The Imaging Server Kit is an open-source Python package for deploying image analysis algorithms as web services.
- Run computations remotely, while client applications remain focused on visualization.
- Connect to an algorithm server and run algorithms from QuPath, Napari, and Python.
- Easily create algorithm servers for Python-based algorithms
The documentation is available on this page.
| Task | Examples | Napari | QuPath |
|---|---|---|---|
| Segmentation | StarDist, CellPose, Rembg, SAM-2, InstanSeg | ✅ | ✅ |
| Object detection | YOLO, Spotiflow, LoG detector | ✅ | ✅ |
| Vector fields | Orientationpy | ✅ | ✅ |
| Object tracking | Trackpy, Trackastra | ✅ | |
| Image-to-Image | SPAM, Noise2Void, StackReg | ✅ | |
| Text-to-Image | Stable Diffusion | ✅ | |
| Image-to-Text | Image captioning | ✅ | |
| Classification | ResNet50 | ✅ |
April 2025
The Imaging Server Kit is under construction! Here is what we're up to:
- Make the
/inforoute look nice - Handle streaming/tiling for processing whole-slide images
- Add a sample image button in the QuPath extension
- Add a server-side timeout to the
/processendpoint - Make a Fiji plugin
- Mallory Wittwer, EPFL Center for Imaging ([email protected])
- Edward Andò, EPFL Center for Imaging
- Maud Barthélémy, EPFL Center for Imaging
- Florian Aymanns, EPFL Center for Imaging
We acknowledge the Personalized Health and Related Technologies (PHRT) initiative for supporting this project.