GASA-UNet: Global Axial Self-Attention U-Net for 3D Medical Image Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916402550538240 |
|---|---|
| author | Sun, Chengkun Terry, Russell Stevens Bian, Jiang Xu, Jie |
| author_facet | Sun, Chengkun Terry, Russell Stevens Bian, Jiang Xu, Jie |
| contents | Accurate segmentation of multiple organs and the differentiation of pathological tissues in medical imaging are crucial but challenging, especially for nuanced classifications and ambiguous organ boundaries. To tackle these challenges, we introduce GASA-UNet, a refined U-Net-like model featuring a novel Global Axial Self-Attention (GASA) block. This block processes image data as a 3D entity, with each 2D plane representing a different anatomical cross-section. Voxel features are defined within this spatial context, and a Multi-Head Self-Attention (MHSA) mechanism is utilized on extracted 1D patches to facilitate connections across these planes. Positional embeddings (PE) are incorporated into our attention framework, enriching voxel features with spatial context and enhancing tissue classification and organ edge delineation. Our model has demonstrated promising improvements in segmentation performance, particularly for smaller anatomical structures, as evidenced by enhanced Dice scores and Normalized Surface Dice (NSD) on three benchmark datasets, i.e., BTCV, AMOS, and KiTS23. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13146 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GASA-UNet: Global Axial Self-Attention U-Net for 3D Medical Image Segmentation Sun, Chengkun Terry, Russell Stevens Bian, Jiang Xu, Jie Image and Video Processing Computer Vision and Pattern Recognition Accurate segmentation of multiple organs and the differentiation of pathological tissues in medical imaging are crucial but challenging, especially for nuanced classifications and ambiguous organ boundaries. To tackle these challenges, we introduce GASA-UNet, a refined U-Net-like model featuring a novel Global Axial Self-Attention (GASA) block. This block processes image data as a 3D entity, with each 2D plane representing a different anatomical cross-section. Voxel features are defined within this spatial context, and a Multi-Head Self-Attention (MHSA) mechanism is utilized on extracted 1D patches to facilitate connections across these planes. Positional embeddings (PE) are incorporated into our attention framework, enriching voxel features with spatial context and enhancing tissue classification and organ edge delineation. Our model has demonstrated promising improvements in segmentation performance, particularly for smaller anatomical structures, as evidenced by enhanced Dice scores and Normalized Surface Dice (NSD) on three benchmark datasets, i.e., BTCV, AMOS, and KiTS23. |
| title | GASA-UNet: Global Axial Self-Attention U-Net for 3D Medical Image Segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.13146 |