tcVAE-Fusion: Variational Autoencoder with Temporal Condition for Effective Shape-based Calcium Imaging Neuron Registration
If you use any materials from this repository, please cite our paper:
- Cyrus Y. H. Fung, Sudipta Acharya, Tak Pan Wong, and Steven H. H. Ding. Variational Autoencoder with Temporal Conditions for Effective Shape-based Calcium Imaging Neuron Registration. In Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 6 pages, Istanbul, Turkey: December 2023.
@inproceedings{fung2023variational,
title={Variational Autoencoder with Temporal Condition for Effective Shape-based Calcium Imaging Neuron Registration},
author={Fung, Cyrus YH and Acharya, Sudipta and Wong, Tak Pan and Ding, Steven HH},
booktitle={2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
pages={1911--1916},
year={2023},
organization={IEEE}
}
Thanks to recent advances in optical imaging techniques, calcium imaging can now record the activities of thousands of neurons simultaneously, through several sessions and over long periods. Neuron registration assumes a vital role in this process, enabling the monitoring of neurons across multiple movies and extended timeframes by aligning their spatial patterns. We introduce a novel technique for cell registration, using a temporal-conditional variational autoencoder (tcVAE) for precise shape modeling. A comprehensive evaluation demonstrates that incorporating shape-related details can significantly enhance the quality of neuron registration.
The software was developed by Cyrus Y. H. Fung, and Steven H. H. Ding in the Queen's L1NNA Research Laboratory in Canada. It is distributed under the Apache License Version 2.0. Please refer to LICENSE or http://apache.org/licenses/ for details.
The software is provided as-is with no warranty or support. We do not take any responsibility for any damage, loss of income, or any problems you might experience from using our software. If you have questions, you are encouraged to consult the paper and the source code. If you find our software useful, please cite our paper above.