Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic Surgery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917750904979456 |
|---|---|
| author | Xu, Jialang Wang, Jiacheng Yu, Lequan Stoyanov, Danail Jin, Yueming Mazomenos, Evangelos B. |
| author_facet | Xu, Jialang Wang, Jiacheng Yu, Lequan Stoyanov, Danail Jin, Yueming Mazomenos, Evangelos B. |
| contents | Personalized federated learning (PFL) for surgical instrument segmentation (SIS) is a promising approach. It enables multiple clinical sites to collaboratively train a series of models in privacy, with each model tailored to the individual distribution of each site. Existing PFL methods rarely consider the personalization of multi-headed self-attention, and do not account for appearance diversity and instrument shape similarity, both inherent in surgical scenes. We thus propose PFedSIS, a novel PFL method with visual trait priors for SIS, incorporating global-personalized disentanglement (GPD), appearance-regulation personalized enhancement (APE), and shape-similarity global enhancement (SGE), to boost SIS performance in each site. GPD represents the first attempt at head-wise assignment for multi-headed self-attention personalization. To preserve the unique appearance representation of each site and gradually leverage the inter-site difference, APE introduces appearance regulation and provides customized layer-wise aggregation solutions via hypernetworks for each site's personalized parameters. The mutual shape information of instruments is maintained and shared via SGE, which enhances the cross-style shape consistency on the image level and computes the shape-similarity contribution of each site on the prediction level for updating the global parameters. PFedSIS outperforms state-of-the-art methods with +1.51% Dice, +2.11% IoU, -2.79 ASSD, -15.55 HD95 performance gains. The corresponding code and models will be released at https://github.com/wzjialang/PFedSIS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03208 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic Surgery Xu, Jialang Wang, Jiacheng Yu, Lequan Stoyanov, Danail Jin, Yueming Mazomenos, Evangelos B. Computer Vision and Pattern Recognition Artificial Intelligence Robotics Medical Physics Personalized federated learning (PFL) for surgical instrument segmentation (SIS) is a promising approach. It enables multiple clinical sites to collaboratively train a series of models in privacy, with each model tailored to the individual distribution of each site. Existing PFL methods rarely consider the personalization of multi-headed self-attention, and do not account for appearance diversity and instrument shape similarity, both inherent in surgical scenes. We thus propose PFedSIS, a novel PFL method with visual trait priors for SIS, incorporating global-personalized disentanglement (GPD), appearance-regulation personalized enhancement (APE), and shape-similarity global enhancement (SGE), to boost SIS performance in each site. GPD represents the first attempt at head-wise assignment for multi-headed self-attention personalization. To preserve the unique appearance representation of each site and gradually leverage the inter-site difference, APE introduces appearance regulation and provides customized layer-wise aggregation solutions via hypernetworks for each site's personalized parameters. The mutual shape information of instruments is maintained and shared via SGE, which enhances the cross-style shape consistency on the image level and computes the shape-similarity contribution of each site on the prediction level for updating the global parameters. PFedSIS outperforms state-of-the-art methods with +1.51% Dice, +2.11% IoU, -2.79 ASSD, -15.55 HD95 performance gains. The corresponding code and models will be released at https://github.com/wzjialang/PFedSIS. |
| title | Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic Surgery |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics Medical Physics |
| url | https://arxiv.org/abs/2408.03208 |