We provide a Python package for tracking tumor nodules in mice CT scans. The project is based on Trackpy and Laptrack (algorithms from both libraries are implemented). It also provides a registration utility to align CT scans before tracking objects based on segmentation masks of the lungs cavity produced by the mouselungseg model.
[Installation] [Usage]
This project is part of a collaboration between the EPFL Center for Imaging and the De Palma Lab.
We recommend performing the installation in a clean Python environment. Install our package from PyPi:
pip install mousetumortrackor from the repository:
pip install git+https://github.com/EPFL-Center-for-Imaging/mousetumortrack.gitor clone the repository and install with:
git clone git+https://github.com/EPFL-Center-for-Imaging/mousetumortrack.git
cd mousetumortrack
pip install -e .Track tumor nodules from a labelled 3D timesereies array:
from mousetumortrack import run_tracking
# labels_timeseries is a 4D array of shape (TZYX)
linkage_df, grouped_df, labels_timeseries_tracked = run_tracking(labels_timeseries)For more details, see example.py.
If you encounter any problems, please file an issue along with a detailed description.
This project is licensed under the AGPL-3 license.
This project depends on the ultralytics package which is licensed under AGPL-3.
- Mouse Tumor Net | Detect tumor nodules in mice CT scans.
- Mouse Lungs Seg | Detect the lungs cavity in mice CT scans.
Special thanks go to Sandra Gebraiel for her contribution to the ideation and exploration of the data and for developing the preliminary code that laid the foundations for this project during the course of her lab immersion in Summer 2024.