MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
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_ | 1866912622701445120 |
|---|---|
| author | Xu, Meilong Hu, Xiaoling Abousamra, Shahira Li, Chen Chen, Chao |
| author_facet | Xu, Meilong Hu, Xiaoling Abousamra, Shahira Li, Chen Chen, Chao |
| contents | In semi-supervised segmentation, capturing meaningful semantic structures from unlabeled data is essential. This is particularly challenging in histopathology image analysis, where objects are densely distributed. To address this issue, we propose a semi-supervised segmentation framework designed to robustly identify and preserve relevant topological features. Our method leverages multiple perturbed predictions obtained through stochastic dropouts and temporal training snapshots, enforcing topological consistency across these varied outputs. This consistency mechanism helps distinguish biologically meaningful structures from transient and noisy artifacts. A key challenge in this process is to accurately match the corresponding topological features across the predictions in the absence of ground truth. To overcome this, we introduce a novel matching strategy that integrates spatial overlap with global structural alignment, minimizing discrepancies among predictions. Extensive experiments demonstrate that our approach effectively reduces topological errors, resulting in more robust and accurate segmentations essential for reliable downstream analysis. Code is available at \href{https://github.com/Melon-Xu/MATCH}{https://github.com/Melon-Xu/MATCH}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01532 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation Xu, Meilong Hu, Xiaoling Abousamra, Shahira Li, Chen Chen, Chao Computer Vision and Pattern Recognition In semi-supervised segmentation, capturing meaningful semantic structures from unlabeled data is essential. This is particularly challenging in histopathology image analysis, where objects are densely distributed. To address this issue, we propose a semi-supervised segmentation framework designed to robustly identify and preserve relevant topological features. Our method leverages multiple perturbed predictions obtained through stochastic dropouts and temporal training snapshots, enforcing topological consistency across these varied outputs. This consistency mechanism helps distinguish biologically meaningful structures from transient and noisy artifacts. A key challenge in this process is to accurately match the corresponding topological features across the predictions in the absence of ground truth. To overcome this, we introduce a novel matching strategy that integrates spatial overlap with global structural alignment, minimizing discrepancies among predictions. Extensive experiments demonstrate that our approach effectively reduces topological errors, resulting in more robust and accurate segmentations essential for reliable downstream analysis. Code is available at \href{https://github.com/Melon-Xu/MATCH}{https://github.com/Melon-Xu/MATCH}. |
| title | MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.01532 |