Leveraging Spatial Context for Positive Pair Sampling in Histopathology Image Representation Learning
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_ | 1866908878584676352 |
|---|---|
| author | Robles, Willmer Rafell Quinones Noree, Sakonporn Kim, Jongwoo Ko, Young Sin Wong, Bryan Yi, Mun Yong |
| author_facet | Robles, Willmer Rafell Quinones Noree, Sakonporn Kim, Jongwoo Ko, Young Sin Wong, Bryan Yi, Mun Yong |
| contents | Deep learning has shown strong potential in cancer classification from whole-slide images (WSIs), but the need for extensive expert annotations often limits its success. Annotation-free approaches, such as multiple instance learning (MIL) and self-supervised learning (SSL), have emerged as promising alternatives to traditional annotation-based methods. However, conventional SSL methods typically rely on synthetic data augmentations, which may fail to capture the spatial structure critical to histopathology. In this work, we propose a spatial context-driven positive pair sampling strategy that enhances SSL by leveraging the morphological coherence of spatially adjacent patches within WSIs. Our method is modular and compatible with established joint embedding SSL frameworks, including Barlow Twins, BYOL, VICReg, and DINOv2. We evaluate its effectiveness on both slide-level classification using MIL and patch-level linear probing. Experiments across four datasets demonstrate consistent performance improvements, with accuracy gains of 5\% to 10\% compared to standard augmentation-based sampling. These findings highlight the value of spatial context in improving representation learning for computational pathology and provide a biologically meaningful enhancement for pretraining models in annotation-limited settings. The code is available at https://anonymous.4open.science/r/contextual-pairs-E72F/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Spatial Context for Positive Pair Sampling in Histopathology Image Representation Learning Robles, Willmer Rafell Quinones Noree, Sakonporn Kim, Jongwoo Ko, Young Sin Wong, Bryan Yi, Mun Yong Computer Vision and Pattern Recognition Deep learning has shown strong potential in cancer classification from whole-slide images (WSIs), but the need for extensive expert annotations often limits its success. Annotation-free approaches, such as multiple instance learning (MIL) and self-supervised learning (SSL), have emerged as promising alternatives to traditional annotation-based methods. However, conventional SSL methods typically rely on synthetic data augmentations, which may fail to capture the spatial structure critical to histopathology. In this work, we propose a spatial context-driven positive pair sampling strategy that enhances SSL by leveraging the morphological coherence of spatially adjacent patches within WSIs. Our method is modular and compatible with established joint embedding SSL frameworks, including Barlow Twins, BYOL, VICReg, and DINOv2. We evaluate its effectiveness on both slide-level classification using MIL and patch-level linear probing. Experiments across four datasets demonstrate consistent performance improvements, with accuracy gains of 5\% to 10\% compared to standard augmentation-based sampling. These findings highlight the value of spatial context in improving representation learning for computational pathology and provide a biologically meaningful enhancement for pretraining models in annotation-limited settings. The code is available at https://anonymous.4open.science/r/contextual-pairs-E72F/. |
| title | Leveraging Spatial Context for Positive Pair Sampling in Histopathology Image Representation Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.05170 |