Shortcuts

About Us

This project was started by Zudi Lin (@zudi-lin) and Donglai Wei (@donglaiw) in 2019 and supported by the Visual Computing Group (VCG) at Harvard University. PyTorch Connectomics is currently under active development, and besides handling connectomics data collected with electron microscopy (EM), we are extending the application to other biological structures and more imaging modalities (e.g., micro-CT, fluorescence light microscopy).

Authors

The following people are currently core contributors to PyTorch Connectomics’s development and maintenance:

  • Zudi Lin - Applied Scientist at Amazon. Previous Ph.D. student in the Visual Computing Group at Harvard University.

  • Donglai Wei - Assistant Professor of Computer Science at Boston College. Previous postdoctoral fellow in the Visual Computing Group at Harvard University.

Advisors

The following people regularly provide suggestions on the design and future directions of the package:

  • Hanspeter Pfister - Professor of Computer Science, Harvard University

  • Jeff Lichtman - Professor of Molecular and Cellular Biology, Harvard University

Contributing

We would like to thank all current and previous contributors to the PyTorch Connectomics package.

We are looking for motivated contributors to become collaborators and help out with the project. Besides opening issues and pull request on Github, please join our Slack community to discuss bugs and feature requests. If you are interested in working on this project as a research intern at Harvard University or Boston College, please contact Prof. Donglai Wei or Prof. Hanspeter Pfister via email for more details.

Citation

Please read this technical report for a detailed description of the framework. If you use PyTorch Connectomics (PyTC) in a scientific publication, we would appreciate citations to the project.

@article{lin2021pytorch,
    title={PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics},
    author={Lin, Zudi and Wei, Donglai and Lichtman, Jeff and Pfister, Hanspeter},
    journal={arXiv preprint arXiv:2112.05754},
    year={2021}
}

We gratefully acknowledge the support from NSF awards IIS-1835231 and IIS-2124179.