PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings
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_ | 1866908376318869504 |
|---|---|
| author | Chin, Sinchee Ma, Yinuo Yang, Xiaochen Xue, Jing-Hao Yang, Wenming |
| author_facet | Chin, Sinchee Ma, Yinuo Yang, Xiaochen Xue, Jing-Hao Yang, Wenming |
| contents | Unsupervised pathology detection trains models on non-pathological data to flag deviations as pathologies, offering strong generalizability for identifying novel diseases and avoiding costly annotations. However, building reliable normality models requires vast healthy datasets, as hospitals' data is inherently biased toward symptomatic populations, while privacy regulations hinder the assembly of representative healthy cohorts. To address this limitation, we propose PathoSCOPE, a few-shot unsupervised pathology detection framework that requires only a small set of non-pathological samples (minimum 2 shots), significantly improving data efficiency. We introduce Global-Local Contrastive Loss (GLCL), comprised of a Local Contrastive Loss to reduce the variability of non-pathological embeddings and a Global Contrastive Loss to enhance the discrimination of pathological regions. We also propose a Pathology-informed Embedding Generation (PiEG) module that synthesizes pathological embeddings guided by the global loss, better exploiting the limited non-pathological samples. Evaluated on the BraTS2020 and ChestXray8 datasets, PathoSCOPE achieves state-of-the-art performance among unsupervised methods while maintaining computational efficiency (2.48 GFLOPs, 166 FPS). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17614 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings Chin, Sinchee Ma, Yinuo Yang, Xiaochen Xue, Jing-Hao Yang, Wenming Computer Vision and Pattern Recognition Unsupervised pathology detection trains models on non-pathological data to flag deviations as pathologies, offering strong generalizability for identifying novel diseases and avoiding costly annotations. However, building reliable normality models requires vast healthy datasets, as hospitals' data is inherently biased toward symptomatic populations, while privacy regulations hinder the assembly of representative healthy cohorts. To address this limitation, we propose PathoSCOPE, a few-shot unsupervised pathology detection framework that requires only a small set of non-pathological samples (minimum 2 shots), significantly improving data efficiency. We introduce Global-Local Contrastive Loss (GLCL), comprised of a Local Contrastive Loss to reduce the variability of non-pathological embeddings and a Global Contrastive Loss to enhance the discrimination of pathological regions. We also propose a Pathology-informed Embedding Generation (PiEG) module that synthesizes pathological embeddings guided by the global loss, better exploiting the limited non-pathological samples. Evaluated on the BraTS2020 and ChestXray8 datasets, PathoSCOPE achieves state-of-the-art performance among unsupervised methods while maintaining computational efficiency (2.48 GFLOPs, 166 FPS). |
| title | PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.17614 |