MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks
Brain tumors are one of the major health threats to humans, and their complex pathological features and anatomical structures make accurate segmentation and detection crucial. However, existing models based on Transformers and Convolutional Neural Networks (CNNs) still have limitations in medical im...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2025.1513059/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582902620094464 |
|---|---|
| author | Lijuan Yang Lijuan Yang Qiumei Dong Da Lin Chunfang Tian Xinliang Lü |
| author_facet | Lijuan Yang Lijuan Yang Qiumei Dong Da Lin Chunfang Tian Xinliang Lü |
| author_sort | Lijuan Yang |
| collection | DOAJ |
| description | Brain tumors are one of the major health threats to humans, and their complex pathological features and anatomical structures make accurate segmentation and detection crucial. However, existing models based on Transformers and Convolutional Neural Networks (CNNs) still have limitations in medical image processing. While Transformers are proficient in capturing global features, they suffer from high computational complexity and require large amounts of data for training. On the other hand, CNNs perform well in extracting local features but have limited performance when handling global information. To address these issues, this paper proposes a novel network framework, MUNet, which combines the advantages of UNet and Mamba, specifically designed for brain tumor segmentation. MUNet introduces the SD-SSM module, which effectively captures both global and local features of the image through selective scanning and state-space modeling, significantly improving segmentation accuracy. Additionally, we design the SD-Conv structure, which reduces feature redundancy without increasing model parameters, further enhancing computational efficiency. Finally, we propose a new loss function that combines mIoU loss, Dice loss, and Boundary loss, which improves segmentation overlap, similarity, and boundary accuracy from multiple perspectives. Experimental results show that, on the BraTS2020 dataset, MUNet achieves DSC values of 0.835, 0.915, and 0.823 for enhancing tumor (ET), whole tumor (WT), and tumor core (TC), respectively, and Hausdorff95 scores of 2.421, 3.755, and 6.437. On the BraTS2018 dataset, MUNet achieves DSC values of 0.815, 0.901, and 0.815, with Hausdorff95 scores of 4.389, 6.243, and 6.152, all outperforming existing methods and achieving significant performance improvements. Furthermore, when validated on the independent LGG dataset, MUNet demonstrated excellent generalization ability, proving its effectiveness in various medical imaging scenarios. The code is available at https://github.com/Dalin1977331/MUNet. |
| format | Article |
| id | doaj-art-6068b4f5f9b346479770912bfc53373f |
| institution | Kabale University |
| issn | 1662-5188 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj-art-6068b4f5f9b346479770912bfc53373f2025-01-29T06:46:00ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882025-01-011910.3389/fncom.2025.15130591513059MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networksLijuan Yang0Lijuan Yang1Qiumei Dong2Da Lin3Chunfang Tian4Xinliang Lü5Department of Rheumatology, Inner Mongolia Autonomous Region Hospital of Traditional Chinese Medicine, Hohhot, ChinaCollege of Traditional Chinese Medicine, Inner Mongolia Medical University, Hohhot, ChinaCollege of Traditional Chinese Medicine, Inner Mongolia Medical University, Hohhot, ChinaSchool of Mathematical Sciences, Inner Mongolia University, Hohhot, ChinaDepartment of Oncology, Inner Mongolia Autonomous Region Hospital of Traditional Chinese Medicine, Hohhot, ChinaDepartment of Rheumatology, Inner Mongolia Autonomous Region Hospital of Traditional Chinese Medicine, Hohhot, ChinaBrain tumors are one of the major health threats to humans, and their complex pathological features and anatomical structures make accurate segmentation and detection crucial. However, existing models based on Transformers and Convolutional Neural Networks (CNNs) still have limitations in medical image processing. While Transformers are proficient in capturing global features, they suffer from high computational complexity and require large amounts of data for training. On the other hand, CNNs perform well in extracting local features but have limited performance when handling global information. To address these issues, this paper proposes a novel network framework, MUNet, which combines the advantages of UNet and Mamba, specifically designed for brain tumor segmentation. MUNet introduces the SD-SSM module, which effectively captures both global and local features of the image through selective scanning and state-space modeling, significantly improving segmentation accuracy. Additionally, we design the SD-Conv structure, which reduces feature redundancy without increasing model parameters, further enhancing computational efficiency. Finally, we propose a new loss function that combines mIoU loss, Dice loss, and Boundary loss, which improves segmentation overlap, similarity, and boundary accuracy from multiple perspectives. Experimental results show that, on the BraTS2020 dataset, MUNet achieves DSC values of 0.835, 0.915, and 0.823 for enhancing tumor (ET), whole tumor (WT), and tumor core (TC), respectively, and Hausdorff95 scores of 2.421, 3.755, and 6.437. On the BraTS2018 dataset, MUNet achieves DSC values of 0.815, 0.901, and 0.815, with Hausdorff95 scores of 4.389, 6.243, and 6.152, all outperforming existing methods and achieving significant performance improvements. Furthermore, when validated on the independent LGG dataset, MUNet demonstrated excellent generalization ability, proving its effectiveness in various medical imaging scenarios. The code is available at https://github.com/Dalin1977331/MUNet.https://www.frontiersin.org/articles/10.3389/fncom.2025.1513059/fullbrain tumor segmentationdeep learningMUNetSD-SSM modulemedical image analysis |
| spellingShingle | Lijuan Yang Lijuan Yang Qiumei Dong Da Lin Chunfang Tian Xinliang Lü MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks Frontiers in Computational Neuroscience brain tumor segmentation deep learning MUNet SD-SSM module medical image analysis |
| title | MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks |
| title_full | MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks |
| title_fullStr | MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks |
| title_full_unstemmed | MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks |
| title_short | MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks |
| title_sort | munet a novel framework for accurate brain tumor segmentation combining unet and mamba networks |
| topic | brain tumor segmentation deep learning MUNet SD-SSM module medical image analysis |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2025.1513059/full |
| work_keys_str_mv | AT lijuanyang munetanovelframeworkforaccuratebraintumorsegmentationcombiningunetandmambanetworks AT lijuanyang munetanovelframeworkforaccuratebraintumorsegmentationcombiningunetandmambanetworks AT qiumeidong munetanovelframeworkforaccuratebraintumorsegmentationcombiningunetandmambanetworks AT dalin munetanovelframeworkforaccuratebraintumorsegmentationcombiningunetandmambanetworks AT chunfangtian munetanovelframeworkforaccuratebraintumorsegmentationcombiningunetandmambanetworks AT xinlianglu munetanovelframeworkforaccuratebraintumorsegmentationcombiningunetandmambanetworks |