang deepensemblelearningframeworkforgliomasegmentationandgradingprediction AT yueyu deepensemblelearningframeworkforgliomasegmentationandgradingprediction |