Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.24251 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908856307679232 |
|---|---|
| author | Zhang, Xiaolong Zhang, Jianwei Sevim, Selim Demir, Emek Eksi, Ece Song, Xubo |
| author_facet | Zhang, Xiaolong Zhang, Jianwei Sevim, Selim Demir, Emek Eksi, Ece Song, Xubo |
| contents | Batch effects arising from technical variations in histopathology staining protocols, scanners, and acquisition pipelines pose a persistent challenge for computational pathology, hindering cross-batch generalization and limiting reliable deployment of models across clinical sites. In this work, we introduce Latent Manifold Compaction (LMC), an unsupervised representation learning framework that performs image harmonization by learning batch-invariant embeddings from a single source dataset through explicit compaction of stain-induced latent manifolds. This allows LMC to generalize to target domain data unseen during training. Evaluated on three challenging public and in-house benchmarks, LMC substantially reduces batch-induced separations across multiple datasets and consistently outperforms state-of-the-art normalization methods in downstream cross-batch classification and detection tasks, enabling superior generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_24251 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Histopathology Image Normalization via Latent Manifold Compaction Zhang, Xiaolong Zhang, Jianwei Sevim, Selim Demir, Emek Eksi, Ece Song, Xubo Machine Learning Computer Vision and Pattern Recognition Batch effects arising from technical variations in histopathology staining protocols, scanners, and acquisition pipelines pose a persistent challenge for computational pathology, hindering cross-batch generalization and limiting reliable deployment of models across clinical sites. In this work, we introduce Latent Manifold Compaction (LMC), an unsupervised representation learning framework that performs image harmonization by learning batch-invariant embeddings from a single source dataset through explicit compaction of stain-induced latent manifolds. This allows LMC to generalize to target domain data unseen during training. Evaluated on three challenging public and in-house benchmarks, LMC substantially reduces batch-induced separations across multiple datasets and consistently outperforms state-of-the-art normalization methods in downstream cross-batch classification and detection tasks, enabling superior generalization. |
| title | Histopathology Image Normalization via Latent Manifold Compaction |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.24251 |