Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.10526 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915243224989696 |
|---|---|
| author | Zhu, Mingyang Liu, Yinting Li, Mingyu Wang, Jiacheng |
| author_facet | Zhu, Mingyang Liu, Yinting Li, Mingyu Wang, Jiacheng |
| contents | Current methods for pathology image segmentation typically treat 2D slices independently, ignoring valuable cross-slice information. We present PathSeqSAM, a novel approach that treats 2D pathology slices as sequential video frames using SAM2's memory mechanisms. Our method introduces a distance-aware attention mechanism that accounts for variable physical distances between slices and employs LoRA for domain adaptation. Evaluated on the KPI Challenge 2024 dataset for glomeruli segmentation, PathSeqSAM demonstrates improved segmentation quality, particularly in challenging cases that benefit from cross-slice context. We have publicly released our code at https://github.com/JackyyyWang/PathSeqSAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10526 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PathSeqSAM: Sequential Modeling for Pathology Image Segmentation with SAM2 Zhu, Mingyang Liu, Yinting Li, Mingyu Wang, Jiacheng Image and Video Processing Computer Vision and Pattern Recognition Current methods for pathology image segmentation typically treat 2D slices independently, ignoring valuable cross-slice information. We present PathSeqSAM, a novel approach that treats 2D pathology slices as sequential video frames using SAM2's memory mechanisms. Our method introduces a distance-aware attention mechanism that accounts for variable physical distances between slices and employs LoRA for domain adaptation. Evaluated on the KPI Challenge 2024 dataset for glomeruli segmentation, PathSeqSAM demonstrates improved segmentation quality, particularly in challenging cases that benefit from cross-slice context. We have publicly released our code at https://github.com/JackyyyWang/PathSeqSAM. |
| title | PathSeqSAM: Sequential Modeling for Pathology Image Segmentation with SAM2 |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10526 |