Saved in:
Bibliographic Details
Main Authors: Cheng, Hangbei, Dong, Xiaorong, Liu, Xueyu, Zhang, Jianan, Ma, Xuetao, Wei, Mingqiang, Wang, Liansheng, Chen, Junxin, Wu, Yongfei
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