DeepCAD: Deep self-supervised learning for calcium imaging denoising

Yang Tan, Haitian Zheng, Yinheng Zhu, Xiaoyun Yuan, Xing Lin, David Brady, Lu Fang.
Nature Methods. 2021 Aug 16.

github     pdf    

Introduction

Calcium imaging is inherently susceptible to detection noise especially when imaging with high frame rate or under low excitation dosage. However, calcium transients are highly dynamic, non-repetitive activities and a firing pattern cannot be captured twice. Clean images for supervised training of deep neural networks are not accessible. Here, we present DeepCAD, a deep self-supervised learning-based method for calcium imaging denoising. Using our method, detection noise can be effectively removed and the accuracy of neuron extraction and spike inference can be highly improved.

Framework

Citation

If you find this project useful for your research, please cite:

@article{li2021reinforcing,
  title={Reinforcing neuron extraction and spike inference in calcium imaging using deep self-supervised denoising},
  author={Li, Xinyang and Zhang, Guoxun and Wu, Jiamin and Zhang, Yuanlong and Zhao, Zhifeng and Lin, Xing and Qiao, Hui and Xie, Hao and Wang, Haoqian and Fang, Lu and others},
  journal={Nature Methods},
  pages={1--6},
  year={2021},
  publisher={Nature Publishing Group}
}