Fractal tasks core is the official task package for the Fractal framework. It provides essential tools for building Fractal tasks, helpful utility functions, and a collection of ready-to-use tasks for processing bioimaging data. These tasks include OME-Zarr conversion, image registration, segmentation, and measurements.
Fractal is a framework developed at the BioVisionCenter to process bioimaging data at scale in the OME-Zarr format and prepare the images for interactive visualization.
This repository includes several core sub-packages:
The NGFF, Tables & ROI Sub-package functionality will get replaced by functionality in ngio over the coming months.
See https://fractal-analytics-platform.github.io/fractal-tasks-core
This package includes the following tasks:
Image Conversion:
Image Processing:
Segmentation:
Registration:
Measurements:
Other Utilities:
To install and use the library components, run:
pip install fractal-tasks-core
This will install the core library, including all sub-packages for working with NGFF metadata, tables, ROIs, and more.
If you intend to run Fractal tasks (such as segmentation or registration), install with the additional task dependencies:
pip install "fractal-tasks-core[fractal-tasks]"
This includes larger dependencies such as Torch (for Cellpose) and Napari (for Napari workflows).
If you collect this package on Fractal server to run the task, make sure to add the fractal-tasks extra in the corresponding field for extras.
Fractal was conceived in the Liberali Lab at the Friedrich Miescher Institute for Biomedical Research and in the Pelkmans Lab at the University of Zurich by @jluethi and @gusqgm. The Fractal project is now developed at the BioVisionCenter at the University of Zurich and the project lead is with @jluethi. The core development is done under contract by eXact lab S.r.l..
Unless otherwise specified, Fractal components are released under the BSD 3-Clause License, and copyright is with the BioVisionCenter at the University of Zurich.