GaMNet: A Hybrid Network with Gabor Fusion and NMamba for Efficient 3D Glioma Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910934533931008 |
|---|---|
| author | Ye, Chengwei Zhang, Huanzhen Lin, Yufei Wang, Kangsheng Xu, Linuo Liu, Shuyan |
| author_facet | Ye, Chengwei Zhang, Huanzhen Lin, Yufei Wang, Kangsheng Xu, Linuo Liu, Shuyan |
| contents | Gliomas are aggressive brain tumors that pose serious health risks. Deep learning aids in lesion segmentation, but CNN and Transformer-based models often lack context modeling or demand heavy computation, limiting real-time use on mobile medical devices. We propose GaMNet, integrating the NMamba module for global modeling and a multi-scale CNN for efficient local feature extraction. To improve interpretability and mimic the human visual system, we apply Gabor filters at multiple scales. Our method achieves high segmentation accuracy with fewer parameters and faster computation. Extensive experiments show GaMNet outperforms existing methods, notably reducing false positives and negatives, which enhances the reliability of clinical diagnosis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05520 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GaMNet: A Hybrid Network with Gabor Fusion and NMamba for Efficient 3D Glioma Segmentation Ye, Chengwei Zhang, Huanzhen Lin, Yufei Wang, Kangsheng Xu, Linuo Liu, Shuyan Computer Vision and Pattern Recognition Artificial Intelligence Gliomas are aggressive brain tumors that pose serious health risks. Deep learning aids in lesion segmentation, but CNN and Transformer-based models often lack context modeling or demand heavy computation, limiting real-time use on mobile medical devices. We propose GaMNet, integrating the NMamba module for global modeling and a multi-scale CNN for efficient local feature extraction. To improve interpretability and mimic the human visual system, we apply Gabor filters at multiple scales. Our method achieves high segmentation accuracy with fewer parameters and faster computation. Extensive experiments show GaMNet outperforms existing methods, notably reducing false positives and negatives, which enhances the reliability of clinical diagnosis. |
| title | GaMNet: A Hybrid Network with Gabor Fusion and NMamba for Efficient 3D Glioma Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.05520 |