Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.07652 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910996016136192 |
|---|---|
| author | Cheng, Hangbei Dong, Xiaorong Liu, Xueyu Zhang, Jianan Ma, Xuetao Wei, Mingqiang Wang, Liansheng Chen, Junxin Wu, Yongfei |
| author_facet | Cheng, Hangbei Dong, Xiaorong Liu, Xueyu Zhang, Jianan Ma, Xuetao Wei, Mingqiang Wang, Liansheng Chen, Junxin Wu, Yongfei |
| contents | Accurate lesion segmentation in histopathology images is essential for diagnostic interpretation and quantitative analysis, yet it remains challenging due to the limited availability of costly pixel-level annotations. To address this, we propose FMaMIL, a novel two-stage framework for weakly supervised lesion segmentation based solely on image-level labels. In the first stage, a lightweight Mamba-based encoder is introduced to capture long-range dependencies across image patches under the MIL paradigm. To enhance spatial sensitivity and structural awareness, we design a learnable frequency-domain encoding module that supplements spatial-domain features with spectrum-based information. CAMs generated in this stage are used to guide segmentation training. In the second stage, we refine the initial pseudo labels via a CAM-guided soft-label supervision and a self-correction mechanism, enabling robust training even under label noise. Extensive experiments on both public and private histopathology datasets demonstrate that FMaMIL outperforms state-of-the-art weakly supervised methods without relying on pixel-level annotations, validating its effectiveness and potential for digital pathology applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07652 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FMaMIL: Frequency-Driven Mamba Multi-Instance Learning for Weakly Supervised Lesion Segmentation in Medical Images Cheng, Hangbei Dong, Xiaorong Liu, Xueyu Zhang, Jianan Ma, Xuetao Wei, Mingqiang Wang, Liansheng Chen, Junxin Wu, Yongfei Computer Vision and Pattern Recognition Artificial Intelligence Accurate lesion segmentation in histopathology images is essential for diagnostic interpretation and quantitative analysis, yet it remains challenging due to the limited availability of costly pixel-level annotations. To address this, we propose FMaMIL, a novel two-stage framework for weakly supervised lesion segmentation based solely on image-level labels. In the first stage, a lightweight Mamba-based encoder is introduced to capture long-range dependencies across image patches under the MIL paradigm. To enhance spatial sensitivity and structural awareness, we design a learnable frequency-domain encoding module that supplements spatial-domain features with spectrum-based information. CAMs generated in this stage are used to guide segmentation training. In the second stage, we refine the initial pseudo labels via a CAM-guided soft-label supervision and a self-correction mechanism, enabling robust training even under label noise. Extensive experiments on both public and private histopathology datasets demonstrate that FMaMIL outperforms state-of-the-art weakly supervised methods without relying on pixel-level annotations, validating its effectiveness and potential for digital pathology applications. |
| title | FMaMIL: Frequency-Driven Mamba Multi-Instance Learning for Weakly Supervised Lesion Segmentation in Medical Images |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.07652 |