DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908396090818560 |
|---|---|
| author | Zhao, Ziwei Zhang, Zhixing Liu, Yuhang Zhang, Zhao Yu, Haojun Wang, Dong Wang, Liwei |
| author_facet | Zhao, Ziwei Zhang, Zhixing Liu, Yuhang Zhang, Zhao Yu, Haojun Wang, Dong Wang, Liwei |
| contents | In the field of 3D medical imaging, accurately extracting and representing the blood vessels with curvilinear structures holds paramount importance for clinical diagnosis. Previous methods have commonly relied on discrete representation like mask, often resulting in local fractures or scattered fragments due to the inherent limitations of the per-pixel classification paradigm. In this work, we introduce DeformCL, a new continuous representation based on Deformable Centerlines, where centerline points act as nodes connected by edges that capture spatial relationships. Compared with previous representations, DeformCL offers three key advantages: natural connectivity, noise robustness, and interaction facility. We present a comprehensive training pipeline structured in a cascaded manner to fully exploit these favorable properties of DeformCL. Extensive experiments on four 3D vessel segmentation datasets demonstrate the effectiveness and superiority of our method. Furthermore, the visualization of curved planar reformation images validates the clinical significance of the proposed framework. We release the code in https://github.com/barry664/DeformCL |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05820 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image Zhao, Ziwei Zhang, Zhixing Liu, Yuhang Zhang, Zhao Yu, Haojun Wang, Dong Wang, Liwei Computer Vision and Pattern Recognition In the field of 3D medical imaging, accurately extracting and representing the blood vessels with curvilinear structures holds paramount importance for clinical diagnosis. Previous methods have commonly relied on discrete representation like mask, often resulting in local fractures or scattered fragments due to the inherent limitations of the per-pixel classification paradigm. In this work, we introduce DeformCL, a new continuous representation based on Deformable Centerlines, where centerline points act as nodes connected by edges that capture spatial relationships. Compared with previous representations, DeformCL offers three key advantages: natural connectivity, noise robustness, and interaction facility. We present a comprehensive training pipeline structured in a cascaded manner to fully exploit these favorable properties of DeformCL. Extensive experiments on four 3D vessel segmentation datasets demonstrate the effectiveness and superiority of our method. Furthermore, the visualization of curved planar reformation images validates the clinical significance of the proposed framework. We release the code in https://github.com/barry664/DeformCL |
| title | DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.05820 |