LSA: Latent Style Augmentation Towards Stain-Agnostic Cervical Cancer Screening
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_ | 1866916647803027456 |
|---|---|
| author | Cai, Jiangdong Jiang, Haotian Shen, Zhenrong Li, Yonghao Xiong, Honglin Zhang, Lichi Wang, Qian |
| author_facet | Cai, Jiangdong Jiang, Haotian Shen, Zhenrong Li, Yonghao Xiong, Honglin Zhang, Lichi Wang, Qian |
| contents | The deployment of computer-aided diagnosis systems for cervical cancer screening using whole slide images (WSIs) faces critical challenges due to domain shifts caused by staining variations across different scanners and imaging environments. While existing stain augmentation methods improve patch-level robustness, they fail to scale to WSIs due to two key limitations: (1) inconsistent stain patterns when extending patch operations to gigapixel slides, and (2) prohibitive computational/storage costs from offline processing of augmented WSIs.To address this, we propose Latent Style Augmentation (LSA), a framework that performs efficient, online stain augmentation directly on WSI-level latent features. We first introduce WSAug, a WSI-level stain augmentation method ensuring consistent stain across patches within a WSI. Using offline-augmented WSIs by WSAug, we design and train Stain Transformer, which can simulate targeted style in the latent space, efficiently enhancing the robustness of the WSI-level classifier. We validate our method on a multi-scanner WSI dataset for cervical cancer diagnosis. Despite being trained on data from a single scanner, our approach achieves significant performance improvements on out-of-distribution data from other scanners. Code will be available at https://github.com/caijd2000/LSA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06563 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LSA: Latent Style Augmentation Towards Stain-Agnostic Cervical Cancer Screening Cai, Jiangdong Jiang, Haotian Shen, Zhenrong Li, Yonghao Xiong, Honglin Zhang, Lichi Wang, Qian Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition The deployment of computer-aided diagnosis systems for cervical cancer screening using whole slide images (WSIs) faces critical challenges due to domain shifts caused by staining variations across different scanners and imaging environments. While existing stain augmentation methods improve patch-level robustness, they fail to scale to WSIs due to two key limitations: (1) inconsistent stain patterns when extending patch operations to gigapixel slides, and (2) prohibitive computational/storage costs from offline processing of augmented WSIs.To address this, we propose Latent Style Augmentation (LSA), a framework that performs efficient, online stain augmentation directly on WSI-level latent features. We first introduce WSAug, a WSI-level stain augmentation method ensuring consistent stain across patches within a WSI. Using offline-augmented WSIs by WSAug, we design and train Stain Transformer, which can simulate targeted style in the latent space, efficiently enhancing the robustness of the WSI-level classifier. We validate our method on a multi-scanner WSI dataset for cervical cancer diagnosis. Despite being trained on data from a single scanner, our approach achieves significant performance improvements on out-of-distribution data from other scanners. Code will be available at https://github.com/caijd2000/LSA. |
| title | LSA: Latent Style Augmentation Towards Stain-Agnostic Cervical Cancer Screening |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.06563 |