HER-Seg: Holistically Efficient Segmentation for High-Resolution Medical Images
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913950632771584 |
|---|---|
| author | Xu, Qing Lou, Zhenye Li, Chenxin Li, Yue He, Xiangjian Berhanu, Tesema Fiseha Qu, Rong Duan, Wenting Chen, Zhen |
| author_facet | Xu, Qing Lou, Zhenye Li, Chenxin Li, Yue He, Xiangjian Berhanu, Tesema Fiseha Qu, Rong Duan, Wenting Chen, Zhen |
| contents | High-resolution segmentation is critical for precise disease diagnosis by extracting fine-grained morphological details. Existing hierarchical encoder-decoder frameworks have demonstrated remarkable adaptability across diverse medical segmentation tasks. While beneficial, they usually require the huge computation and memory cost when handling large-size segmentation, which limits their applications in foundation model building and real-world clinical scenarios. To address this limitation, we propose a holistically efficient framework for high-resolution medical image segmentation, called HER-Seg. Specifically, we first devise a computation-efficient image encoder (CE-Encoder) to model long-range dependencies with linear complexity while maintaining sufficient representations. In particular, we introduce the dual-gated linear attention (DLA) mechanism to perform cascaded token filtering, selectively retaining important tokens while ignoring irrelevant ones to enhance attention computation efficiency. Then, we introduce a memory-efficient mask decoder (ME-Decoder) to eliminate the demand for the hierarchical structure by leveraging cross-scale segmentation decoding. Extensive experiments reveal that HER-Seg outperforms state-of-the-arts in high-resolution medical 2D, 3D and video segmentation tasks. In particular, our HER-Seg requires only 0.59GB training GPU memory and 9.39G inference FLOPs per 1024$\times$1024 image, demonstrating superior memory and computation efficiency. The code is available at https://github.com/xq141839/HER-Seg. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06205 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HER-Seg: Holistically Efficient Segmentation for High-Resolution Medical Images Xu, Qing Lou, Zhenye Li, Chenxin Li, Yue He, Xiangjian Berhanu, Tesema Fiseha Qu, Rong Duan, Wenting Chen, Zhen Image and Video Processing Computer Vision and Pattern Recognition High-resolution segmentation is critical for precise disease diagnosis by extracting fine-grained morphological details. Existing hierarchical encoder-decoder frameworks have demonstrated remarkable adaptability across diverse medical segmentation tasks. While beneficial, they usually require the huge computation and memory cost when handling large-size segmentation, which limits their applications in foundation model building and real-world clinical scenarios. To address this limitation, we propose a holistically efficient framework for high-resolution medical image segmentation, called HER-Seg. Specifically, we first devise a computation-efficient image encoder (CE-Encoder) to model long-range dependencies with linear complexity while maintaining sufficient representations. In particular, we introduce the dual-gated linear attention (DLA) mechanism to perform cascaded token filtering, selectively retaining important tokens while ignoring irrelevant ones to enhance attention computation efficiency. Then, we introduce a memory-efficient mask decoder (ME-Decoder) to eliminate the demand for the hierarchical structure by leveraging cross-scale segmentation decoding. Extensive experiments reveal that HER-Seg outperforms state-of-the-arts in high-resolution medical 2D, 3D and video segmentation tasks. In particular, our HER-Seg requires only 0.59GB training GPU memory and 9.39G inference FLOPs per 1024$\times$1024 image, demonstrating superior memory and computation efficiency. The code is available at https://github.com/xq141839/HER-Seg. |
| title | HER-Seg: Holistically Efficient Segmentation for High-Resolution Medical Images |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.06205 |