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.

9 pages, 5 figures, 2 ancillary files; minor changes for camera-ready version. appears in Advances in Neural Information Processing Systems 29 (NIPS 2016)

References in corpus (1)

• ZNN - A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-Core and Many-Core Shared Memory Machines

Cited by in corpus (6)

• Fast amortized inference of neural activity from calcium imaging data with variational autoencoders
• Morphological Error Detection in 3D Segmentations
• Efficient and accurate extraction of in vivo calcium signals from microendoscopic video data
• LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
• Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
• Seeds Cleansing CNMF for Spatiotemporal Neural Signals Extraction of Miniscope Imaging Data