nnY-Net: Swin-NeXt with Cross-Attention for 3D Medical Images Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915088115433472 |
|---|---|
| author | Liu, Haixu Tao, Zerui Dong, Wenzhen Sun, Qiuzhuang |
| author_facet | Liu, Haixu Tao, Zerui Dong, Wenzhen Sun, Qiuzhuang |
| contents | This paper provides a novel 3D medical image segmentation model structure called nnY-Net. This name comes from the fact that our model adds a cross-attention module at the bottom of the U-net structure to form a Y structure. We integrate the advantages of the two latest SOTA models, MedNeXt and SwinUNETR, and use Swin Transformer as the encoder and ConvNeXt as the decoder to innovatively design the Swin-NeXt structure. Our model uses the lowest-level feature map of the encoder as Key and Value and uses patient features such as pathology and treatment information as Query to calculate the attention weights in a Cross Attention module. Moreover, we simplify some pre- and post-processing as well as data enhancement methods in 3D image segmentation based on the dynUnet and nnU-net frameworks. We integrate our proposed Swin-NeXt with Cross-Attention framework into this framework. Last, we construct a DiceFocalCELoss to improve the training efficiency for the uneven data convergence of voxel classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01406 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | nnY-Net: Swin-NeXt with Cross-Attention for 3D Medical Images Segmentation Liu, Haixu Tao, Zerui Dong, Wenzhen Sun, Qiuzhuang Computer Vision and Pattern Recognition This paper provides a novel 3D medical image segmentation model structure called nnY-Net. This name comes from the fact that our model adds a cross-attention module at the bottom of the U-net structure to form a Y structure. We integrate the advantages of the two latest SOTA models, MedNeXt and SwinUNETR, and use Swin Transformer as the encoder and ConvNeXt as the decoder to innovatively design the Swin-NeXt structure. Our model uses the lowest-level feature map of the encoder as Key and Value and uses patient features such as pathology and treatment information as Query to calculate the attention weights in a Cross Attention module. Moreover, we simplify some pre- and post-processing as well as data enhancement methods in 3D image segmentation based on the dynUnet and nnU-net frameworks. We integrate our proposed Swin-NeXt with Cross-Attention framework into this framework. Last, we construct a DiceFocalCELoss to improve the training efficiency for the uneven data convergence of voxel classification. |
| title | nnY-Net: Swin-NeXt with Cross-Attention for 3D Medical Images Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.01406 |