Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks
Abstract
Calcium imaging is an important technique for monitoring the activity of thousands of neurons simultaneously. As calcium imaging datasets grow in size, automated detection of individual neurons is becoming important. Here we apply a supervised learning approach to this problem and show that convolutional networks can achieve near-human accuracy and superhuman speed. Accuracy is superior to the popular PCA/ICA method based on precision and recall relative to ground truth annotation by a human expert. These results suggest that convolutional networks are an efficient and flexible tool for the analysis of large-scale calcium imaging data.
Cite
Text
Apthorpe et al. "Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks." Neural Information Processing Systems, 2016.Markdown
[Apthorpe et al. "Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks." Neural Information Processing Systems, 2016.](https://mlanthology.org/neurips/2016/apthorpe2016neurips-automatic/)BibTeX
@inproceedings{apthorpe2016neurips-automatic,
title = {{Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks}},
author = {Apthorpe, Noah and Riordan, Alexander and Aguilar, Robert and Homann, Jan and Gu, Yi and Tank, David and Seung, H. Sebastian},
booktitle = {Neural Information Processing Systems},
year = {2016},
pages = {3270-3278},
url = {https://mlanthology.org/neurips/2016/apthorpe2016neurips-automatic/}
}