Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.20326 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911532710887424 |
|---|---|
| author | Maqsood, Muhammad Hassan Zhu, Yanming Lam, Alfred Dagnaw, Getamesay Yin, Xuefei Liew, Alan Wee-Chung |
| author_facet | Maqsood, Muhammad Hassan Zhu, Yanming Lam, Alfred Dagnaw, Getamesay Yin, Xuefei Liew, Alan Wee-Chung |
| contents | Histopathology nuclei segmentation is crucial for quantitative tissue analysis and cancer diagnosis. Although existing segmentation methods have achieved strong performance, they are often computationally heavy and show limited generalization across datasets, which constrains their practical deployment. Recent SAM-based approaches have shown great potential in general and medical imaging, but typically rely on prompt guidance or complex decoders, making them less suitable for histopathology images with dense nuclei and heterogeneous appearances. We propose a prompt-free and lightweight SAM adaptation that leverages multi-level encoder features and residual decoding for accurate and efficient nuclei segmentation. The framework fine-tunes only LoRA modules within the frozen SAM encoder, requiring just 4.1M trainable parameters. Experiments on three benchmark datasets TNBC, MoNuSeg, and PanNuke demonstrate state-of-the-art performance and strong cross-dataset generalization, highlighting the effectiveness and practicality of the proposed framework for histopathology applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20326 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Prompt-Free Lightweight SAM Adaptation for Histopathology Nuclei Segmentation with Strong Cross-Dataset Generalization Maqsood, Muhammad Hassan Zhu, Yanming Lam, Alfred Dagnaw, Getamesay Yin, Xuefei Liew, Alan Wee-Chung Computer Vision and Pattern Recognition Histopathology nuclei segmentation is crucial for quantitative tissue analysis and cancer diagnosis. Although existing segmentation methods have achieved strong performance, they are often computationally heavy and show limited generalization across datasets, which constrains their practical deployment. Recent SAM-based approaches have shown great potential in general and medical imaging, but typically rely on prompt guidance or complex decoders, making them less suitable for histopathology images with dense nuclei and heterogeneous appearances. We propose a prompt-free and lightweight SAM adaptation that leverages multi-level encoder features and residual decoding for accurate and efficient nuclei segmentation. The framework fine-tunes only LoRA modules within the frozen SAM encoder, requiring just 4.1M trainable parameters. Experiments on three benchmark datasets TNBC, MoNuSeg, and PanNuke demonstrate state-of-the-art performance and strong cross-dataset generalization, highlighting the effectiveness and practicality of the proposed framework for histopathology applications. |
| title | Prompt-Free Lightweight SAM Adaptation for Histopathology Nuclei Segmentation with Strong Cross-Dataset Generalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.20326 |