Spatio-Temporal Representation Decoupling and Enhancement for Federated Instrument Segmentation in Surgical Videos
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_ | 1866917205933817856 |
|---|---|
| author | Fang, Zheng Qi, Xiaoming Feng, Chun-Mei Pei, Jialun Si, Weixin Jin, Yueming |
| author_facet | Fang, Zheng Qi, Xiaoming Feng, Chun-Mei Pei, Jialun Si, Weixin Jin, Yueming |
| contents | Surgical instrument segmentation under Federated Learning (FL) is a promising direction, which enables multiple surgical sites to collaboratively train the model without centralizing datasets. However, there exist very limited FL works in surgical data science, and FL methods for other modalities do not consider inherent characteristics in surgical domain: i) different scenarios show diverse anatomical backgrounds while highly similar instrument representation; ii) there exist surgical simulators which promote large-scale synthetic data generation with minimal efforts. In this paper, we propose a novel Personalized FL scheme, Spatio-Temporal Representation Decoupling and Enhancement (FedST), which wisely leverages surgical domain knowledge during both local-site and global-server training to boost segmentation. Concretely, our model embraces a Representation Separation and Cooperation (RSC) mechanism in local-site training, which decouples the query embedding layer to be trained privately, to encode respective backgrounds. Meanwhile, other parameters are optimized globally to capture the consistent representations of instruments, including the temporal layer to capture similar motion patterns. A textual-guided channel selection is further designed to highlight site-specific features, facilitating model adapta tion to each site. Moreover, in global-server training, we propose Synthesis-based Explicit Representation Quantification (SERQ), which defines an explicit representation target based on synthetic data to synchronize the model convergence during fusion for improving model generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23759 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spatio-Temporal Representation Decoupling and Enhancement for Federated Instrument Segmentation in Surgical Videos Fang, Zheng Qi, Xiaoming Feng, Chun-Mei Pei, Jialun Si, Weixin Jin, Yueming Image and Video Processing Computer Vision and Pattern Recognition Surgical instrument segmentation under Federated Learning (FL) is a promising direction, which enables multiple surgical sites to collaboratively train the model without centralizing datasets. However, there exist very limited FL works in surgical data science, and FL methods for other modalities do not consider inherent characteristics in surgical domain: i) different scenarios show diverse anatomical backgrounds while highly similar instrument representation; ii) there exist surgical simulators which promote large-scale synthetic data generation with minimal efforts. In this paper, we propose a novel Personalized FL scheme, Spatio-Temporal Representation Decoupling and Enhancement (FedST), which wisely leverages surgical domain knowledge during both local-site and global-server training to boost segmentation. Concretely, our model embraces a Representation Separation and Cooperation (RSC) mechanism in local-site training, which decouples the query embedding layer to be trained privately, to encode respective backgrounds. Meanwhile, other parameters are optimized globally to capture the consistent representations of instruments, including the temporal layer to capture similar motion patterns. A textual-guided channel selection is further designed to highlight site-specific features, facilitating model adapta tion to each site. Moreover, in global-server training, we propose Synthesis-based Explicit Representation Quantification (SERQ), which defines an explicit representation target based on synthetic data to synchronize the model convergence during fusion for improving model generalization. |
| title | Spatio-Temporal Representation Decoupling and Enhancement for Federated Instrument Segmentation in Surgical Videos |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.23759 |