Snake with Shifted Window: Learning to Adapt Vessel Pattern for OCTA Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909183831441408 |
|---|---|
| author | Chen, Xinrun Shen, Mei Ning, Haojian Zhang, Mengzhan Wang, Chengliang Li, Shiying |
| author_facet | Chen, Xinrun Shen, Mei Ning, Haojian Zhang, Mengzhan Wang, Chengliang Li, Shiying |
| contents | Segmenting specific targets or structures in optical coherence tomography angiography (OCTA) images is fundamental for conducting further pathological studies. The retinal vascular layers are rich and intricate, and such vascular with complex shapes can be captured by the widely-studied OCTA images. In this paper, we thus study how to use OCTA images with projection vascular layers to segment retinal structures. To this end, we propose the SSW-OCTA model, which integrates the advantages of deformable convolutions suited for tubular structures and the swin-transformer for global feature extraction, adapting to the characteristics of OCTA modality images. Our model underwent testing and comparison on the OCTA-500 dataset, achieving state-of-the-art performance. The code is available at: https://github.com/ShellRedia/Snake-SWin-OCTA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18096 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Snake with Shifted Window: Learning to Adapt Vessel Pattern for OCTA Segmentation Chen, Xinrun Shen, Mei Ning, Haojian Zhang, Mengzhan Wang, Chengliang Li, Shiying Image and Video Processing Computer Vision and Pattern Recognition Segmenting specific targets or structures in optical coherence tomography angiography (OCTA) images is fundamental for conducting further pathological studies. The retinal vascular layers are rich and intricate, and such vascular with complex shapes can be captured by the widely-studied OCTA images. In this paper, we thus study how to use OCTA images with projection vascular layers to segment retinal structures. To this end, we propose the SSW-OCTA model, which integrates the advantages of deformable convolutions suited for tubular structures and the swin-transformer for global feature extraction, adapting to the characteristics of OCTA modality images. Our model underwent testing and comparison on the OCTA-500 dataset, achieving state-of-the-art performance. The code is available at: https://github.com/ShellRedia/Snake-SWin-OCTA. |
| title | Snake with Shifted Window: Learning to Adapt Vessel Pattern for OCTA Segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.18096 |