README 未给出安装与使用细节,需查阅官方文档;交互式功能依赖 napari 界面;使用 vit-tiny 模型或自动追踪时需额外引用对应论文

micro-sam
computational-cell-analyticsMIT活跃维护把 Segment Anything 模型适配到显微图像上的分割工具,支持细胞、细胞核、线粒体等结构的自动与交互式分割,并集成 napari 做可视化标注。
Segment Anything for Microscopy
基于 Segment Anything 的显微图像分割与追踪工具,通过 napari 界面点几下即可交互式分割细胞等目标
把 Segment Anything 模型适配到显微图像上的分割工具,支持细胞、细胞核、线粒体等结构的自动与交互式分割,并集成 napari 做可视化标注。
核心能力
- 提供 napari 插件做交互式 2D 分割
- 支持 EM 图像的交互式 3D 分割
- 支持 2D 图像数据的交互式追踪
- 提供针对显微数据的微调方法与微调模型
- 支持自动 prompt 生成(APG)与自动追踪
容易踩的坑
- v1.8.14v1.8.14 🌈最新正式版2026-09-06 · 2026-09-06 12:16 UTC
Changes
- Fix prompt clearing with napari 0.9.1 and bump version @anwai98 (#1367)
- v1.8.13v1.8.13 🌈2026-09-01 · 2026-09-01 14:50 UTC
查看更新说明
Changes
- Bump the version to 1.8.13 @anwai98 (#1362)
- Fix segment anything installation from pip @anwai98 (#1361)
- v1.8.12v1.8.12 🌈2026-08-26 · 2026-08-26 12:39 UTC
查看更新说明
Changes
- Support napari 0.9 and bump the version to 1.8.12 @anwai98 (#1352)
- v1.8.11v1.8.11 🌈2026-08-25 · 2026-08-25 17:13 UTC
查看更新说明
Changes
- Test exported decoder models via automatic instance segmentation @nilsmechtel (#1348)
- Invalidate cached image embeddings when forward() receives a different image @nilsmechtel (#1347)
- v1.8.10v1.8.10 🌈2026-08-20 · 2026-08-20 23:03 UTC
查看更新说明
Changes
- Bump version @anwai98 (#1338)
- Add automatic instance segmentation to the bioimageio model export @nilsmechtel (#1337)
- Add code of conduct and contributing guide @anwai98 (#1326)
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
Segment Anything for Microscopy
Tools for segmentation and tracking in microscopy build on top of Segment Anything. Segment and track objects in microscopy images interactively with a few clicks!
We implement napari applications for:
- interactive 2d segmentation (Left: interactive cell segmentation)
- interactive 3d segmentation (Middle: interactive mitochondria segmentation in EM)
- interactive tracking of 2d image data (Right: interactive cell tracking)
If you run into any problems or have questions regarding our tool please open an issue on Github or reach out via image.sc using the tag micro-sam, and tagging @constantinpape and @anwai98.
You can follow recent updates on micro_sam in our news feed.
Installation and Usage
Please check the documentation for details on how to install and use micro_sam. You can also watch the quickstart video, our virtual I2K workshop video or all video tutorials.
Contributing
We always welcome new contributions!
If you just want to suggest a documentation edit, you can do this directly here, on GitHub. For more complex changes, see CONTRIBUTING.md or the contributing guide in our documentation for details. The first step is to discuss your idea in a new issue with the current developers.
Everyone participating in this project is expected to follow our Code of Conduct.
Citation
If you are using this repository in your research please cite
- our paper (now published in Nature Methods!)
- and the original Segment Anything publication.
- If you use
vit-tinymodels please also cite Mobile SAM. - If you use automatic tracking, please also cite Trackastra.
- If you use automatic prompt generation (APG), please also cite our APG paper.
Related Projects
There are a few other napari plugins build around Segment Anything:
- https://github.com/MIC-DKFZ/napari-sam (2d and 3d support)
- https://github.com/royerlab/napari-segment-anything (only 2d support)
- https://github.com/hiroalchem/napari-SAM4IS
Compared to these we support more applications (2d, 3d and tracking), and provide finetuning methods and finetuned models for microscopy data. WebKnossos and QuPath also offer integration of Segment Anything for interactive segmentation.
We have also built follow-up work that is based on micro_sam:
- https://github.com/computational-cell-analytics/patho-sam - improves SAM for histopathology.
- https://github.com/computational-cell-analytics/medico-sam - improves SAM for medical imaging.
- https://github.com/computational-cell-analytics/peft-sam - studies parameter efficient fine-tuning for SAM.
Release Overview
You can find an overview of changes introduced in previous releases here.